diff --git a/cli/cloud/agent.mdx b/api-reference/cli/cloud/agent.mdx similarity index 100% rename from cli/cloud/agent.mdx rename to api-reference/cli/cloud/agent.mdx diff --git a/cli/cloud/auth.mdx b/api-reference/cli/cloud/auth.mdx similarity index 100% rename from cli/cloud/auth.mdx rename to api-reference/cli/cloud/auth.mdx diff --git a/cli/cloud/build.mdx b/api-reference/cli/cloud/build.mdx similarity index 94% rename from cli/cloud/build.mdx rename to api-reference/cli/cloud/build.mdx index c11be07d2..c3f46daf1 100644 --- a/cli/cloud/build.mdx +++ b/api-reference/cli/cloud/build.mdx @@ -5,7 +5,7 @@ description: "Manage cloud builds" The `build` command provides tools for managing cloud builds on Pipecat Cloud. You can view build logs, check build status, and list recent builds. -Cloud builds are typically triggered automatically when you run [`pipecat cloud deploy`](/cli/cloud/deploy) without specifying an image. These commands help you monitor and manage those builds. +Cloud builds are typically triggered automatically when you run [`pipecat cloud deploy`](/api-reference/cli/cloud/deploy) without specifying an image. These commands help you monitor and manage those builds. ## logs diff --git a/cli/cloud/deploy.mdx b/api-reference/cli/cloud/deploy.mdx similarity index 98% rename from cli/cloud/deploy.mdx rename to api-reference/cli/cloud/deploy.mdx index e741d2b37..fbcb0b924 100644 --- a/cli/cloud/deploy.mdx +++ b/api-reference/cli/cloud/deploy.mdx @@ -72,7 +72,7 @@ pipecat cloud deploy [ARGS] [OPTIONS] - `tel`: Telephony model (up to 16kHz) - `pro`: WebRTC model (up to 32kHz) -In addition to this flag, you also need to enable the `KrispVivaFilter()` for your transport. See the [Krisp VIVA](/server/utilities/audio/krisp-viva-filter) documentation for more information. +In addition to this flag, you also need to enable the `KrispVivaFilter()` for your transport. See the [Krisp VIVA](/api-reference/server/utilities/audio/krisp-viva-filter) documentation for more information. diff --git a/cli/cloud/docker.mdx b/api-reference/cli/cloud/docker.mdx similarity index 100% rename from cli/cloud/docker.mdx rename to api-reference/cli/cloud/docker.mdx diff --git a/cli/cloud/organizations.mdx b/api-reference/cli/cloud/organizations.mdx similarity index 100% rename from cli/cloud/organizations.mdx rename to api-reference/cli/cloud/organizations.mdx diff --git a/cli/cloud/regions.mdx b/api-reference/cli/cloud/regions.mdx similarity index 100% rename from cli/cloud/regions.mdx rename to api-reference/cli/cloud/regions.mdx diff --git a/cli/cloud/secrets.mdx b/api-reference/cli/cloud/secrets.mdx similarity index 100% rename from cli/cloud/secrets.mdx rename to api-reference/cli/cloud/secrets.mdx diff --git a/cli/init.mdx b/api-reference/cli/init.mdx similarity index 100% rename from cli/init.mdx rename to api-reference/cli/init.mdx diff --git a/cli/overview.mdx b/api-reference/cli/overview.mdx similarity index 63% rename from cli/overview.mdx rename to api-reference/cli/overview.mdx index 41ad3d51c..cc8aeb0a1 100644 --- a/cli/overview.mdx +++ b/api-reference/cli/overview.mdx @@ -4,13 +4,13 @@ description: "Command-line tool for scaffolding, deploying, and monitoring Pipec --- - + Create new phone or web/mobile bots with interactive setup - + Push your bots to production with one command - + Watch real-time logs, conversations, and metrics @@ -39,11 +39,11 @@ pipecat --version ## Commands -**[`pipecat init`](/cli/init)** - Scaffold new projects with interactive setup +**[`pipecat init`](/api-reference/cli/init)** - Scaffold new projects with interactive setup -**[`pipecat tail`](/cli/tail)** - Monitor sessions in real-time with a terminal dashboard +**[`pipecat tail`](/api-reference/cli/tail)** - Monitor sessions in real-time with a terminal dashboard -**[`pipecat cloud`](/cli/cloud/auth)** - Deploy and manage bots on Pipecat Cloud +**[`pipecat cloud`](/api-reference/cli/cloud/auth)** - Deploy and manage bots on Pipecat Cloud ## Getting Help @@ -58,6 +58,6 @@ pipecat cloud --help ## Next Steps - + Scaffold a new project with pipecat init diff --git a/cli/tail.mdx b/api-reference/cli/tail.mdx similarity index 100% rename from cli/tail.mdx rename to api-reference/cli/tail.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-create.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-create.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-create.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-create.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-delete.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-delete.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-delete.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-delete.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-get-logs.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-logs.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-get-logs.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-logs.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-get-session.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-session.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-get-session.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-session.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-get-sessions.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-sessions.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-get-sessions.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-sessions.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-list-all.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-all.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-list-all.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-all.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-list-one.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-one.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-list-one.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-one.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/agent-update.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/agent-update.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/agent-update.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/agent-update.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/build-create.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/build-create.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/build-create.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/build-create.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/build-get-logs.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/build-get-logs.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/build-get-logs.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/build-get-logs.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/build-get.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/build-get.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/build-get.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/build-get.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/build-list.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/build-list.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/build-list.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/build-list.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/build-upload-url.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/build-upload-url.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/build-upload-url.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/build-upload-url.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/properties-get.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/properties-get.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/properties-get.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/properties-get.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/properties-update.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/properties-update.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/properties-update.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/properties-update.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/regions-list.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/regions-list.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/regions-list.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/regions-list.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/secret-create-update.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/secret-create-update.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/secret-create-update.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/secret-create-update.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/secret-list-all.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-all.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/secret-list-all.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-all.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/secret-list-one.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-one.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/secret-list-one.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-one.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/session-proxy.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/session-proxy.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/session-proxy.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/session-proxy.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/start.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/start.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/start.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/start.mdx diff --git a/pipecat-cloud/rest-reference/endpoint/stop.mdx b/api-reference/pipecat-cloud/rest-reference/endpoint/stop.mdx similarity index 100% rename from pipecat-cloud/rest-reference/endpoint/stop.mdx rename to api-reference/pipecat-cloud/rest-reference/endpoint/stop.mdx diff --git a/pipecat-cloud/rest-reference/openapi-agent-create.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-create.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-create.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-create.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-delete.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-delete.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-delete.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-delete.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-get-logs.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-get-logs.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-get-logs.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-get-logs.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-get-session.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-get-session.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-get-session.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-get-session.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-get-sessions.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-get-sessions.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-get-sessions.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-get-sessions.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-list-all.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-list-all.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-list-all.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-list-all.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-list-one.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-list-one.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-list-one.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-list-one.json diff --git a/pipecat-cloud/rest-reference/openapi-agent-update.json b/api-reference/pipecat-cloud/rest-reference/openapi-agent-update.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-agent-update.json rename to api-reference/pipecat-cloud/rest-reference/openapi-agent-update.json diff --git a/pipecat-cloud/rest-reference/openapi-build-create.json b/api-reference/pipecat-cloud/rest-reference/openapi-build-create.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-build-create.json rename to api-reference/pipecat-cloud/rest-reference/openapi-build-create.json diff --git a/pipecat-cloud/rest-reference/openapi-build-get-logs.json b/api-reference/pipecat-cloud/rest-reference/openapi-build-get-logs.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-build-get-logs.json rename to api-reference/pipecat-cloud/rest-reference/openapi-build-get-logs.json diff --git a/pipecat-cloud/rest-reference/openapi-build-get.json b/api-reference/pipecat-cloud/rest-reference/openapi-build-get.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-build-get.json rename to api-reference/pipecat-cloud/rest-reference/openapi-build-get.json diff --git a/pipecat-cloud/rest-reference/openapi-build-list.json b/api-reference/pipecat-cloud/rest-reference/openapi-build-list.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-build-list.json rename to api-reference/pipecat-cloud/rest-reference/openapi-build-list.json diff --git a/pipecat-cloud/rest-reference/openapi-build-upload-url.json b/api-reference/pipecat-cloud/rest-reference/openapi-build-upload-url.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-build-upload-url.json rename to api-reference/pipecat-cloud/rest-reference/openapi-build-upload-url.json diff --git a/pipecat-cloud/rest-reference/openapi-properties-get.json b/api-reference/pipecat-cloud/rest-reference/openapi-properties-get.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-properties-get.json rename to api-reference/pipecat-cloud/rest-reference/openapi-properties-get.json diff --git a/pipecat-cloud/rest-reference/openapi-properties-update.json b/api-reference/pipecat-cloud/rest-reference/openapi-properties-update.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-properties-update.json rename to api-reference/pipecat-cloud/rest-reference/openapi-properties-update.json diff --git a/pipecat-cloud/rest-reference/openapi-regions-list.json b/api-reference/pipecat-cloud/rest-reference/openapi-regions-list.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-regions-list.json rename to api-reference/pipecat-cloud/rest-reference/openapi-regions-list.json diff --git a/pipecat-cloud/rest-reference/openapi-secret-create-update.json b/api-reference/pipecat-cloud/rest-reference/openapi-secret-create-update.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-secret-create-update.json rename to api-reference/pipecat-cloud/rest-reference/openapi-secret-create-update.json diff --git a/pipecat-cloud/rest-reference/openapi-secret-delete-secret-set.json b/api-reference/pipecat-cloud/rest-reference/openapi-secret-delete-secret-set.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-secret-delete-secret-set.json rename to api-reference/pipecat-cloud/rest-reference/openapi-secret-delete-secret-set.json diff --git a/pipecat-cloud/rest-reference/openapi-secret-delete-specific-secret.json b/api-reference/pipecat-cloud/rest-reference/openapi-secret-delete-specific-secret.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-secret-delete-specific-secret.json rename to api-reference/pipecat-cloud/rest-reference/openapi-secret-delete-specific-secret.json diff --git a/pipecat-cloud/rest-reference/openapi-secret-list-all.json b/api-reference/pipecat-cloud/rest-reference/openapi-secret-list-all.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-secret-list-all.json rename to api-reference/pipecat-cloud/rest-reference/openapi-secret-list-all.json diff --git a/pipecat-cloud/rest-reference/openapi-secret-list-one.json b/api-reference/pipecat-cloud/rest-reference/openapi-secret-list-one.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-secret-list-one.json rename to api-reference/pipecat-cloud/rest-reference/openapi-secret-list-one.json diff --git a/pipecat-cloud/rest-reference/openapi-session-proxy.json b/api-reference/pipecat-cloud/rest-reference/openapi-session-proxy.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-session-proxy.json rename to api-reference/pipecat-cloud/rest-reference/openapi-session-proxy.json diff --git a/pipecat-cloud/rest-reference/openapi-start.json b/api-reference/pipecat-cloud/rest-reference/openapi-start.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-start.json rename to api-reference/pipecat-cloud/rest-reference/openapi-start.json diff --git a/pipecat-cloud/rest-reference/openapi-stop.json b/api-reference/pipecat-cloud/rest-reference/openapi-stop.json similarity index 100% rename from pipecat-cloud/rest-reference/openapi-stop.json rename to api-reference/pipecat-cloud/rest-reference/openapi-stop.json diff --git a/pipecat-cloud/sdk-reference/examples.mdx b/api-reference/pipecat-cloud/sdk-reference/examples.mdx similarity index 100% rename from pipecat-cloud/sdk-reference/examples.mdx rename to api-reference/pipecat-cloud/sdk-reference/examples.mdx diff --git a/pipecat-cloud/sdk-reference/exceptions.mdx b/api-reference/pipecat-cloud/sdk-reference/exceptions.mdx similarity index 100% rename from pipecat-cloud/sdk-reference/exceptions.mdx rename to api-reference/pipecat-cloud/sdk-reference/exceptions.mdx diff --git a/pipecat-cloud/sdk-reference/overview.mdx b/api-reference/pipecat-cloud/sdk-reference/overview.mdx similarity index 100% rename from pipecat-cloud/sdk-reference/overview.mdx rename to api-reference/pipecat-cloud/sdk-reference/overview.mdx diff --git a/pipecat-cloud/sdk-reference/session-arguments.mdx b/api-reference/pipecat-cloud/sdk-reference/session-arguments.mdx similarity index 100% rename from pipecat-cloud/sdk-reference/session-arguments.mdx rename to api-reference/pipecat-cloud/sdk-reference/session-arguments.mdx diff --git a/pipecat-cloud/sdk-reference/sessions.mdx b/api-reference/pipecat-cloud/sdk-reference/sessions.mdx similarity index 100% rename from pipecat-cloud/sdk-reference/sessions.mdx rename to api-reference/pipecat-cloud/sdk-reference/sessions.mdx diff --git a/pipecat-flows/reference/exceptions.mdx b/api-reference/pipecat-flows/exceptions.mdx similarity index 100% rename from pipecat-flows/reference/exceptions.mdx rename to api-reference/pipecat-flows/exceptions.mdx diff --git a/pipecat-flows/reference/flow-manager.mdx b/api-reference/pipecat-flows/flow-manager.mdx similarity index 97% rename from pipecat-flows/reference/flow-manager.mdx rename to api-reference/pipecat-flows/flow-manager.mdx index 8081a774f..f64e95b75 100644 --- a/pipecat-flows/reference/flow-manager.mdx +++ b/api-reference/pipecat-flows/flow-manager.mdx @@ -34,9 +34,9 @@ All parameters are keyword-only. > Default context strategy for managing conversation context during node transitions. Can be overridden per-node via - [`NodeConfig.context_strategy`](/pipecat-flows/reference/types#nodeconfig). + [`NodeConfig.context_strategy`](/api-reference/pipecat-flows/types#nodeconfig). See - [ContextStrategyConfig](/pipecat-flows/reference/types#contextstrategyconfig). + [ContextStrategyConfig](/api-reference/pipecat-flows/types#contextstrategyconfig). diff --git a/pipecat-flows/reference/overview.mdx b/api-reference/pipecat-flows/overview.mdx similarity index 91% rename from pipecat-flows/reference/overview.mdx rename to api-reference/pipecat-flows/overview.mdx index 28268b4f9..80b81ec0b 100644 --- a/pipecat-flows/reference/overview.mdx +++ b/api-reference/pipecat-flows/overview.mdx @@ -62,18 +62,18 @@ pip install "pipecat-ai[daily,openai,deepgram,cartesia,silero]" Core orchestration class: constructor, properties, and methods - + NodeConfig, FlowsFunctionSchema, ActionConfig, context strategies, and type aliases Error handling hierarchy for flow management @@ -91,7 +91,7 @@ Create transitions between conversation states, optionally processing data first ### Direct Functions -Functions passed directly to NodeConfig with automatic metadata extraction from signatures and docstrings. See [`flows_direct_function`](/pipecat-flows/reference/types#flows_direct_function-decorator) and [`FlowsDirectFunction`](/pipecat-flows/reference/types#flowsdirectfunction). +Functions passed directly to NodeConfig with automatic metadata extraction from signatures and docstrings. See [`flows_direct_function`](/api-reference/pipecat-flows/types#flows_direct_function-decorator) and [`FlowsDirectFunction`](/api-reference/pipecat-flows/types#flowsdirectfunction). ## LLM Provider Support diff --git a/pipecat-flows/reference/types.mdx b/api-reference/pipecat-flows/types.mdx similarity index 98% rename from pipecat-flows/reference/types.mdx rename to api-reference/pipecat-flows/types.mdx index 81f16c965..1f07a512d 100644 --- a/pipecat-flows/reference/types.mdx +++ b/api-reference/pipecat-flows/types.mdx @@ -55,7 +55,7 @@ Configuration for a single node in a conversation flow. `task_messages` is the o List of function definitions available in this node. Accepts provider-specific dict format, [`FlowsFunctionSchema`](#flowsfunctionschema) objects, or [direct functions](#flowsdirectfunction). See [Function - Types](/pipecat-flows/reference/overview#function-types). + Types](/api-reference/pipecat-flows/overview#function-types). @@ -72,7 +72,7 @@ Configuration for a single node in a conversation flow. `task_messages` is the o Strategy for managing conversation context when transitioning to this node. Overrides the default strategy set on - [FlowManager](/pipecat-flows/reference/flow-manager). See + [FlowManager](/api-reference/pipecat-flows/flow-manager). See [ContextStrategyConfig](#contextstrategyconfig). @@ -179,7 +179,7 @@ TypedDict for configuring actions that execute during node transitions. Action handler function. Required for custom action types if not previously registered via - [`FlowManager.register_action()`](/pipecat-flows/reference/flow-manager#register_action). + [`FlowManager.register_action()`](/api-reference/pipecat-flows/flow-manager#register_action). Can be a legacy handler `(action)` or modern handler `(action, flow_manager)`. diff --git a/server/events/frame-processor-events.mdx b/api-reference/server/events/frame-processor-events.mdx similarity index 94% rename from server/events/frame-processor-events.mdx rename to api-reference/server/events/frame-processor-events.mdx index bb4874af9..7a7cbb994 100644 --- a/server/events/frame-processor-events.mdx +++ b/api-reference/server/events/frame-processor-events.mdx @@ -147,6 +147,6 @@ async def on_after_push(processor, frame): ## Related -- [Events](/server/events/overview) - Overview of all events in Pipecat -- [PipelineTask](/server/pipeline/pipeline-task#event-handlers) - Pipeline lifecycle events -- [Observer Pattern](/server/utilities/observers/observer-pattern) - Non-intrusive pipeline monitoring +- [Events](/api-reference/server/events/overview) - Overview of all events in Pipecat +- [PipelineTask](/api-reference/server/pipeline/pipeline-task#event-handlers) - Pipeline lifecycle events +- [Observer Pattern](/api-reference/server/utilities/observers/observer-pattern) - Non-intrusive pipeline monitoring diff --git a/server/events/overview.mdx b/api-reference/server/events/overview.mdx similarity index 94% rename from server/events/overview.mdx rename to api-reference/server/events/overview.mdx index 5e24d4a47..7f31bdab5 100644 --- a/server/events/overview.mdx +++ b/api-reference/server/events/overview.mdx @@ -77,7 +77,7 @@ The table below lists all events available in Pipecat, grouped by component. Cli ### Pipeline -Events on [`PipelineTask`](/server/pipeline/pipeline-task#event-handlers). +Events on [`PipelineTask`](/api-reference/server/pipeline/pipeline-task#event-handlers). | Event | Description | | ----------------------------- | ---------------------------------------------------------------- | @@ -90,7 +90,7 @@ Events on [`PipelineTask`](/server/pipeline/pipeline-task#event-handlers). ### Frame Processor -Events on every [`FrameProcessor`](/server/events/frame-processor-events). Since all services, transports, and processors inherit from `FrameProcessor`, these events are available on any processor in your pipeline. +Events on every [`FrameProcessor`](/api-reference/server/events/frame-processor-events). Since all services, transports, and processors inherit from `FrameProcessor`, these events are available on any processor in your pipeline. | Event | Description | | ------------------------- | --------------------------------------------------- | @@ -102,7 +102,7 @@ Events on every [`FrameProcessor`](/server/events/frame-processor-events). Since ### Turn Management -Events on context aggregators from [`LLMContextAggregatorPair`](/server/utilities/turn-management/turn-events). +Events on context aggregators from [`LLMContextAggregatorPair`](/api-reference/server/utilities/turn-management/turn-events). | Event | Emitter | Description | | --------------------------- | ---------------------- | --------------------------------------------------- | @@ -118,7 +118,7 @@ Events on context aggregators from [`LLMContextAggregatorPair`](/server/utilitie ### STT Services -Events on STT service instances. Available on all WebSocket-based STT services. See [Service Events](/server/events/service-events) for details. +Events on STT service instances. Available on all WebSocket-based STT services. See [Service Events](/api-reference/server/events/service-events) for details. | Event | Description | | --------------------- | ----------------------------------- | @@ -161,7 +161,7 @@ Some STT services have additional events: ### TTS Services -Events on TTS service instances. Available on all WebSocket-based TTS services. See [Service Events](/server/events/service-events) for details. +Events on TTS service instances. Available on all WebSocket-based TTS services. See [Service Events](/api-reference/server/events/service-events) for details. | Event | Description | | --------------------- | ------------------------------------- | @@ -172,7 +172,7 @@ Events on TTS service instances. Available on all WebSocket-based TTS services. ### LLM Services -Events on LLM service instances. See [Service Events](/server/events/service-events) for details. +Events on LLM service instances. See [Service Events](/api-reference/server/events/service-events) for details. | Event | Description | | --------------------------- | ------------------------------------------ | @@ -188,7 +188,7 @@ Events on LLM service instances. See [Service Events](/server/events/service-eve ### Daily Transport -Events on [`DailyTransport`](/server/services/transport/daily#event-handlers) instances. +Events on [`DailyTransport`](/api-reference/server/services/transport/daily#event-handlers) instances. | Event | Description | | ----------------------------- | --------------------------------- | @@ -222,7 +222,7 @@ Events on [`DailyTransport`](/server/services/transport/daily#event-handlers) in ### LiveKit Transport -Events on [`LiveKitTransport`](/server/services/transport/livekit#event-handlers) instances. +Events on [`LiveKitTransport`](/api-reference/server/services/transport/livekit#event-handlers) instances. | Event | Description | | ----------------------------- | -------------------------- | diff --git a/server/events/service-events.mdx b/api-reference/server/events/service-events.mdx similarity index 93% rename from server/events/service-events.mdx rename to api-reference/server/events/service-events.mdx index 12967baf2..a64be6229 100644 --- a/server/events/service-events.mdx +++ b/api-reference/server/events/service-events.mdx @@ -141,6 +141,6 @@ async def on_completion_timeout(service): ## Related -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat -- [FrameProcessor Events](/server/events/frame-processor-events) - Error handling and frame monitoring events -- [Turn Events](/server/utilities/turn-management/turn-events) - User and assistant turn lifecycle events +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat +- [FrameProcessor Events](/api-reference/server/events/frame-processor-events) - Error handling and frame monitoring events +- [Turn Events](/api-reference/server/utilities/turn-management/turn-events) - User and assistant turn lifecycle events diff --git a/server/frames/control-frames.mdx b/api-reference/server/frames/control-frames.mdx similarity index 97% rename from server/frames/control-frames.mdx rename to api-reference/server/frames/control-frames.mdx index 73b4a9879..9555de840 100644 --- a/server/frames/control-frames.mdx +++ b/api-reference/server/frames/control-frames.mdx @@ -3,7 +3,7 @@ title: "Control Frames" description: "Reference for ControlFrame types: pipeline lifecycle, response boundaries, service settings, and runtime configuration" --- -ControlFrames signal boundaries, state changes, and configuration updates within the pipeline. They are queued and processed in order alongside DataFrames. ControlFrames are cancelled on `InterruptionFrame` unless combined with `UninterruptibleFrame`. See the [frames overview](/server/frames/overview) for base class details and the full frame hierarchy. +ControlFrames signal boundaries, state changes, and configuration updates within the pipeline. They are queued and processed in order alongside DataFrames. ControlFrames are cancelled on `InterruptionFrame` unless combined with `UninterruptibleFrame`. See the [frames overview](/api-reference/server/frames/overview) for base class details and the full frame hierarchy. ## Pipeline Lifecycle @@ -50,7 +50,7 @@ Internally, each processor has two queues: a high-priority input queue for Syste stay paused. To resume a paused processor from outside, use the `SystemFrame` variant `FrameProcessorResumeUrgentFrame` instead — it bypasses the process queue entirely. See [System - Frames](/server/frames/system-frames#processor-pauseresume-urgent). + Frames](/api-reference/server/frames/system-frames#processor-pauseresume-urgent). ### FrameProcessorPauseFrame @@ -236,7 +236,7 @@ Signals the end of a TTS audio response. ## Service Settings -Runtime settings updates for LLM, TTS, STT, and other services. These let you change service configuration mid-conversation without rebuilding the pipeline. Push an `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, or `STTUpdateSettingsFrame` to update the corresponding service. See the [Changing Service Settings at Runtime](/server/frames/overview#changing-service-settings-at-runtime) pattern for an example. +Runtime settings updates for LLM, TTS, STT, and other services. These let you change service configuration mid-conversation without rebuilding the pipeline. Push an `LLMUpdateSettingsFrame`, `TTSUpdateSettingsFrame`, or `STTUpdateSettingsFrame` to update the corresponding service. See the [Changing Service Settings at Runtime](/api-reference/server/frames/overview#changing-service-settings-at-runtime) pattern for an example. ### ServiceUpdateSettingsFrame diff --git a/server/frames/data-frames.mdx b/api-reference/server/frames/data-frames.mdx similarity index 97% rename from server/frames/data-frames.mdx rename to api-reference/server/frames/data-frames.mdx index 540b67a05..f2b5e833a 100644 --- a/server/frames/data-frames.mdx +++ b/api-reference/server/frames/data-frames.mdx @@ -5,11 +5,11 @@ description: "Reference for DataFrame types: audio, image, text, transcription, ## Overview -DataFrames carry the main content flowing through a pipeline: audio chunks, text, images, transcriptions, and messages. They are queued and processed in order with other DataFrames and ControlFrames, and any pending DataFrames are discarded when a user interrupts. See the [Frames overview](/server/frames/overview) for base class details, mixin fields, and frame properties common to all frames. +DataFrames carry the main content flowing through a pipeline: audio chunks, text, images, transcriptions, and messages. They are queued and processed in order with other DataFrames and ControlFrames, and any pending DataFrames are discarded when a user interrupts. See the [Frames overview](/api-reference/server/frames/overview) for base class details, mixin fields, and frame properties common to all frames. ## Audio Frames -These frames carry raw audio through the pipeline toward the output transport. Each inherits the `audio`, `sample_rate`, `num_channels`, and `num_frames` fields from the [`AudioRawFrame`](/server/frames/overview#audiorawframe) mixin. +These frames carry raw audio through the pipeline toward the output transport. Each inherits the `audio`, `sample_rate`, `num_channels`, and `num_frames` fields from the [`AudioRawFrame`](/api-reference/server/frames/overview#audiorawframe) mixin. ### OutputAudioRawFrame @@ -35,7 +35,7 @@ Inherits from `OutputAudioRawFrame`. ## Image Frames -Frames for carrying image data to the output transport. Each inherits `image`, `size`, and `format` from the [`ImageRawFrame`](/server/frames/overview#imagerawframe) mixin. +Frames for carrying image data to the output transport. Each inherits `image`, `size`, and `format` from the [`ImageRawFrame`](/api-reference/server/frames/overview#imagerawframe) mixin. ### OutputImageRawFrame diff --git a/server/frames/llm-frames.mdx b/api-reference/server/frames/llm-frames.mdx similarity index 68% rename from server/frames/llm-frames.mdx rename to api-reference/server/frames/llm-frames.mdx index e0664779a..67eae5283 100644 --- a/server/frames/llm-frames.mdx +++ b/api-reference/server/frames/llm-frames.mdx @@ -59,6 +59,6 @@ Configures how a function call result is handled after execution. LLM-related frames organized by base type: -- **Data Frames**: [Context Management](/server/frames/data-frames#llm-context-management), [Thinking](/server/frames/data-frames#llm-thinking), [Tool Configuration](/server/frames/data-frames#llm-tool-configuration), [Function Call Results](/server/frames/data-frames#function-call-results) -- **Control Frames**: [Response Boundaries](/server/frames/control-frames#llm-response-boundaries), [Context Summarization](/server/frames/control-frames#llm-context-summarization), [Thought Frames](/server/frames/control-frames#llm-thought-frames), [Function Calling](/server/frames/control-frames#function-calling), [Service Settings](/server/frames/control-frames#service-settings) -- **System Frames**: [Function Calling](/server/frames/system-frames#function-calling) +- **Data Frames**: [Context Management](/api-reference/server/frames/data-frames#llm-context-management), [Thinking](/api-reference/server/frames/data-frames#llm-thinking), [Tool Configuration](/api-reference/server/frames/data-frames#llm-tool-configuration), [Function Call Results](/api-reference/server/frames/data-frames#function-call-results) +- **Control Frames**: [Response Boundaries](/api-reference/server/frames/control-frames#llm-response-boundaries), [Context Summarization](/api-reference/server/frames/control-frames#llm-context-summarization), [Thought Frames](/api-reference/server/frames/control-frames#llm-thought-frames), [Function Calling](/api-reference/server/frames/control-frames#function-calling), [Service Settings](/api-reference/server/frames/control-frames#service-settings) +- **System Frames**: [Function Calling](/api-reference/server/frames/system-frames#function-calling) diff --git a/server/frames/overview.mdx b/api-reference/server/frames/overview.mdx similarity index 97% rename from server/frames/overview.mdx rename to api-reference/server/frames/overview.mdx index 6f86ef6ed..3a783a7ed 100644 --- a/server/frames/overview.mdx +++ b/api-reference/server/frames/overview.mdx @@ -277,23 +277,23 @@ class ResponseLogger(FrameProcessor): The individual reference pages below document every frame class, organized by function: - + Audio, image, text, transcription, and transport message frames that carry content through the pipeline. Pipeline lifecycle, LLM response boundaries, TTS state, service settings, and filter/mixer configuration. - + Interruptions, user/bot speaking state, VAD events, errors, metrics, and raw input frames. - + LLM context frame, function calling helper dataclasses, and links to LLM-related frames on other pages. diff --git a/server/frames/system-frames.mdx b/api-reference/server/frames/system-frames.mdx similarity index 91% rename from server/frames/system-frames.mdx rename to api-reference/server/frames/system-frames.mdx index deb3d24e0..2c219b45c 100644 --- a/server/frames/system-frames.mdx +++ b/api-reference/server/frames/system-frames.mdx @@ -3,7 +3,7 @@ title: "System Frames" description: "Reference for SystemFrame types: pipeline lifecycle, interruptions, speaking state, input, and diagnostics" --- -SystemFrames have higher priority than DataFrames and ControlFrames and are never cancelled during user interruptions. They are queued and processed in order with other SystemFrames. They carry signals that must always be delivered: pipeline startup and teardown, error notifications, user input, and speaking state changes. See the [frames overview](/server/frames/overview) for base class details, mixin fields, and frame properties common to all frames. +SystemFrames have higher priority than DataFrames and ControlFrames and are never cancelled during user interruptions. They are queued and processed in order with other SystemFrames. They carry signals that must always be delivered: pipeline startup and teardown, error notifications, user input, and speaking state changes. See the [frames overview](/api-reference/server/frames/overview) for base class details, mixin fields, and frame properties common to all frames. ## Pipeline Lifecycle @@ -95,7 +95,7 @@ Inherits from `ErrorFrame`. ## Processor Pause/Resume (Urgent) -These are the `SystemFrame` variants of `FrameProcessorPauseFrame` and `FrameProcessorResumeFrame`. As SystemFrames, they flow through the high-priority input queue rather than the process queue, so they are not blocked by paused state or buffered frames. This makes `FrameProcessorResumeUrgentFrame` the correct way to resume a processor externally — the `ControlFrame` variant (`FrameProcessorResumeFrame`) would get stuck behind any DataFrames that queued up during the pause. See [Control Frames](/server/frames/control-frames#processor-pauseresume) for the full explanation. +These are the `SystemFrame` variants of `FrameProcessorPauseFrame` and `FrameProcessorResumeFrame`. As SystemFrames, they flow through the high-priority input queue rather than the process queue, so they are not blocked by paused state or buffered frames. This makes `FrameProcessorResumeUrgentFrame` the correct way to resume a processor externally — the `ControlFrame` variant (`FrameProcessorResumeFrame`) would get stuck behind any DataFrames that queued up during the pause. See [Control Frames](/api-reference/server/frames/control-frames#processor-pauseresume) for the full explanation. ### FrameProcessorPauseUrgentFrame @@ -145,11 +145,11 @@ Emitted by the VAD processor while the user is actively speaking. Useful for UI ### UserMuteStartedFrame -Broadcast when one or more [user mute strategies](/server/utilities/turn-management/user-mute-strategies) activate. User mute temporarily suppresses user input while the bot is speaking to prevent interruptions. While muted, the `LLMUserAggregator` drops incoming user frames (`InputAudioRawFrame`, `TranscriptionFrame`, `InterimTranscriptionFrame`, `UserStartedSpeakingFrame`, `UserStoppedSpeakingFrame`, VAD signals, and `InterruptionFrame`). Lifecycle frames (`StartFrame`, `EndFrame`, `CancelFrame`) are never muted. +Broadcast when one or more [user mute strategies](/api-reference/server/utilities/turn-management/user-mute-strategies) activate. User mute temporarily suppresses user input while the bot is speaking to prevent interruptions. While muted, the `LLMUserAggregator` drops incoming user frames (`InputAudioRawFrame`, `TranscriptionFrame`, `InterimTranscriptionFrame`, `UserStartedSpeakingFrame`, `UserStoppedSpeakingFrame`, VAD signals, and `InterruptionFrame`). Lifecycle frames (`StartFrame`, `EndFrame`, `CancelFrame`) are never muted. ### UserMuteStoppedFrame -Broadcast when all active [user mute strategies](/server/utilities/turn-management/user-mute-strategies) deactivate, allowing user input to be processed again. +Broadcast when all active [user mute strategies](/api-reference/server/utilities/turn-management/user-mute-strategies) deactivate, allowing user input to be processed again. ## VAD Events @@ -221,7 +221,7 @@ Input frames carry raw data from transport sources into the pipeline. As `System ### InputAudioRawFrame -Raw audio received from the transport. Inherits the `audio`, `sample_rate`, `num_channels`, and `num_frames` fields from the [`AudioRawFrame`](/server/frames/overview#audiorawframe) mixin. +Raw audio received from the transport. Inherits the `audio`, `sample_rate`, `num_channels`, and `num_frames` fields from the [`AudioRawFrame`](/api-reference/server/frames/overview#audiorawframe) mixin. Inherits from `AudioRawFrame`. @@ -237,7 +237,7 @@ Inherits from `InputAudioRawFrame`. ### InputImageRawFrame -Raw image received from the transport. Inherits `image`, `size`, and `format` from the [`ImageRawFrame`](/server/frames/overview#imagerawframe) mixin. +Raw image received from the transport. Inherits `image`, `size`, and `format` from the [`ImageRawFrame`](/api-reference/server/frames/overview#imagerawframe) mixin. Inherits from `ImageRawFrame`. @@ -410,7 +410,7 @@ Inherits from `ServiceMetadataFrame`. ## RTVI -Frames for the [Real-Time Voice Interface (RTVI)](/server/frameworks/rtvi) protocol, which bridges clients and the pipeline. These frames handle custom messaging between the client and server. +Frames for the [Real-Time Voice Interface (RTVI)](/api-reference/server/rtvi) protocol, which bridges clients and the pipeline. These frames handle custom messaging between the client and server. ### RTVIServerMessageFrame diff --git a/server/introduction.mdx b/api-reference/server/introduction.mdx similarity index 86% rename from server/introduction.mdx rename to api-reference/server/introduction.mdx index c2797b5ab..27a0bb0dc 100644 --- a/server/introduction.mdx +++ b/api-reference/server/introduction.mdx @@ -20,15 +20,15 @@ This is the API reference for the server-side Pipecat Python framework. It cover Browse the full list of AI service integrations and their install commands - + Understand the data, control, system, and LLM frames that flow through pipelines - + Hook into pipeline lifecycle with frame processor and service events DEPRECATED: This parameter is deprecated. Configure interruption behavior via [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies) instead. + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) instead. See the `enable_interruptions` parameter on start strategies. Whether to allow pipeline interruptions. When enabled, a user's speech will @@ -61,7 +61,7 @@ task = PipelineTask(pipeline, params=params) Whether to enable heartbeat monitoring to detect pipeline stalls. See - [Heartbeats](/server/pipeline/heartbeats) for details. + [Heartbeats](/api-reference/server/pipeline/heartbeats) for details. diff --git a/server/pipeline/pipeline-task.mdx b/api-reference/server/pipeline/pipeline-task.mdx similarity index 93% rename from server/pipeline/pipeline-task.mdx rename to api-reference/server/pipeline/pipeline-task.mdx index f7fbe6312..32e275d25 100644 --- a/server/pipeline/pipeline-task.mdx +++ b/api-reference/server/pipeline/pipeline-task.mdx @@ -36,12 +36,12 @@ await runner.run(task) Configuration parameters for the pipeline. See - [PipelineParams](/server/pipeline/pipeline-params) for details. + [PipelineParams](/api-reference/server/pipeline/pipeline-params) for details. List of observers for monitoring pipeline execution. See - [Observers](/server/utilities/observers/observer-pattern) for details. + [Observers](/api-reference/server/utilities/observers/observer-pattern) for details. @@ -60,7 +60,7 @@ await runner.run(task) Timeout in seconds before considering the pipeline idle. Set to None to disable idle detection. See [Pipeline Idle - Detection](/server/pipeline/pipeline-idle-detection) for details. + Detection](/api-reference/server/pipeline/pipeline-idle-detection) for details. Frame types that should prevent the pipeline from being considered idle. See - [Pipeline Idle Detection](/server/pipeline/pipeline-idle-detection) for + [Pipeline Idle Detection](/api-reference/server/pipeline/pipeline-idle-detection) for details. Whether to automatically cancel the pipeline task when idle timeout is reached. See [Pipeline Idle - Detection](/server/pipeline/pipeline-idle-detection) for details. + Detection](/api-reference/server/pipeline/pipeline-idle-detection) for details. Whether to enable OpenTelemetry tracing. See [The OpenTelemetry - guide](/server/utilities/opentelemetry) for details. + guide](/api-reference/server/utilities/opentelemetry) for details. Whether to enable turn tracking. See [The OpenTelemetry - guide](/server/utilities/opentelemetry) for details. + guide](/api-reference/server/utilities/opentelemetry) for details. Custom ID for the conversation. If not provided, a UUID will be generated. See - [The OpenTelemetry guide](/server/utilities/opentelemetry) for details. + [The OpenTelemetry guide](/api-reference/server/utilities/opentelemetry) for details. Any additional attributes to add to top-level OpenTelemetry conversation span. - See [The OpenTelemetry guide](/server/utilities/opentelemetry) for details. + See [The OpenTelemetry guide](/api-reference/server/utilities/opentelemetry) for details. ## Methods @@ -326,7 +326,7 @@ async def on_frame_reached_downstream(task, frame): ### on_idle_timeout -Fired when no activity frames (as specified by `idle_timeout_frames`) have been received within the idle timeout period. See [Pipeline Idle Detection](/server/pipeline/pipeline-idle-detection) for configuration details. +Fired when no activity frames (as specified by `idle_timeout_frames`) have been received within the idle timeout period. See [Pipeline Idle Detection](/api-reference/server/pipeline/pipeline-idle-detection) for configuration details. ```python @task.event_handler("on_idle_timeout") diff --git a/server/frameworks/rtvi/google-rtvi-observer.mdx b/api-reference/server/rtvi/google-rtvi-observer.mdx similarity index 90% rename from server/frameworks/rtvi/google-rtvi-observer.mdx rename to api-reference/server/rtvi/google-rtvi-observer.mdx index ab3349547..c86792b24 100644 --- a/server/frameworks/rtvi/google-rtvi-observer.mdx +++ b/api-reference/server/rtvi/google-rtvi-observer.mdx @@ -5,7 +5,7 @@ description: "Adding support for sending search responses to RTVI clients" ## Overview -The `GoogleRTVIObserver` extends the [base `RTVIObserver` type](./rtvi-observer), to add support for the `bot-llm-search-response` message type and providing clients with the search results from the `GoogleLLMService`. See [this section on Search Grounding](/server/services/llm/google#search-grounding) for more details. +The `GoogleRTVIObserver` extends the [base `RTVIObserver` type](./rtvi-observer), to add support for the `bot-llm-search-response` message type and providing clients with the search results from the `GoogleLLMService`. See [this section on Search Grounding](/api-reference/server/services/llm/google#search-grounding) for more details. + href="/api-reference/server/rtvi/rtvi-processor"> Configure and manage RTVI services, actions, and client communication + href="/api-reference/server/rtvi/rtvi-observer"> Translate internal pipeline events to standardized client messages diff --git a/server/frameworks/rtvi/rtvi-observer.mdx b/api-reference/server/rtvi/rtvi-observer.mdx similarity index 100% rename from server/frameworks/rtvi/rtvi-observer.mdx rename to api-reference/server/rtvi/rtvi-observer.mdx diff --git a/server/frameworks/rtvi/rtvi-processor.mdx b/api-reference/server/rtvi/rtvi-processor.mdx similarity index 100% rename from server/frameworks/rtvi/rtvi-processor.mdx rename to api-reference/server/rtvi/rtvi-processor.mdx diff --git a/server/services/analytics/sentry.mdx b/api-reference/server/services/analytics/sentry.mdx similarity index 100% rename from server/services/analytics/sentry.mdx rename to api-reference/server/services/analytics/sentry.mdx diff --git a/server/services/community-integrations.mdx b/api-reference/server/services/community-integrations.mdx similarity index 100% rename from server/services/community-integrations.mdx rename to api-reference/server/services/community-integrations.mdx diff --git a/server/services/image-generation/azure.mdx b/api-reference/server/services/image-generation/azure.mdx similarity index 100% rename from server/services/image-generation/azure.mdx rename to api-reference/server/services/image-generation/azure.mdx diff --git a/server/services/image-generation/fal.mdx b/api-reference/server/services/image-generation/fal.mdx similarity index 100% rename from server/services/image-generation/fal.mdx rename to api-reference/server/services/image-generation/fal.mdx diff --git a/server/services/image-generation/google.mdx b/api-reference/server/services/image-generation/google.mdx similarity index 100% rename from server/services/image-generation/google.mdx rename to api-reference/server/services/image-generation/google.mdx diff --git a/server/services/image-generation/openai.mdx b/api-reference/server/services/image-generation/openai.mdx similarity index 100% rename from server/services/image-generation/openai.mdx rename to api-reference/server/services/image-generation/openai.mdx diff --git a/server/services/llm/anthropic.mdx b/api-reference/server/services/llm/anthropic.mdx similarity index 99% rename from server/services/llm/anthropic.mdx rename to api-reference/server/services/llm/anthropic.mdx index 7409ed008..6baa2ea80 100644 --- a/server/services/llm/anthropic.mdx +++ b/api-reference/server/services/llm/anthropic.mdx @@ -207,7 +207,7 @@ await task.queue_frame( ## Event Handlers -`AnthropicLLMService` supports the following event handlers, inherited from [LLMService](/server/events/service-events): +`AnthropicLLMService` supports the following event handlers, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | ----------------------------------------------------------------------- | diff --git a/server/services/llm/aws.mdx b/api-reference/server/services/llm/aws.mdx similarity index 99% rename from server/services/llm/aws.mdx rename to api-reference/server/services/llm/aws.mdx index b4ec7cf6c..b7af10037 100644 --- a/server/services/llm/aws.mdx +++ b/api-reference/server/services/llm/aws.mdx @@ -215,7 +215,7 @@ await task.queue_frame( ## Event Handlers -`AWSBedrockLLMService` supports the following event handlers, inherited from [LLMService](/server/events/service-events): +`AWSBedrockLLMService` supports the following event handlers, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | ----------------------------------------------------------------------- | diff --git a/server/services/llm/azure.mdx b/api-reference/server/services/llm/azure.mdx similarity index 96% rename from server/services/llm/azure.mdx rename to api-reference/server/services/llm/azure.mdx index 4d14401b7..460367cfd 100644 --- a/server/services/llm/azure.mdx +++ b/api-reference/server/services/llm/azure.mdx @@ -103,7 +103,7 @@ Since `AzureLLMService` inherits from `OpenAILLMService`, it also accepts the fo Runtime-configurable settings passed via the `settings` constructor argument using `AzureLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -`AzureLLMService` uses the same settings as `OpenAILLMService`. See the [OpenAI LLM Settings](/server/services/llm/openai#settings) section for the full parameter reference. +`AzureLLMService` uses the same settings as `OpenAILLMService`. See the [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) section for the full parameter reference. ## Usage @@ -163,7 +163,7 @@ await task.queue_frame( ## Event Handlers -`AzureLLMService` supports the same event handlers as `OpenAILLMService`, inherited from [LLMService](/server/events/service-events): +`AzureLLMService` supports the same event handlers as `OpenAILLMService`, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | ----------------------------------------------------------------------- | diff --git a/server/services/llm/cerebras.mdx b/api-reference/server/services/llm/cerebras.mdx similarity index 97% rename from server/services/llm/cerebras.mdx rename to api-reference/server/services/llm/cerebras.mdx index 97feadc6a..145584f2b 100644 --- a/server/services/llm/cerebras.mdx +++ b/api-reference/server/services/llm/cerebras.mdx @@ -85,7 +85,7 @@ _Deprecated in v0.0.105. Use `settings=CerebrasLLMService.Settings(model=...)` i Runtime-configurable settings passed via the `settings` constructor argument using `CerebrasLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/deepseek.mdx b/api-reference/server/services/llm/deepseek.mdx similarity index 97% rename from server/services/llm/deepseek.mdx rename to api-reference/server/services/llm/deepseek.mdx index 6abc3b97a..b56cb2984 100644 --- a/server/services/llm/deepseek.mdx +++ b/api-reference/server/services/llm/deepseek.mdx @@ -85,7 +85,7 @@ _Deprecated in v0.0.105. Use `settings=DeepSeekLLMService.Settings(model=...)` i Runtime-configurable settings passed via the `settings` constructor argument using `DeepSeekLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/fireworks.mdx b/api-reference/server/services/llm/fireworks.mdx similarity index 97% rename from server/services/llm/fireworks.mdx rename to api-reference/server/services/llm/fireworks.mdx index 7bbb6a6bd..ca13e4ef1 100644 --- a/server/services/llm/fireworks.mdx +++ b/api-reference/server/services/llm/fireworks.mdx @@ -94,7 +94,7 @@ _Deprecated in v0.0.105. Use `settings=FireworksLLMService.Settings(model=...)` Runtime-configurable settings passed via the `settings` constructor argument using `FireworksLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/google-vertex.mdx b/api-reference/server/services/llm/google-vertex.mdx similarity index 98% rename from server/services/llm/google-vertex.mdx rename to api-reference/server/services/llm/google-vertex.mdx index 5d63f58a3..9513bce0c 100644 --- a/server/services/llm/google-vertex.mdx +++ b/api-reference/server/services/llm/google-vertex.mdx @@ -97,7 +97,7 @@ Before using Google Vertex AI LLM services, you need: default="None" > Runtime-configurable settings. See [Google Gemini - Settings](/server/services/llm/google#settings) for the full parameter + Settings](/api-reference/server/services/llm/google#settings) for the full parameter reference. diff --git a/server/services/llm/google.mdx b/api-reference/server/services/llm/google.mdx similarity index 99% rename from server/services/llm/google.mdx rename to api-reference/server/services/llm/google.mdx index b87babc04..cfca28526 100644 --- a/server/services/llm/google.mdx +++ b/api-reference/server/services/llm/google.mdx @@ -229,7 +229,7 @@ await task.queue_frame( ## Event Handlers -`GoogleLLMService` supports the following event handlers, inherited from [LLMService](/server/events/service-events): +`GoogleLLMService` supports the following event handlers, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | --------------------------------------------------------------------------- | diff --git a/server/services/llm/grok.mdx b/api-reference/server/services/llm/grok.mdx similarity index 97% rename from server/services/llm/grok.mdx rename to api-reference/server/services/llm/grok.mdx index a0f6cb2a3..9bed59601 100644 --- a/server/services/llm/grok.mdx +++ b/api-reference/server/services/llm/grok.mdx @@ -81,7 +81,7 @@ _Deprecated in v0.0.105. Use `settings=GrokLLMService.Settings(model=...)` inste Runtime-configurable settings passed via the `settings` constructor argument using `GrokLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/groq.mdx b/api-reference/server/services/llm/groq.mdx similarity index 97% rename from server/services/llm/groq.mdx rename to api-reference/server/services/llm/groq.mdx index cda441e1f..95eae5545 100644 --- a/server/services/llm/groq.mdx +++ b/api-reference/server/services/llm/groq.mdx @@ -81,7 +81,7 @@ _Deprecated in v0.0.105. Use `settings=GroqLLMService.Settings(model=...)` inste Runtime-configurable settings passed via the `settings` constructor argument using `GroqLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/mistral.mdx b/api-reference/server/services/llm/mistral.mdx similarity index 97% rename from server/services/llm/mistral.mdx rename to api-reference/server/services/llm/mistral.mdx index 5a9fda4dc..35424b026 100644 --- a/server/services/llm/mistral.mdx +++ b/api-reference/server/services/llm/mistral.mdx @@ -85,7 +85,7 @@ _Deprecated in v0.0.105. Use `settings=MistralLLMService.Settings(model=...)` in Runtime-configurable settings passed via the `settings` constructor argument using `MistralLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/novita.mdx b/api-reference/server/services/llm/novita.mdx similarity index 97% rename from server/services/llm/novita.mdx rename to api-reference/server/services/llm/novita.mdx index 9c54c2ffa..f92569abb 100644 --- a/server/services/llm/novita.mdx +++ b/api-reference/server/services/llm/novita.mdx @@ -74,7 +74,7 @@ Before using Novita AI LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `NovitaLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. The default model is `"moonshotai/kimi-k2.5"`. diff --git a/server/services/llm/nvidia.mdx b/api-reference/server/services/llm/nvidia.mdx similarity index 97% rename from server/services/llm/nvidia.mdx rename to api-reference/server/services/llm/nvidia.mdx index 0909c4a3f..c17f1e31b 100644 --- a/server/services/llm/nvidia.mdx +++ b/api-reference/server/services/llm/nvidia.mdx @@ -95,7 +95,7 @@ _Deprecated in v0.0.105. Use `settings=NvidiaLLMService.Settings(model=...)` ins Runtime-configurable settings passed via the `settings` constructor argument using `NvidiaLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/ollama.mdx b/api-reference/server/services/llm/ollama.mdx similarity index 97% rename from server/services/llm/ollama.mdx rename to api-reference/server/services/llm/ollama.mdx index 341dc0b49..f54e801f3 100644 --- a/server/services/llm/ollama.mdx +++ b/api-reference/server/services/llm/ollama.mdx @@ -98,7 +98,7 @@ _Deprecated in v0.0.105. Use `settings=OLLamaLLMService.Settings(model=...)` ins Runtime-configurable settings passed via the `settings` constructor argument using `OLLamaLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/openai-responses.mdx b/api-reference/server/services/llm/openai-responses.mdx similarity index 99% rename from server/services/llm/openai-responses.mdx rename to api-reference/server/services/llm/openai-responses.mdx index 943936466..6e9642cdf 100644 --- a/server/services/llm/openai-responses.mdx +++ b/api-reference/server/services/llm/openai-responses.mdx @@ -206,7 +206,7 @@ print(response) # "The capital of France is Paris." ## Event Handlers -`OpenAIResponsesLLMService` supports the following event handlers, inherited from [LLMService](/server/events/service-events): +`OpenAIResponsesLLMService` supports the following event handlers, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | ----------------------------------------------------------------------- | diff --git a/server/services/llm/openai.mdx b/api-reference/server/services/llm/openai.mdx similarity index 99% rename from server/services/llm/openai.mdx rename to api-reference/server/services/llm/openai.mdx index 32b0bafca..988730f1f 100644 --- a/server/services/llm/openai.mdx +++ b/api-reference/server/services/llm/openai.mdx @@ -195,7 +195,7 @@ await task.queue_frame( ## Event Handlers -`OpenAILLMService` supports the following event handlers, inherited from [LLMService](/server/events/service-events): +`OpenAILLMService` supports the following event handlers, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | ----------------------------------------------------------------------- | diff --git a/server/services/llm/openpipe.mdx b/api-reference/server/services/llm/openpipe.mdx similarity index 97% rename from server/services/llm/openpipe.mdx rename to api-reference/server/services/llm/openpipe.mdx index 62d60bc5e..8367e66fa 100644 --- a/server/services/llm/openpipe.mdx +++ b/api-reference/server/services/llm/openpipe.mdx @@ -98,7 +98,7 @@ Before using OpenPipe LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `OpenPipeLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/openrouter.mdx b/api-reference/server/services/llm/openrouter.mdx similarity index 97% rename from server/services/llm/openrouter.mdx rename to api-reference/server/services/llm/openrouter.mdx index eef35b94e..88a4c61aa 100644 --- a/server/services/llm/openrouter.mdx +++ b/api-reference/server/services/llm/openrouter.mdx @@ -85,7 +85,7 @@ Before using OpenRouter LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `OpenRouterLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/perplexity.mdx b/api-reference/server/services/llm/perplexity.mdx similarity index 97% rename from server/services/llm/perplexity.mdx rename to api-reference/server/services/llm/perplexity.mdx index 2919a9055..68e681f42 100644 --- a/server/services/llm/perplexity.mdx +++ b/api-reference/server/services/llm/perplexity.mdx @@ -89,7 +89,7 @@ Before using Perplexity LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `PerplexityLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/qwen.mdx b/api-reference/server/services/llm/qwen.mdx similarity index 97% rename from server/services/llm/qwen.mdx rename to api-reference/server/services/llm/qwen.mdx index 49aff2ed3..7663e4c4c 100644 --- a/server/services/llm/qwen.mdx +++ b/api-reference/server/services/llm/qwen.mdx @@ -87,7 +87,7 @@ Before using Qwen LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `QwenLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/sambanova.mdx b/api-reference/server/services/llm/sambanova.mdx similarity index 97% rename from server/services/llm/sambanova.mdx rename to api-reference/server/services/llm/sambanova.mdx index 617670cee..08ef95de1 100644 --- a/server/services/llm/sambanova.mdx +++ b/api-reference/server/services/llm/sambanova.mdx @@ -83,7 +83,7 @@ Before using SambaNova LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `SambaNovaLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/llm/sarvam.mdx b/api-reference/server/services/llm/sarvam.mdx similarity index 99% rename from server/services/llm/sarvam.mdx rename to api-reference/server/services/llm/sarvam.mdx index 12527fdd0..920df57b3 100644 --- a/server/services/llm/sarvam.mdx +++ b/api-reference/server/services/llm/sarvam.mdx @@ -149,7 +149,7 @@ await task.queue_frame( ## Event Handlers -`SarvamLLMService` supports the following event handlers, inherited from [LLMService](/server/events/service-events): +`SarvamLLMService` supports the following event handlers, inherited from [LLMService](/api-reference/server/events/service-events): | Event | Description | | --------------------------- | ----------------------------------------------------------------------- | diff --git a/server/services/llm/together.mdx b/api-reference/server/services/llm/together.mdx similarity index 97% rename from server/services/llm/together.mdx rename to api-reference/server/services/llm/together.mdx index 8619bdd79..1e33e0bca 100644 --- a/server/services/llm/together.mdx +++ b/api-reference/server/services/llm/together.mdx @@ -83,7 +83,7 @@ Before using Together AI LLM services, you need: Runtime-configurable settings passed via the `settings` constructor argument using `TogetherLLMService.Settings(...)`. These can be updated mid-conversation with `LLMUpdateSettingsFrame`. See [Service Settings](/pipecat/fundamentals/service-settings) for details. -This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/server/services/llm/openai#settings) for the full parameter reference. +This service uses the same settings as `OpenAILLMService`. See [OpenAI LLM Settings](/api-reference/server/services/llm/openai#settings) for the full parameter reference. ## Usage diff --git a/server/services/memory/mem0.mdx b/api-reference/server/services/memory/mem0.mdx similarity index 100% rename from server/services/memory/mem0.mdx rename to api-reference/server/services/memory/mem0.mdx diff --git a/server/services/s2s/aws.mdx b/api-reference/server/services/s2s/aws.mdx similarity index 100% rename from server/services/s2s/aws.mdx rename to api-reference/server/services/s2s/aws.mdx diff --git a/server/services/s2s/gemini-live-vertex.mdx b/api-reference/server/services/s2s/gemini-live-vertex.mdx similarity index 95% rename from server/services/s2s/gemini-live-vertex.mdx rename to api-reference/server/services/s2s/gemini-live-vertex.mdx index 5dabec7ac..438fe2737 100644 --- a/server/services/s2s/gemini-live-vertex.mdx +++ b/api-reference/server/services/s2s/gemini-live-vertex.mdx @@ -82,7 +82,7 @@ Before using Gemini Live Vertex AI services, you need: ### GeminiLiveVertexLLMService -This service extends `GeminiLiveLLMService` with Vertex AI authentication. It accepts all the same parameters as the [Gemini Live](/server/services/s2s/gemini-live) service, with these differences: +This service extends `GeminiLiveLLMService` with Vertex AI authentication. It accepts all the same parameters as the [Gemini Live](/api-reference/server/services/s2s/gemini-live) service, with these differences: JSON string of Google service account credentials. If not provided, falls back @@ -131,7 +131,7 @@ _Deprecated in v0.0.105. Use `settings=GeminiLiveVertexLLMService.Settings(voice Runtime-configurable generation and session settings. See the [Gemini Live - InputParams](/server/services/s2s/gemini-live#inputparams) for details. + InputParams](/api-reference/server/services/s2s/gemini-live#inputparams) for details. _Deprecated in v0.0.105. Use `settings=GeminiLiveVertexLLMService.Settings(...)` instead._ @@ -143,7 +143,7 @@ _Deprecated in v0.0.105. Use `settings=GeminiLiveVertexLLMService.Settings(...)` default="None" > Runtime-configurable settings. See the [Gemini Live - Settings](/server/services/s2s/gemini-live#settings) for the full reference. + Settings](/api-reference/server/services/s2s/gemini-live#settings) for the full reference. @@ -169,7 +169,7 @@ _Deprecated in v0.0.105. Use `settings=GeminiLiveVertexLLMService.Settings(...)` ### Settings -The Vertex AI variant uses the same Settings as the base Gemini Live service. See [Gemini Live Settings](/server/services/s2s/gemini-live#settings) for the full reference. +The Vertex AI variant uses the same Settings as the base Gemini Live service. See [Gemini Live Settings](/api-reference/server/services/s2s/gemini-live#settings) for the full reference. ## Usage @@ -251,4 +251,4 @@ llm = GeminiLiveVertexLLMService( - **Authentication priority**: The service tries credentials in this order: (1) `credentials` JSON string, (2) `credentials_path` file, (3) Application Default Credentials (ADC). - **File API not supported**: The Gemini File API is not available through Vertex AI. Use Google Cloud Storage for file handling instead. - **Model naming**: Vertex AI uses different model identifiers (e.g., `"google/gemini-live-2.5-flash-native-audio"`) compared to the Google AI variant. -- **All other features** (VAD, context compression, thinking, function calling, etc.) work identically to the base [Gemini Live](/server/services/s2s/gemini-live) service. +- **All other features** (VAD, context compression, thinking, function calling, etc.) work identically to the base [Gemini Live](/api-reference/server/services/s2s/gemini-live) service. diff --git a/server/services/s2s/gemini-live.mdx b/api-reference/server/services/s2s/gemini-live.mdx similarity index 100% rename from server/services/s2s/gemini-live.mdx rename to api-reference/server/services/s2s/gemini-live.mdx diff --git a/server/services/s2s/grok.mdx b/api-reference/server/services/s2s/grok.mdx similarity index 100% rename from server/services/s2s/grok.mdx rename to api-reference/server/services/s2s/grok.mdx diff --git a/server/services/s2s/openai.mdx b/api-reference/server/services/s2s/openai.mdx similarity index 100% rename from server/services/s2s/openai.mdx rename to api-reference/server/services/s2s/openai.mdx diff --git a/server/services/s2s/ultravox.mdx b/api-reference/server/services/s2s/ultravox.mdx similarity index 100% rename from server/services/s2s/ultravox.mdx rename to api-reference/server/services/s2s/ultravox.mdx diff --git a/server/services/serializers/exotel.mdx b/api-reference/server/services/serializers/exotel.mdx similarity index 100% rename from server/services/serializers/exotel.mdx rename to api-reference/server/services/serializers/exotel.mdx diff --git a/server/services/serializers/genesys.mdx b/api-reference/server/services/serializers/genesys.mdx similarity index 100% rename from server/services/serializers/genesys.mdx rename to api-reference/server/services/serializers/genesys.mdx diff --git a/server/services/serializers/introduction.mdx b/api-reference/server/services/serializers/introduction.mdx similarity index 88% rename from server/services/serializers/introduction.mdx rename to api-reference/server/services/serializers/introduction.mdx index 13a4ce31b..d9e97fc2f 100644 --- a/server/services/serializers/introduction.mdx +++ b/api-reference/server/services/serializers/introduction.mdx @@ -23,35 +23,35 @@ Pipecat includes serializers for popular voice and communications platforms: For integrating with Exotel WebSocket media streaming For integrating with Telnyx WebSocket media streaming For integrating with Telnyx WebSocket media streaming For integrating with Twilio Media Streams WebSocket protocol For integrating with Vonage Video API Audio Connector WebSocket protocol diff --git a/server/services/serializers/plivo.mdx b/api-reference/server/services/serializers/plivo.mdx similarity index 100% rename from server/services/serializers/plivo.mdx rename to api-reference/server/services/serializers/plivo.mdx diff --git a/server/services/serializers/telnyx.mdx b/api-reference/server/services/serializers/telnyx.mdx similarity index 100% rename from server/services/serializers/telnyx.mdx rename to api-reference/server/services/serializers/telnyx.mdx diff --git a/server/services/serializers/twilio.mdx b/api-reference/server/services/serializers/twilio.mdx similarity index 100% rename from server/services/serializers/twilio.mdx rename to api-reference/server/services/serializers/twilio.mdx diff --git a/server/services/serializers/vonage.mdx b/api-reference/server/services/serializers/vonage.mdx similarity index 100% rename from server/services/serializers/vonage.mdx rename to api-reference/server/services/serializers/vonage.mdx diff --git a/server/services/stt/assemblyai.mdx b/api-reference/server/services/stt/assemblyai.mdx similarity index 99% rename from server/services/stt/assemblyai.mdx rename to api-reference/server/services/stt/assemblyai.mdx index 25869a841..f8de3e527 100644 --- a/server/services/stt/assemblyai.mdx +++ b/api-reference/server/services/stt/assemblyai.mdx @@ -269,7 +269,7 @@ stt = AssemblyAISTTService( ## Event Handlers -AssemblyAI STT supports the standard [service connection events](/server/events/service-events), plus turn-level events for conversation tracking: +AssemblyAI STT supports the standard [service connection events](/api-reference/server/events/service-events), plus turn-level events for conversation tracking: | Event | Description | | ----------------- | ------------------------------------------------------------- | diff --git a/server/services/stt/aws.mdx b/api-reference/server/services/stt/aws.mdx similarity index 99% rename from server/services/stt/aws.mdx rename to api-reference/server/services/stt/aws.mdx index 3149e8775..fef132814 100644 --- a/server/services/stt/aws.mdx +++ b/api-reference/server/services/stt/aws.mdx @@ -170,7 +170,7 @@ stt = AWSTranscribeSTTService( ## Event Handlers -AWS Transcribe STT supports the standard [service connection events](/server/events/service-events): +AWS Transcribe STT supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | ------------------------------------------ | diff --git a/server/services/stt/azure.mdx b/api-reference/server/services/stt/azure.mdx similarity index 100% rename from server/services/stt/azure.mdx rename to api-reference/server/services/stt/azure.mdx diff --git a/server/services/stt/cartesia.mdx b/api-reference/server/services/stt/cartesia.mdx similarity index 99% rename from server/services/stt/cartesia.mdx rename to api-reference/server/services/stt/cartesia.mdx index 7fa1bfed9..302f63dc7 100644 --- a/server/services/stt/cartesia.mdx +++ b/api-reference/server/services/stt/cartesia.mdx @@ -148,7 +148,7 @@ stt = CartesiaSTTService( ## Event Handlers -Cartesia STT supports the standard [service connection events](/server/events/service-events): +Cartesia STT supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | ------------------------------------ | diff --git a/server/services/stt/deepgram.mdx b/api-reference/server/services/stt/deepgram.mdx similarity index 96% rename from server/services/stt/deepgram.mdx rename to api-reference/server/services/stt/deepgram.mdx index 80485106c..8a4813456 100644 --- a/server/services/stt/deepgram.mdx +++ b/api-reference/server/services/stt/deepgram.mdx @@ -237,7 +237,7 @@ stt = DeepgramSTTService( ### Event Handlers -Supports the standard [service connection events](/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), plus: +Supports the standard [service connection events](/api-reference/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), plus: | Event | Description | | ------------------- | ------------------------------------- | @@ -260,7 +260,7 @@ async def on_utterance_end(service): Since Deepgram Flux provides its own user turn start and end detection, you should use `ExternalUserTurnStrategies` to let Flux handle turn management. See [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies) for + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) for configuration details. @@ -384,7 +384,7 @@ This sends a `Configure` message to Deepgram over the existing WebSocket connect ### Event Handlers -Supports the standard [service connection events](/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), plus turn-level events for more granular conversation tracking: +Supports the standard [service connection events](/api-reference/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), plus turn-level events for more granular conversation tracking: | Event | Description | | ---------------------- | ------------------------------------ | @@ -495,7 +495,7 @@ stt = DeepgramSageMakerSTTService( ### Event Handlers -Supports the standard [service connection events](/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`). +Supports the standard [service connection events](/api-reference/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`). ## DeepgramFluxSageMakerSTTService @@ -503,7 +503,7 @@ Supports the standard [service connection events](/server/events/service-events) Since Deepgram Flux provides its own user turn start and end detection, you should use `ExternalUserTurnStrategies` to let Flux handle turn management. See [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies) for + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) for configuration details. @@ -625,7 +625,7 @@ await task.queue_frame( ### Event Handlers -Supports the standard [service connection events](/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), plus turn-level events for granular conversation tracking: +Supports the standard [service connection events](/api-reference/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), plus turn-level events for granular conversation tracking: | Event | Description | | ---------------------- | ------------------------------------ | diff --git a/server/services/stt/elevenlabs.mdx b/api-reference/server/services/stt/elevenlabs.mdx similarity index 99% rename from server/services/stt/elevenlabs.mdx rename to api-reference/server/services/stt/elevenlabs.mdx index 93bbc0af4..9fc315917 100644 --- a/server/services/stt/elevenlabs.mdx +++ b/api-reference/server/services/stt/elevenlabs.mdx @@ -273,7 +273,7 @@ stt = ElevenLabsRealtimeSTTService( ### Event Handlers -Supports the standard [service connection events](/server/events/service-events): +Supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | --------------------------------------------------- | diff --git a/server/services/stt/fal.mdx b/api-reference/server/services/stt/fal.mdx similarity index 100% rename from server/services/stt/fal.mdx rename to api-reference/server/services/stt/fal.mdx diff --git a/server/services/stt/gladia.mdx b/api-reference/server/services/stt/gladia.mdx similarity index 98% rename from server/services/stt/gladia.mdx rename to api-reference/server/services/stt/gladia.mdx index 22f75a217..827838669 100644 --- a/server/services/stt/gladia.mdx +++ b/api-reference/server/services/stt/gladia.mdx @@ -219,7 +219,7 @@ stt = GladiaSTTService( ## Event Handlers -Gladia STT supports the standard [service connection events](/server/events/service-events): +Gladia STT supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | ---------------------------------- | diff --git a/server/services/stt/google.mdx b/api-reference/server/services/stt/google.mdx similarity index 98% rename from server/services/stt/google.mdx rename to api-reference/server/services/stt/google.mdx index ccf83635c..d439d1d65 100644 --- a/server/services/stt/google.mdx +++ b/api-reference/server/services/stt/google.mdx @@ -206,7 +206,7 @@ await task.queue_frame( ## Event Handlers -Google STT supports the standard [service connection events](/server/events/service-events): +Google STT supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | --------------------------------------------- | diff --git a/server/services/stt/gradium.mdx b/api-reference/server/services/stt/gradium.mdx similarity index 98% rename from server/services/stt/gradium.mdx rename to api-reference/server/services/stt/gradium.mdx index 12689a717..2d9b57dfa 100644 --- a/server/services/stt/gradium.mdx +++ b/api-reference/server/services/stt/gradium.mdx @@ -157,7 +157,7 @@ stt = GradiumSTTService( ## Event Handlers -Gradium STT supports the standard [service connection events](/server/events/service-events): +Gradium STT supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | ----------------------------------- | diff --git a/server/services/stt/groq.mdx b/api-reference/server/services/stt/groq.mdx similarity index 100% rename from server/services/stt/groq.mdx rename to api-reference/server/services/stt/groq.mdx diff --git a/server/services/stt/nvidia.mdx b/api-reference/server/services/stt/nvidia.mdx similarity index 100% rename from server/services/stt/nvidia.mdx rename to api-reference/server/services/stt/nvidia.mdx diff --git a/server/services/stt/openai.mdx b/api-reference/server/services/stt/openai.mdx similarity index 99% rename from server/services/stt/openai.mdx rename to api-reference/server/services/stt/openai.mdx index 6614c4856..30e0e0cbd 100644 --- a/server/services/stt/openai.mdx +++ b/api-reference/server/services/stt/openai.mdx @@ -267,7 +267,7 @@ stt = OpenAIRealtimeSTTService( ### Event Handlers -Supports the standard [service connection events](/server/events/service-events): +Supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | ------------------------------------------- | diff --git a/server/services/stt/sarvam.mdx b/api-reference/server/services/stt/sarvam.mdx similarity index 97% rename from server/services/stt/sarvam.mdx rename to api-reference/server/services/stt/sarvam.mdx index 4853433db..0d620cabb 100644 --- a/server/services/stt/sarvam.mdx +++ b/api-reference/server/services/stt/sarvam.mdx @@ -190,7 +190,7 @@ stt = SarvamSTTService( ## Event Handlers -In addition to the standard [service connection events](/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), Sarvam STT provides: +In addition to the standard [service connection events](/api-reference/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), Sarvam STT provides: | Event | Description | | ------------------- | ----------------------------------- | diff --git a/server/services/stt/soniox.mdx b/api-reference/server/services/stt/soniox.mdx similarity index 98% rename from server/services/stt/soniox.mdx rename to api-reference/server/services/stt/soniox.mdx index 20127f0db..0d0a09d9e 100644 --- a/server/services/stt/soniox.mdx +++ b/api-reference/server/services/stt/soniox.mdx @@ -210,7 +210,7 @@ stt = SonioxSTTService( ## Event Handlers -Soniox STT supports the standard [service connection events](/server/events/service-events): +Soniox STT supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | ----------------- | ---------------------------------- | diff --git a/server/services/stt/speechmatics.mdx b/api-reference/server/services/stt/speechmatics.mdx similarity index 98% rename from server/services/stt/speechmatics.mdx rename to api-reference/server/services/stt/speechmatics.mdx index 36d062afe..cccbb8977 100644 --- a/server/services/stt/speechmatics.mdx +++ b/api-reference/server/services/stt/speechmatics.mdx @@ -11,7 +11,7 @@ description: "Speech-to-text service implementation using Speechmatics' real-tim Since Speechmatics provides its own user turn start and end detection, you should use `ExternalUserTurnStrategies` to let Speechmatics handle turn management. See [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies) for + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) for configuration details. @@ -448,7 +448,7 @@ pipeline = Pipeline([ ## Event Handlers -In addition to the standard [service connection events](/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), Speechmatics provides: +In addition to the standard [service connection events](/api-reference/server/events/service-events) (`on_connected`, `on_disconnected`, `on_connection_error`), Speechmatics provides: | Event | Description | | -------------------- | -------------------------------------- | diff --git a/server/services/stt/whisper.mdx b/api-reference/server/services/stt/whisper.mdx similarity index 100% rename from server/services/stt/whisper.mdx rename to api-reference/server/services/stt/whisper.mdx diff --git a/api-reference/server/services/supported-services.mdx b/api-reference/server/services/supported-services.mdx new file mode 100644 index 000000000..f12dd9bb9 --- /dev/null +++ b/api-reference/server/services/supported-services.mdx @@ -0,0 +1,179 @@ +--- +title: "Supported Services" +description: "AI services integrated with Pipecat and their setup requirements" +--- + +## Transports + +Transports exchange audio and video streams between the user and bot. + +| Service | Setup | +| ------------------------------------------------------------------------- | -------------------------------------- | +| [DailyTransport](/api-reference/server/services/transport/daily) | `pip install "pipecat-ai[daily]"` | +| [FastAPIWebSocketTransport](/api-reference/server/services/transport/fastapi-websocket) | `pip install "pipecat-ai[websocket]"` | +| [HeyGenTransport](/api-reference/server/services/transport/heygen) | `pip install "pipecat-ai[heygen]"` | +| [LemonSliceTransport](/api-reference/server/services/transport/lemonslice) | `pip install "pipecat-ai[lemonslice]"` | +| [LiveKitTransport](/api-reference/server/services/transport/livekit) | `pip install "pipecat-ai[livekit]"` | +| [SmallWebRTCTransport](/api-reference/server/services/transport/small-webrtc) | `pip install "pipecat-ai[webrtc]"` | +| [TavusTransport](/api-reference/server/services/transport/tavus) | `pip install "pipecat-ai[tavus]"` | +| [WebSocket Transports](/api-reference/server/services/transport/websocket-server) | `pip install "pipecat-ai[websocket]"` | +| [WhatsAppTransport](/api-reference/server/services/transport/whatsapp) | `pip install "pipecat-ai[webrtc]"` | + +## Serializers + +Serializers convert between frames and media streams, enabling real-time communication over a websocket. + +| Service | Setup | +| ----------------------------------------------- | ------------------------ | +| [Exotel](/api-reference/server/services/serializers/exotel) | No dependencies required | +| [Genesys](/api-reference/server/services/serializers/genesys) | No dependencies required | +| [Plivo](/api-reference/server/services/serializers/plivo) | No dependencies required | +| [Telnyx](/api-reference/server/services/serializers/telnyx) | No dependencies required | +| [Twilio](/api-reference/server/services/serializers/twilio) | No dependencies required | +| [Vonage](/api-reference/server/services/serializers/vonage) | No dependencies required | + +## Speech-to-Text + +Speech-to-Text services receive and audio input and output transcriptions. + +| Service | Setup | +| ------------------------------------------------- | ---------------------------------------- | +| [AssemblyAI](/api-reference/server/services/stt/assemblyai) | `pip install "pipecat-ai[assemblyai]"` | +| [AWS Transcribe](/api-reference/server/services/stt/aws) | `pip install "pipecat-ai[aws]"` | +| [Azure](/api-reference/server/services/stt/azure) | `pip install "pipecat-ai[azure]"` | +| [Cartesia](/api-reference/server/services/stt/cartesia) | `pip install "pipecat-ai[cartesia]"` | +| [Deepgram](/api-reference/server/services/stt/deepgram) | `pip install "pipecat-ai[deepgram]"` | +| [ElevenLabs](/api-reference/server/services/stt/elevenlabs) | `pip install "pipecat-ai[elevenlabs]"` | +| [Fal Wizper](/api-reference/server/services/stt/fal) | `pip install "pipecat-ai[fal]"` | +| [Gladia](/api-reference/server/services/stt/gladia) | `pip install "pipecat-ai[gladia]"` | +| [Google](/api-reference/server/services/stt/google) | `pip install "pipecat-ai[google]"` | +| [Gradium](/api-reference/server/services/stt/gradium) | `pip install "pipecat-ai[gradium]"` | +| [Groq (Whisper)](/api-reference/server/services/stt/groq) | `pip install "pipecat-ai[groq]"` | +| [NVIDIA](/api-reference/server/services/stt/nvidia) | `pip install "pipecat-ai[nvidia]"` | +| [OpenAI](/api-reference/server/services/stt/openai) | `pip install "pipecat-ai[openai]"` | +| [Sarvam](/api-reference/server/services/stt/sarvam) | `pip install "pipecat-ai[sarvam]"` | +| [Soniox](/api-reference/server/services/stt/soniox) | `pip install "pipecat-ai[soniox]"` | +| [Speechmatics](/api-reference/server/services/stt/speechmatics) | `pip install "pipecat-ai[speechmatics]"` | +| [Whisper](/api-reference/server/services/stt/whisper) | `pip install "pipecat-ai[whisper]"` | + +## Large Language Models + +LLMs receive text or audio based input and output a streaming text response. + +| Service | Setup | +| --------------------------------------------------------- | -------------------------------------- | +| [Anthropic](/api-reference/server/services/llm/anthropic) | `pip install "pipecat-ai[anthropic]"` | +| [AWS Bedrock](/api-reference/server/services/llm/aws) | `pip install "pipecat-ai[aws]"` | +| [Azure](/api-reference/server/services/llm/azure) | `pip install "pipecat-ai[azure]"` | +| [Cerebras](/api-reference/server/services/llm/cerebras) | `pip install "pipecat-ai[cerebras]"` | +| [DeepSeek](/api-reference/server/services/llm/deepseek) | `pip install "pipecat-ai[deepseek]"` | +| [Fireworks AI](/api-reference/server/services/llm/fireworks) | `pip install "pipecat-ai[fireworks]"` | +| [Google Gemini](/api-reference/server/services/llm/google) | `pip install "pipecat-ai[google]"` | +| [Google Vertex AI](/api-reference/server/services/llm/google-vertex) | `pip install "pipecat-ai[google]"` | +| [Grok](/api-reference/server/services/llm/grok) | `pip install "pipecat-ai[grok]"` | +| [Groq](/api-reference/server/services/llm/groq) | `pip install "pipecat-ai[groq]"` | +| [Mistral](/api-reference/server/services/llm/mistral) | `pip install "pipecat-ai[mistral]"` | +| [NVIDIA](/api-reference/server/services/llm/nvidia) | `pip install "pipecat-ai[nvidia]"` | +| [Novita AI](/api-reference/server/services/llm/novita) | `pip install "pipecat-ai[novita]"` | +| [Ollama](/api-reference/server/services/llm/ollama) | `pip install "pipecat-ai[ollama]"` | +| [OpenAI](/api-reference/server/services/llm/openai) | `pip install "pipecat-ai[openai]"` | +| [OpenAI Responses](/api-reference/server/services/llm/openai-responses) | `pip install "pipecat-ai[openai]"` | +| [OpenPipe](/api-reference/server/services/llm/openpipe) | `pip install "pipecat-ai[openpipe]"` | +| [OpenRouter](/api-reference/server/services/llm/openrouter) | `pip install "pipecat-ai[openrouter]"` | +| [Perplexity](/api-reference/server/services/llm/perplexity) | `pip install "pipecat-ai[perplexity]"` | +| [Qwen](/api-reference/server/services/llm/qwen) | `pip install "pipecat-ai[qwen]"` | +| [SambaNova](/api-reference/server/services/llm/sambanova) | `pip install "pipecat-ai[sambanova]"` | +| [Sarvam](/api-reference/server/services/llm/sarvam) | `pip install "pipecat-ai[sarvam]"` | +| [Together AI](/api-reference/server/services/llm/together) | `pip install "pipecat-ai[together]"` | + +## Text-to-Speech + +Text-to-Speech services receive text input and output audio streams or chunks. + +| Service | Setup | +| ------------------------------------------------- | ---------------------------------------- | +| [Async](/api-reference/server/services/tts/asyncai) | `pip install "pipecat-ai[asyncai]"` | +| [AWS Polly](/api-reference/server/services/tts/aws) | `pip install "pipecat-ai[aws]"` | +| [Azure](/api-reference/server/services/tts/azure) | `pip install "pipecat-ai[azure]"` | +| [Camb AI](/api-reference/server/services/tts/camb) | `pip install "pipecat-ai[camb]"` | +| [Cartesia](/api-reference/server/services/tts/cartesia) | `pip install "pipecat-ai[cartesia]"` | +| [Deepgram](/api-reference/server/services/tts/deepgram) | `pip install "pipecat-ai[deepgram]"` | +| [ElevenLabs](/api-reference/server/services/tts/elevenlabs) | `pip install "pipecat-ai[elevenlabs]"` | +| [Fish](/api-reference/server/services/tts/fish) | `pip install "pipecat-ai[fish]"` | +| [Google](/api-reference/server/services/tts/google) | `pip install "pipecat-ai[google]"` | +| [Gradium](/api-reference/server/services/tts/gradium) | `pip install "pipecat-ai[gradium]"` | +| [Groq](/api-reference/server/services/tts/groq) | `pip install "pipecat-ai[groq]"` | +| [Hume](/api-reference/server/services/tts/hume) | `pip install "pipecat-ai[hume]"` | +| [Inworld](/api-reference/server/services/tts/inworld) | No dependencies required | +| [Kokoro](/api-reference/server/services/tts/kokoro) | `pip install "pipecat-ai[kokoro]"` | +| [LMNT](/api-reference/server/services/tts/lmnt) | `pip install "pipecat-ai[lmnt]"` | +| [MiniMax](/api-reference/server/services/tts/minimax) | No dependencies required | +| [Neuphonic](/api-reference/server/services/tts/neuphonic) | `pip install "pipecat-ai[neuphonic]"` | +| [NVIDIA](/api-reference/server/services/tts/nvidia) | `pip install "pipecat-ai[nvidia]"` | +| [OpenAI](/api-reference/server/services/tts/openai) | `pip install "pipecat-ai[openai]"` | +| [Piper](/api-reference/server/services/tts/piper) | No dependencies required | +| [ResembleAI](/api-reference/server/services/tts/resembleai) | `pip install "pipecat-ai[resembleai]"` | +| [Rime](/api-reference/server/services/tts/rime) | `pip install "pipecat-ai[rime]"` | +| [Sarvam](/api-reference/server/services/tts/sarvam) | No dependencies required | +| [Smallest AI](/api-reference/server/services/tts/smallest) | `pip install "pipecat-ai[smallest]"` | +| [Speechmatics](/api-reference/server/services/tts/speechmatics) | `pip install "pipecat-ai[speechmatics]"` | +| [xAI](/api-reference/server/services/tts/xai) | `pip install "pipecat-ai[xai]"` | +| [XTTS](/api-reference/server/services/tts/xtts) | `pip install "pipecat-ai[xtts]"` | + +## Speech-to-Speech + +Speech-to-Speech services are multi-modal LLM services that take in audio, video, or text and output audio or text. + +| Service | Setup | +| ---------------------------------------------------------------- | ------------------------------------------ | +| [AWS Nova Sonic](/api-reference/server/services/s2s/aws) | `pip install "pipecat-ai[aws-nova-sonic]"` | +| [Gemini Live](/api-reference/server/services/s2s/gemini-live) | `pip install "pipecat-ai[google]"` | +| [Gemini Live Vertex AI](/api-reference/server/services/s2s/gemini-live-vertex) | `pip install "pipecat-ai[google]"` | +| [Grok Voice Agent](/api-reference/server/services/s2s/grok) | `pip install "pipecat-ai[grok]"` | +| [OpenAI Realtime](/api-reference/server/services/s2s/openai) | `pip install "pipecat-ai[openai]"` | +| [Ultravox](/api-reference/server/services/s2s/ultravox) | `pip install "pipecat-ai[ultravox]"` | + +## Image Generation + +Image generation services receive text inputs and output images. + +| Service | Setup | +| -------------------------------------------------- | ---------------------------------- | +| [Azure](/api-reference/server/services/image-generation/azure) | `pip install "pipecat-ai[azure]"` | +| [fal](/api-reference/server/services/image-generation/fal) | `pip install "pipecat-ai[fal]"` | +| [Google](/api-reference/server/services/image-generation/google) | `pip install "pipecat-ai[google]"` | +| [OpenAI](/api-reference/server/services/image-generation/openai) | `pip install "pipecat-ai[openai]"` | + +## Video + +Video services enable you to build an avatar where audio and video are synchronized. + +| Service | Setup | +| --------------------------------------- | ---------------------------------- | +| [HeyGen](/api-reference/server/services/video/heygen) | `pip install "pipecat-ai[heygen]"` | +| [Simli](/api-reference/server/services/video/simli) | `pip install "pipecat-ai[simli]"` | +| [Tavus](/api-reference/server/services/video/tavus) | `pip install "pipecat-ai[tavus]"` | + +## Memory + +Memory services can be used to store and retrieve conversations. + +| Service | Setup | +| ------------------------------------ | -------------------------------- | +| [mem0](/api-reference/server/services/memory/mem0) | `pip install "pipecat-ai[mem0]"` | + +## Vision + +Vision services receive a streaming video input and output text describing the video input. + +| Service | Setup | +| ---------------------------------------------- | ------------------------------------- | +| [Moondream](/api-reference/server/services/vision/moondream) | `pip install "pipecat-ai[moondream]"` | + +## Analytics & Monitoring + +Analytics services help you better understand how your service operates. + +| Service | Setup | +| ------------------------------------------- | ---------------------------------- | +| [Sentry](/api-reference/server/services/analytics/sentry) | `pip install "pipecat-ai[sentry]"` | diff --git a/server/services/transport/daily.mdx b/api-reference/server/services/transport/daily.mdx similarity index 97% rename from server/services/transport/daily.mdx rename to api-reference/server/services/transport/daily.mdx index 51c7c3f09..8e90d4989 100644 --- a/server/services/transport/daily.mdx +++ b/api-reference/server/services/transport/daily.mdx @@ -90,7 +90,7 @@ Before using DailyTransport, you need: Transport configuration parameters. See [DailyParams](#dailyparams) below and - [TransportParams](/server/services/transport/transport-params) for inherited + [TransportParams](/api-reference/server/services/transport/transport-params) for inherited base parameters. @@ -104,7 +104,7 @@ Before using DailyTransport, you need: ### DailyParams -Inherits all parameters from [TransportParams](/server/services/transport/transport-params) (audio, video, VAD settings) with these additional fields: +Inherits all parameters from [TransportParams](/api-reference/server/services/transport/transport-params) (audio, video, VAD settings) with these additional fields: Daily API base URL. @@ -660,7 +660,7 @@ async def on_dtmf_event(transport, data): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat -- [Daily REST Helper Utility](/server/utilities/daily/rest-helper) -- [Pipecat Development Runner's Transport Utilities](/server/utilities/runner/transport-utils) +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat +- [Daily REST Helper Utility](/api-reference/server/utilities/daily/rest-helper) +- [Pipecat Development Runner's Transport Utilities](/api-reference/server/utilities/runner/transport-utils) - [Client SDK Integration](/client/js/transports/daily) diff --git a/server/services/transport/fastapi-websocket.mdx b/api-reference/server/services/transport/fastapi-websocket.mdx similarity index 96% rename from server/services/transport/fastapi-websocket.mdx rename to api-reference/server/services/transport/fastapi-websocket.mdx index 3cb10b058..f9a4d8366 100644 --- a/server/services/transport/fastapi-websocket.mdx +++ b/api-reference/server/services/transport/fastapi-websocket.mdx @@ -39,7 +39,7 @@ For general client/server applications, we recommend using WebRTC-based transpor Learn about supported FrameSerializers for telephony providers @@ -201,5 +201,5 @@ async def on_session_timeout(transport, websocket): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat -- [Serializers](/server/services/serializers/introduction) - Frame serializers for telephony providers +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat +- [Serializers](/api-reference/server/services/serializers/introduction) - Frame serializers for telephony providers diff --git a/server/services/transport/heygen.mdx b/api-reference/server/services/transport/heygen.mdx similarity index 98% rename from server/services/transport/heygen.mdx rename to api-reference/server/services/transport/heygen.mdx index c940a6414..9e92a90cc 100644 --- a/server/services/transport/heygen.mdx +++ b/api-reference/server/services/transport/heygen.mdx @@ -195,4 +195,4 @@ async def on_client_disconnected(transport, participant): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat diff --git a/server/services/transport/lemonslice.mdx b/api-reference/server/services/transport/lemonslice.mdx similarity index 96% rename from server/services/transport/lemonslice.mdx rename to api-reference/server/services/transport/lemonslice.mdx index d2005987b..55ed7f2d7 100644 --- a/server/services/transport/lemonslice.mdx +++ b/api-reference/server/services/transport/lemonslice.mdx @@ -228,9 +228,9 @@ async def on_client_disconnected(transport, participant): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat -- [DailyTransport](/server/services/transport/daily) - Underlying Daily transport +- [DailyTransport](/api-reference/server/services/transport/daily) - Underlying Daily transport documentation -- [TransportParams](/server/services/transport/transport-params) - Base transport +- [TransportParams](/api-reference/server/services/transport/transport-params) - Base transport parameters diff --git a/server/services/transport/livekit.mdx b/api-reference/server/services/transport/livekit.mdx similarity index 98% rename from server/services/transport/livekit.mdx rename to api-reference/server/services/transport/livekit.mdx index 997952c02..707c78ffa 100644 --- a/server/services/transport/livekit.mdx +++ b/api-reference/server/services/transport/livekit.mdx @@ -89,7 +89,7 @@ Before using LiveKitTransport, you need: Transport configuration parameters. Inherits all parameters from - [TransportParams](/server/services/transport/transport-params). + [TransportParams](/api-reference/server/services/transport/transport-params). @@ -321,4 +321,4 @@ async def on_data_received(transport, data, participant_id): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat diff --git a/server/services/transport/small-webrtc.mdx b/api-reference/server/services/transport/small-webrtc.mdx similarity index 97% rename from server/services/transport/small-webrtc.mdx rename to api-reference/server/services/transport/small-webrtc.mdx index 2fa2d8ebd..d34db7ce0 100644 --- a/server/services/transport/small-webrtc.mdx +++ b/api-reference/server/services/transport/small-webrtc.mdx @@ -186,6 +186,6 @@ async def on_app_message(transport, message, sender): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat -- [Pipecat Development Runner's Transport Utilities](/server/utilities/runner/transport-utils) +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat +- [Pipecat Development Runner's Transport Utilities](/api-reference/server/utilities/runner/transport-utils) - [Client SDK Integration](/client/js/transports/small-webrtc) diff --git a/server/services/transport/tavus.mdx b/api-reference/server/services/transport/tavus.mdx similarity index 98% rename from server/services/transport/tavus.mdx rename to api-reference/server/services/transport/tavus.mdx index 16bacd879..9047617ef 100644 --- a/server/services/transport/tavus.mdx +++ b/api-reference/server/services/transport/tavus.mdx @@ -217,5 +217,5 @@ async def on_client_disconnected(transport, participant): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat - [Client SDK Integration](/client/js/transports/daily) diff --git a/server/services/transport/transport-params.mdx b/api-reference/server/services/transport/transport-params.mdx similarity index 86% rename from server/services/transport/transport-params.mdx rename to api-reference/server/services/transport/transport-params.mdx index 41296df30..6244eac60 100644 --- a/server/services/transport/transport-params.mdx +++ b/api-reference/server/services/transport/transport-params.mdx @@ -214,8 +214,8 @@ Each transport extends `TransportParams` with provider-specific fields: | Transport | Params Class | Additional Fields | | ------------------------------------------------------------------------- | ------------------------ | ------------------------------------------------------------------------------------------ | -| [DailyTransport](/server/services/transport/daily) | `DailyParams` | `api_key`, `api_url`, `dialin_settings`, `transcription_enabled`, `transcription_settings` | -| [LiveKitTransport](/server/services/transport/livekit) | `LiveKitParams` | (no additional fields) | -| [SmallWebRTCTransport](/server/services/transport/small-webrtc) | `TransportParams` | Uses base class directly | -| [WebsocketServerTransport](/server/services/transport/websocket-server) | `WebsocketServerParams` | `add_wav_header`, `serializer`, `session_timeout` | -| [FastAPIWebsocketTransport](/server/services/transport/fastapi-websocket) | `FastAPIWebsocketParams` | `serializer`, `session_timeout` | +| [DailyTransport](/api-reference/server/services/transport/daily) | `DailyParams` | `api_key`, `api_url`, `dialin_settings`, `transcription_enabled`, `transcription_settings` | +| [LiveKitTransport](/api-reference/server/services/transport/livekit) | `LiveKitParams` | (no additional fields) | +| [SmallWebRTCTransport](/api-reference/server/services/transport/small-webrtc) | `TransportParams` | Uses base class directly | +| [WebsocketServerTransport](/api-reference/server/services/transport/websocket-server) | `WebsocketServerParams` | `add_wav_header`, `serializer`, `session_timeout` | +| [FastAPIWebsocketTransport](/api-reference/server/services/transport/fastapi-websocket) | `FastAPIWebsocketParams` | `serializer`, `session_timeout` | diff --git a/server/services/transport/websocket-server.mdx b/api-reference/server/services/transport/websocket-server.mdx similarity index 99% rename from server/services/transport/websocket-server.mdx rename to api-reference/server/services/transport/websocket-server.mdx index 128858d58..2c57e9f59 100644 --- a/server/services/transport/websocket-server.mdx +++ b/api-reference/server/services/transport/websocket-server.mdx @@ -285,4 +285,4 @@ async def on_disconnected(transport, websocket): ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat diff --git a/server/services/transport/whatsapp.mdx b/api-reference/server/services/transport/whatsapp.mdx similarity index 95% rename from server/services/transport/whatsapp.mdx rename to api-reference/server/services/transport/whatsapp.mdx index 2e5a6e5cd..60fb7435a 100644 --- a/server/services/transport/whatsapp.mdx +++ b/api-reference/server/services/transport/whatsapp.mdx @@ -129,6 +129,6 @@ See the [complete example](https://github.com/pipecat-ai/pipecat-examples/tree/m ## Additional Resources -- [Events Overview](/server/events/overview) - Overview of all events in Pipecat -- [SmallWebRTCTransport](/server/services/transport/small-webrtc) - The underlying transport used for WebRTC connectivity +- [Events Overview](/api-reference/server/events/overview) - Overview of all events in Pipecat +- [SmallWebRTCTransport](/api-reference/server/services/transport/small-webrtc) - The underlying transport used for WebRTC connectivity - [WhatsApp Cloud API Calling Docs](https://developers.facebook.com/docs/whatsapp/cloud-api/calling/) - Official WhatsApp calling documentation diff --git a/server/services/tts/asyncai.mdx b/api-reference/server/services/tts/asyncai.mdx similarity index 98% rename from server/services/tts/asyncai.mdx rename to api-reference/server/services/tts/asyncai.mdx index 08c426fe2..be6fc4482 100644 --- a/server/services/tts/asyncai.mdx +++ b/api-reference/server/services/tts/asyncai.mdx @@ -196,7 +196,7 @@ async with aiohttp.ClientSession() as session: ## Event Handlers -Async TTS supports the standard [service connection events](/server/events/service-events): +Async TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ----------------------------------- | diff --git a/server/services/tts/aws.mdx b/api-reference/server/services/tts/aws.mdx similarity index 100% rename from server/services/tts/aws.mdx rename to api-reference/server/services/tts/aws.mdx diff --git a/server/services/tts/azure.mdx b/api-reference/server/services/tts/azure.mdx similarity index 100% rename from server/services/tts/azure.mdx rename to api-reference/server/services/tts/azure.mdx diff --git a/server/services/tts/camb.mdx b/api-reference/server/services/tts/camb.mdx similarity index 100% rename from server/services/tts/camb.mdx rename to api-reference/server/services/tts/camb.mdx diff --git a/server/services/tts/cartesia.mdx b/api-reference/server/services/tts/cartesia.mdx similarity index 99% rename from server/services/tts/cartesia.mdx rename to api-reference/server/services/tts/cartesia.mdx index a4ea8db84..1da308efb 100644 --- a/server/services/tts/cartesia.mdx +++ b/api-reference/server/services/tts/cartesia.mdx @@ -328,7 +328,7 @@ tts = CartesiaTTSService( ## Event Handlers -Cartesia TTS supports the standard [service connection events](/server/events/service-events): +Cartesia TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ------------------------------------ | diff --git a/server/services/tts/deepgram.mdx b/api-reference/server/services/tts/deepgram.mdx similarity index 99% rename from server/services/tts/deepgram.mdx rename to api-reference/server/services/tts/deepgram.mdx index da6257719..866c39f82 100644 --- a/server/services/tts/deepgram.mdx +++ b/api-reference/server/services/tts/deepgram.mdx @@ -275,7 +275,7 @@ tts = DeepgramSageMakerTTSService( ## Event Handlers -The WebSocket and SageMaker services support the standard [service connection events](/server/events/service-events): +The WebSocket and SageMaker services support the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ---------------------------------------------- | diff --git a/server/services/tts/elevenlabs.mdx b/api-reference/server/services/tts/elevenlabs.mdx similarity index 99% rename from server/services/tts/elevenlabs.mdx rename to api-reference/server/services/tts/elevenlabs.mdx index d8fa5c20d..644f62c86 100644 --- a/server/services/tts/elevenlabs.mdx +++ b/api-reference/server/services/tts/elevenlabs.mdx @@ -234,7 +234,7 @@ async with aiohttp.ClientSession() as session: ## Event Handlers -ElevenLabs TTS supports the standard [service connection events](/server/events/service-events): +ElevenLabs TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | -------------------------------------- | diff --git a/server/services/tts/fish.mdx b/api-reference/server/services/tts/fish.mdx similarity index 99% rename from server/services/tts/fish.mdx rename to api-reference/server/services/tts/fish.mdx index 812bb32ed..66748980a 100644 --- a/server/services/tts/fish.mdx +++ b/api-reference/server/services/tts/fish.mdx @@ -159,7 +159,7 @@ tts = FishAudioTTSService( ## Event Handlers -Fish Audio TTS supports the standard [service connection events](/server/events/service-events): +Fish Audio TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | -------------------------------------- | diff --git a/server/services/tts/google.mdx b/api-reference/server/services/tts/google.mdx similarity index 100% rename from server/services/tts/google.mdx rename to api-reference/server/services/tts/google.mdx diff --git a/server/services/tts/gradium.mdx b/api-reference/server/services/tts/gradium.mdx similarity index 97% rename from server/services/tts/gradium.mdx rename to api-reference/server/services/tts/gradium.mdx index 942ab8397..8b363fa95 100644 --- a/server/services/tts/gradium.mdx +++ b/api-reference/server/services/tts/gradium.mdx @@ -151,7 +151,7 @@ tts = GradiumTTSService( ## Event Handlers -Gradium TTS supports the standard [service connection events](/server/events/service-events): +Gradium TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ----------------------------------- | diff --git a/server/services/tts/groq.mdx b/api-reference/server/services/tts/groq.mdx similarity index 100% rename from server/services/tts/groq.mdx rename to api-reference/server/services/tts/groq.mdx diff --git a/server/services/tts/hume.mdx b/api-reference/server/services/tts/hume.mdx similarity index 100% rename from server/services/tts/hume.mdx rename to api-reference/server/services/tts/hume.mdx diff --git a/server/services/tts/inworld.mdx b/api-reference/server/services/tts/inworld.mdx similarity index 98% rename from server/services/tts/inworld.mdx rename to api-reference/server/services/tts/inworld.mdx index 984859628..93e0027c7 100644 --- a/server/services/tts/inworld.mdx +++ b/api-reference/server/services/tts/inworld.mdx @@ -245,7 +245,7 @@ async with aiohttp.ClientSession() as session: ## Event Handlers -Inworld TTS supports the standard [service connection events](/server/events/service-events): +Inworld TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ----------------------------------- | diff --git a/server/services/tts/kokoro.mdx b/api-reference/server/services/tts/kokoro.mdx similarity index 100% rename from server/services/tts/kokoro.mdx rename to api-reference/server/services/tts/kokoro.mdx diff --git a/server/services/tts/lmnt.mdx b/api-reference/server/services/tts/lmnt.mdx similarity index 97% rename from server/services/tts/lmnt.mdx rename to api-reference/server/services/tts/lmnt.mdx index 474fa1e0f..6b5da4f3e 100644 --- a/server/services/tts/lmnt.mdx +++ b/api-reference/server/services/tts/lmnt.mdx @@ -143,7 +143,7 @@ tts = LmntTTSService( ## Event Handlers -LMNT TTS supports the standard [service connection events](/server/events/service-events): +LMNT TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ----------------------------------- | diff --git a/server/services/tts/minimax.mdx b/api-reference/server/services/tts/minimax.mdx similarity index 100% rename from server/services/tts/minimax.mdx rename to api-reference/server/services/tts/minimax.mdx diff --git a/server/services/tts/neuphonic.mdx b/api-reference/server/services/tts/neuphonic.mdx similarity index 99% rename from server/services/tts/neuphonic.mdx rename to api-reference/server/services/tts/neuphonic.mdx index c16745166..50eff27b3 100644 --- a/server/services/tts/neuphonic.mdx +++ b/api-reference/server/services/tts/neuphonic.mdx @@ -234,7 +234,7 @@ async with aiohttp.ClientSession() as session: ## Event Handlers -Neuphonic WebSocket TTS supports the standard [service connection events](/server/events/service-events): +Neuphonic WebSocket TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ------------------------------------- | diff --git a/server/services/tts/nvidia.mdx b/api-reference/server/services/tts/nvidia.mdx similarity index 100% rename from server/services/tts/nvidia.mdx rename to api-reference/server/services/tts/nvidia.mdx diff --git a/server/services/tts/openai.mdx b/api-reference/server/services/tts/openai.mdx similarity index 100% rename from server/services/tts/openai.mdx rename to api-reference/server/services/tts/openai.mdx diff --git a/server/services/tts/piper.mdx b/api-reference/server/services/tts/piper.mdx similarity index 100% rename from server/services/tts/piper.mdx rename to api-reference/server/services/tts/piper.mdx diff --git a/server/services/tts/resembleai.mdx b/api-reference/server/services/tts/resembleai.mdx similarity index 99% rename from server/services/tts/resembleai.mdx rename to api-reference/server/services/tts/resembleai.mdx index ba559579d..70e53593c 100644 --- a/server/services/tts/resembleai.mdx +++ b/api-reference/server/services/tts/resembleai.mdx @@ -149,7 +149,7 @@ tts = ResembleAITTSService( ## Event Handlers -Resemble AI TTS supports the standard [service connection events](/server/events/service-events): +Resemble AI TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | --------------------------------------- | diff --git a/server/services/tts/rime.mdx b/api-reference/server/services/tts/rime.mdx similarity index 99% rename from server/services/tts/rime.mdx rename to api-reference/server/services/tts/rime.mdx index ae87be0cb..a934df4a3 100644 --- a/server/services/tts/rime.mdx +++ b/api-reference/server/services/tts/rime.mdx @@ -398,7 +398,7 @@ tts = RimeTTSService( ## Event Handlers -Rime WebSocket TTS services support the standard [service connection events](/server/events/service-events): +Rime WebSocket TTS services support the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ----------------------------------- | diff --git a/server/services/tts/sarvam.mdx b/api-reference/server/services/tts/sarvam.mdx similarity index 99% rename from server/services/tts/sarvam.mdx rename to api-reference/server/services/tts/sarvam.mdx index c0f2ce8c7..57eeefb64 100644 --- a/server/services/tts/sarvam.mdx +++ b/api-reference/server/services/tts/sarvam.mdx @@ -262,7 +262,7 @@ async with aiohttp.ClientSession() as session: ## Event Handlers -Sarvam WebSocket TTS supports the standard [service connection events](/server/events/service-events): +Sarvam WebSocket TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ----------------------------------- | diff --git a/server/services/tts/smallest.mdx b/api-reference/server/services/tts/smallest.mdx similarity index 99% rename from server/services/tts/smallest.mdx rename to api-reference/server/services/tts/smallest.mdx index 650a79afa..89300e41e 100644 --- a/server/services/tts/smallest.mdx +++ b/api-reference/server/services/tts/smallest.mdx @@ -160,7 +160,7 @@ await task.queue_frame( ## Event Handlers -Smallest AI TTS supports the standard [service connection events](/server/events/service-events): +Smallest AI TTS supports the standard [service connection events](/api-reference/server/events/service-events): | Event | Description | | --------------------- | ------------------------------------ | diff --git a/server/services/tts/speechmatics.mdx b/api-reference/server/services/tts/speechmatics.mdx similarity index 100% rename from server/services/tts/speechmatics.mdx rename to api-reference/server/services/tts/speechmatics.mdx diff --git a/server/services/tts/xai.mdx b/api-reference/server/services/tts/xai.mdx similarity index 100% rename from server/services/tts/xai.mdx rename to api-reference/server/services/tts/xai.mdx diff --git a/server/services/tts/xtts.mdx b/api-reference/server/services/tts/xtts.mdx similarity index 100% rename from server/services/tts/xtts.mdx rename to api-reference/server/services/tts/xtts.mdx diff --git a/server/services/video/heygen.mdx b/api-reference/server/services/video/heygen.mdx similarity index 100% rename from server/services/video/heygen.mdx rename to api-reference/server/services/video/heygen.mdx diff --git a/server/services/video/simli.mdx b/api-reference/server/services/video/simli.mdx similarity index 100% rename from server/services/video/simli.mdx rename to api-reference/server/services/video/simli.mdx diff --git a/server/services/video/tavus.mdx b/api-reference/server/services/video/tavus.mdx similarity index 100% rename from server/services/video/tavus.mdx rename to api-reference/server/services/video/tavus.mdx diff --git a/server/services/vision/moondream.mdx b/api-reference/server/services/vision/moondream.mdx similarity index 100% rename from server/services/vision/moondream.mdx rename to api-reference/server/services/vision/moondream.mdx diff --git a/server/utilities/audio/aic-filter.mdx b/api-reference/server/utilities/audio/aic-filter.mdx similarity index 100% rename from server/utilities/audio/aic-filter.mdx rename to api-reference/server/utilities/audio/aic-filter.mdx diff --git a/server/utilities/audio/audio-buffer-processor.mdx b/api-reference/server/utilities/audio/audio-buffer-processor.mdx similarity index 100% rename from server/utilities/audio/audio-buffer-processor.mdx rename to api-reference/server/utilities/audio/audio-buffer-processor.mdx diff --git a/server/utilities/audio/koala-filter.mdx b/api-reference/server/utilities/audio/koala-filter.mdx similarity index 100% rename from server/utilities/audio/koala-filter.mdx rename to api-reference/server/utilities/audio/koala-filter.mdx diff --git a/server/utilities/audio/krisp-viva-filter.mdx b/api-reference/server/utilities/audio/krisp-viva-filter.mdx similarity index 100% rename from server/utilities/audio/krisp-viva-filter.mdx rename to api-reference/server/utilities/audio/krisp-viva-filter.mdx diff --git a/server/utilities/audio/krisp-viva-vad-analyzer.mdx b/api-reference/server/utilities/audio/krisp-viva-vad-analyzer.mdx similarity index 100% rename from server/utilities/audio/krisp-viva-vad-analyzer.mdx rename to api-reference/server/utilities/audio/krisp-viva-vad-analyzer.mdx diff --git a/server/utilities/audio/rnnoise-filter.mdx b/api-reference/server/utilities/audio/rnnoise-filter.mdx similarity index 100% rename from server/utilities/audio/rnnoise-filter.mdx rename to api-reference/server/utilities/audio/rnnoise-filter.mdx diff --git a/server/utilities/audio/silero-vad-analyzer.mdx b/api-reference/server/utilities/audio/silero-vad-analyzer.mdx similarity index 100% rename from server/utilities/audio/silero-vad-analyzer.mdx rename to api-reference/server/utilities/audio/silero-vad-analyzer.mdx diff --git a/server/utilities/audio/soundfile-mixer.mdx b/api-reference/server/utilities/audio/soundfile-mixer.mdx similarity index 100% rename from server/utilities/audio/soundfile-mixer.mdx rename to api-reference/server/utilities/audio/soundfile-mixer.mdx diff --git a/server/utilities/context-summarization.mdx b/api-reference/server/utilities/context-summarization.mdx similarity index 100% rename from server/utilities/context-summarization.mdx rename to api-reference/server/utilities/context-summarization.mdx diff --git a/server/utilities/daily/rest-helper.mdx b/api-reference/server/utilities/daily/rest-helper.mdx similarity index 100% rename from server/utilities/daily/rest-helper.mdx rename to api-reference/server/utilities/daily/rest-helper.mdx diff --git a/server/utilities/dtmf-aggregator.mdx b/api-reference/server/utilities/dtmf-aggregator.mdx similarity index 100% rename from server/utilities/dtmf-aggregator.mdx rename to api-reference/server/utilities/dtmf-aggregator.mdx diff --git a/server/utilities/extensions/ivr.mdx b/api-reference/server/utilities/extensions/ivr.mdx similarity index 100% rename from server/utilities/extensions/ivr.mdx rename to api-reference/server/utilities/extensions/ivr.mdx diff --git a/server/utilities/extensions/voicemail.mdx b/api-reference/server/utilities/extensions/voicemail.mdx similarity index 100% rename from server/utilities/extensions/voicemail.mdx rename to api-reference/server/utilities/extensions/voicemail.mdx diff --git a/server/utilities/filters/frame-filter.mdx b/api-reference/server/utilities/filters/frame-filter.mdx similarity index 100% rename from server/utilities/filters/frame-filter.mdx rename to api-reference/server/utilities/filters/frame-filter.mdx diff --git a/server/utilities/filters/function-filter.mdx b/api-reference/server/utilities/filters/function-filter.mdx similarity index 100% rename from server/utilities/filters/function-filter.mdx rename to api-reference/server/utilities/filters/function-filter.mdx diff --git a/server/utilities/filters/identify-filter.mdx b/api-reference/server/utilities/filters/identify-filter.mdx similarity index 100% rename from server/utilities/filters/identify-filter.mdx rename to api-reference/server/utilities/filters/identify-filter.mdx diff --git a/server/utilities/filters/null-filter.mdx b/api-reference/server/utilities/filters/null-filter.mdx similarity index 100% rename from server/utilities/filters/null-filter.mdx rename to api-reference/server/utilities/filters/null-filter.mdx diff --git a/server/utilities/filters/stt-mute.mdx b/api-reference/server/utilities/filters/stt-mute.mdx similarity index 98% rename from server/utilities/filters/stt-mute.mdx rename to api-reference/server/utilities/filters/stt-mute.mdx index 4612db86b..4fbee7581 100644 --- a/server/utilities/filters/stt-mute.mdx +++ b/api-reference/server/utilities/filters/stt-mute.mdx @@ -5,7 +5,7 @@ description: "Processor for controlling STT muting and interruption handling dur DEPRECATED: STTMuteFilter has been deprecated in favor of [User Mute - Strategies](/server/utilities/turn-management/user-mute-strategies). Configure + Strategies](/api-reference/server/utilities/turn-management/user-mute-strategies). Configure `user_mute_strategies` on the `LLMUserAggregator` instead. diff --git a/server/utilities/filters/wake-check-filter.mdx b/api-reference/server/utilities/filters/wake-check-filter.mdx similarity index 95% rename from server/utilities/filters/wake-check-filter.mdx rename to api-reference/server/utilities/filters/wake-check-filter.mdx index 343e5283e..91d982bf0 100644 --- a/server/utilities/filters/wake-check-filter.mdx +++ b/api-reference/server/utilities/filters/wake-check-filter.mdx @@ -5,7 +5,7 @@ description: "Processor that passes frames only after detecting wake phrases in **Deprecated:** `WakeCheckFilter` is deprecated in favor of - [`WakePhraseUserTurnStartStrategy`](/server/utilities/turn-management/user-turn-strategies#wakephraseuserturns tartstrategy). + [`WakePhraseUserTurnStartStrategy`](/api-reference/server/utilities/turn-management/user-turn-strategies#wakephraseuserturns tartstrategy). The new strategy provides better integration with turn management and supports both timeout and single-activation modes. diff --git a/server/utilities/filters/wake-notifier-filter.mdx b/api-reference/server/utilities/filters/wake-notifier-filter.mdx similarity index 100% rename from server/utilities/filters/wake-notifier-filter.mdx rename to api-reference/server/utilities/filters/wake-notifier-filter.mdx diff --git a/server/utilities/frame/llm-text-processor.mdx b/api-reference/server/utilities/frame/llm-text-processor.mdx similarity index 97% rename from server/utilities/frame/llm-text-processor.mdx rename to api-reference/server/utilities/frame/llm-text-processor.mdx index 086fe4776..8bad6257f 100644 --- a/server/utilities/frame/llm-text-processor.mdx +++ b/api-reference/server/utilities/frame/llm-text-processor.mdx @@ -46,7 +46,7 @@ The `LLMTextProcessor` should be integrated into your pipeline after the LLM ser For more usage examples, check out the docs for the - [PatternPairAggregator](/server/utilities/text/pattern-pair-aggregator#usage-examples). + [PatternPairAggregator](/api-reference/server/utilities/text/pattern-pair-aggregator#usage-examples). ```python diff --git a/server/utilities/frame/producer-consumer.mdx b/api-reference/server/utilities/frame/producer-consumer.mdx similarity index 94% rename from server/utilities/frame/producer-consumer.mdx rename to api-reference/server/utilities/frame/producer-consumer.mdx index bdb66649c..526bff2f7 100644 --- a/server/utilities/frame/producer-consumer.mdx +++ b/api-reference/server/utilities/frame/producer-consumer.mdx @@ -5,7 +5,7 @@ description: "Route frames between different parts of a pipeline, allowing selec ## Overview -The Producer and Consumer processors work as a pair to route frames between different parts of a pipeline, particularly useful when working with [`ParallelPipeline`](/server/pipeline/parallel-pipeline). They allow you to selectively capture frames from one pipeline branch and inject them into another. +The Producer and Consumer processors work as a pair to route frames between different parts of a pipeline, particularly useful when working with [`ParallelPipeline`](/api-reference/server/pipeline/parallel-pipeline). They allow you to selectively capture frames from one pipeline branch and inject them into another. ## ProducerProcessor diff --git a/server/utilities/mcp/mcp.mdx b/api-reference/server/utilities/mcp/mcp.mdx similarity index 100% rename from server/utilities/mcp/mcp.mdx rename to api-reference/server/utilities/mcp/mcp.mdx diff --git a/server/utilities/observers/debug-observer.mdx b/api-reference/server/utilities/observers/debug-observer.mdx similarity index 100% rename from server/utilities/observers/debug-observer.mdx rename to api-reference/server/utilities/observers/debug-observer.mdx diff --git a/server/utilities/observers/llm-observer.mdx b/api-reference/server/utilities/observers/llm-observer.mdx similarity index 100% rename from server/utilities/observers/llm-observer.mdx rename to api-reference/server/utilities/observers/llm-observer.mdx diff --git a/server/utilities/observers/observer-pattern.mdx b/api-reference/server/utilities/observers/observer-pattern.mdx similarity index 89% rename from server/utilities/observers/observer-pattern.mdx rename to api-reference/server/utilities/observers/observer-pattern.mdx index 586227e0a..417013e79 100644 --- a/server/utilities/observers/observer-pattern.mdx +++ b/api-reference/server/utilities/observers/observer-pattern.mdx @@ -44,9 +44,9 @@ Pipecat provides several built-in observers: - **LLMLogObserver**: Logs LLM activity and responses - **TranscriptionLogObserver**: Logs speech-to-text transcription events - **RTVIObserver**: Converts internal frames to RTVI protocol messages for server to client messaging -- **[StartupTimingObserver](/server/utilities/observers/startup-timing-observer)**: Measures processor startup times and transport readiness -- **[UserBotLatencyObserver](/server/utilities/observers/user-bot-latency-observer)**: Measures user-to-bot response latency -- **[TurnTrackingObserver](/server/utilities/observers/turn-tracking-observer)**: Tracks conversation turns and events +- **[StartupTimingObserver](/api-reference/server/utilities/observers/startup-timing-observer)**: Measures processor startup times and transport readiness +- **[UserBotLatencyObserver](/api-reference/server/utilities/observers/user-bot-latency-observer)**: Measures user-to-bot response latency +- **[TurnTrackingObserver](/api-reference/server/utilities/observers/turn-tracking-observer)**: Tracks conversation turns and events ## Using Multiple Observers diff --git a/server/utilities/observers/startup-timing-observer.mdx b/api-reference/server/utilities/observers/startup-timing-observer.mdx similarity index 100% rename from server/utilities/observers/startup-timing-observer.mdx rename to api-reference/server/utilities/observers/startup-timing-observer.mdx diff --git a/server/utilities/observers/transcription-observer.mdx b/api-reference/server/utilities/observers/transcription-observer.mdx similarity index 100% rename from server/utilities/observers/transcription-observer.mdx rename to api-reference/server/utilities/observers/transcription-observer.mdx diff --git a/server/utilities/observers/turn-tracking-observer.mdx b/api-reference/server/utilities/observers/turn-tracking-observer.mdx similarity index 100% rename from server/utilities/observers/turn-tracking-observer.mdx rename to api-reference/server/utilities/observers/turn-tracking-observer.mdx diff --git a/server/utilities/observers/user-bot-latency-observer.mdx b/api-reference/server/utilities/observers/user-bot-latency-observer.mdx similarity index 100% rename from server/utilities/observers/user-bot-latency-observer.mdx rename to api-reference/server/utilities/observers/user-bot-latency-observer.mdx diff --git a/server/utilities/opentelemetry.mdx b/api-reference/server/utilities/opentelemetry.mdx similarity index 100% rename from server/utilities/opentelemetry.mdx rename to api-reference/server/utilities/opentelemetry.mdx diff --git a/server/utilities/runner/guide.mdx b/api-reference/server/utilities/runner/guide.mdx similarity index 100% rename from server/utilities/runner/guide.mdx rename to api-reference/server/utilities/runner/guide.mdx diff --git a/server/utilities/runner/transport-utils.mdx b/api-reference/server/utilities/runner/transport-utils.mdx similarity index 97% rename from server/utilities/runner/transport-utils.mdx rename to api-reference/server/utilities/runner/transport-utils.mdx index 9e02b4776..a48ce9570 100644 --- a/server/utilities/runner/transport-utils.mdx +++ b/api-reference/server/utilities/runner/transport-utils.mdx @@ -5,7 +5,7 @@ description: "Configuration and helper utilities for Daily, LiveKit, telephony, ## Overview -Pipecat provides several utility modules for configuring transports and handling transport-specific operations. While the [development runner](/server/utilities/runner/guide) handles most of these automatically, these utilities are useful for custom setups, advanced configurations, or when building your own deployment infrastructure. +Pipecat provides several utility modules for configuring transports and handling transport-specific operations. While the [development runner](/api-reference/server/utilities/runner/guide) handles most of these automatically, these utilities are useful for custom setups, advanced configurations, or when building your own deployment infrastructure. ## Daily Configuration diff --git a/server/utilities/service-switchers/llm-switcher.mdx b/api-reference/server/utilities/service-switchers/llm-switcher.mdx similarity index 100% rename from server/utilities/service-switchers/llm-switcher.mdx rename to api-reference/server/utilities/service-switchers/llm-switcher.mdx diff --git a/server/utilities/service-switchers/service-switcher.mdx b/api-reference/server/utilities/service-switchers/service-switcher.mdx similarity index 100% rename from server/utilities/service-switchers/service-switcher.mdx rename to api-reference/server/utilities/service-switchers/service-switcher.mdx diff --git a/server/utilities/text/markdown-text-filter.mdx b/api-reference/server/utilities/text/markdown-text-filter.mdx similarity index 100% rename from server/utilities/text/markdown-text-filter.mdx rename to api-reference/server/utilities/text/markdown-text-filter.mdx diff --git a/server/utilities/text/overview.mdx b/api-reference/server/utilities/text/overview.mdx similarity index 100% rename from server/utilities/text/overview.mdx rename to api-reference/server/utilities/text/overview.mdx diff --git a/server/utilities/text/pattern-pair-aggregator.mdx b/api-reference/server/utilities/text/pattern-pair-aggregator.mdx similarity index 100% rename from server/utilities/text/pattern-pair-aggregator.mdx rename to api-reference/server/utilities/text/pattern-pair-aggregator.mdx diff --git a/server/utilities/transcript-processor.mdx b/api-reference/server/utilities/transcript-processor.mdx similarity index 98% rename from server/utilities/transcript-processor.mdx rename to api-reference/server/utilities/transcript-processor.mdx index 52214a12e..9b1fd771c 100644 --- a/server/utilities/transcript-processor.mdx +++ b/api-reference/server/utilities/transcript-processor.mdx @@ -7,7 +7,7 @@ description: "Factory for creating and managing conversation transcript processo DEPRECATED: TranscriptProcessor has been deprecated. Use `on_user_turn_stopped` and `on_assistant_turn_stopped` events on the context aggregators to collect transcriptions, see - [Transcriptions](/server/utilities/turn-management/transcriptions) for + [Transcriptions](/api-reference/server/utilities/turn-management/transcriptions) for details. diff --git a/server/utilities/turn-detection/fal-smart-turn.mdx b/api-reference/server/utilities/turn-detection/fal-smart-turn.mdx similarity index 94% rename from server/utilities/turn-detection/fal-smart-turn.mdx rename to api-reference/server/utilities/turn-detection/fal-smart-turn.mdx index 15ef5681d..d45bca2ec 100644 --- a/server/utilities/turn-detection/fal-smart-turn.mdx +++ b/api-reference/server/utilities/turn-detection/fal-smart-turn.mdx @@ -5,7 +5,7 @@ description: "Cloud-hosted Smart Turn detection using Fal.ai" DEPRECATED: `FalSmartTurnAnalyzer` is deprecated. Please use - [LocalSmartTurnAnalyzerV3](/server/utilities/turn-detection/smart-turn-overview#local-smart-turn) + [LocalSmartTurnAnalyzerV3](/api-reference/server/utilities/turn-detection/smart-turn-overview#local-smart-turn) instead, which provides fast CPU inference without requiring external API calls. @@ -52,7 +52,7 @@ pip install "pipecat-ai[remote-smart-turn]" Configuration parameters for turn detection. See - [SmartTurnParams](/server/utilities/turn-detection/smart-turn-overview#configuration) + [SmartTurnParams](/api-reference/server/utilities/turn-detection/smart-turn-overview#configuration) for details. diff --git a/server/utilities/turn-detection/krisp-viva-turn.mdx b/api-reference/server/utilities/turn-detection/krisp-viva-turn.mdx similarity index 88% rename from server/utilities/turn-detection/krisp-viva-turn.mdx rename to api-reference/server/utilities/turn-detection/krisp-viva-turn.mdx index 65abc2264..6b7922dfb 100644 --- a/server/utilities/turn-detection/krisp-viva-turn.mdx +++ b/api-reference/server/utilities/turn-detection/krisp-viva-turn.mdx @@ -5,7 +5,7 @@ description: "Turn detection using Krisp VIVA SDK" ## Overview -`KrispVivaTurn` is a turn analyzer that uses Krisp's VIVA SDK turn detection (Tt) API to determine when a user has finished speaking. Unlike the [Smart Turn model](/server/utilities/turn-detection/smart-turn-overview) which analyzes audio in batches when VAD detects a pause, `KrispVivaTurn` processes audio frame-by-frame in real time using Krisp's streaming model. +`KrispVivaTurn` is a turn analyzer that uses Krisp's VIVA SDK turn detection (Tt) API to determine when a user has finished speaking. Unlike the [Smart Turn model](/api-reference/server/utilities/turn-detection/smart-turn-overview) which analyzes audio in batches when VAD detects a pause, `KrispVivaTurn` processes audio frame-by-frame in real time using Krisp's streaming model. Configured strategies for starting and stopping user turns. See [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies) for + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) for available options. @@ -161,6 +161,6 @@ pipeline = Pipeline( ## Related -- [User Turn Strategies](/server/utilities/turn-management/user-turn-strategies) - Configure turn detection strategies -- [Parallel Pipeline](/server/pipeline/parallel-pipeline) - Run multiple pipeline branches concurrently -- [Turn Events](/server/utilities/turn-management/turn-events) - Handle turn lifecycle events +- [User Turn Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) - Configure turn detection strategies +- [Parallel Pipeline](/api-reference/server/pipeline/parallel-pipeline) - Run multiple pipeline branches concurrently +- [Turn Events](/api-reference/server/utilities/turn-management/turn-events) - Handle turn lifecycle events diff --git a/server/utilities/turn-management/filter-incomplete-turns.mdx b/api-reference/server/utilities/turn-management/filter-incomplete-turns.mdx similarity index 96% rename from server/utilities/turn-management/filter-incomplete-turns.mdx rename to api-reference/server/utilities/turn-management/filter-incomplete-turns.mdx index 2e95c836e..aa32a1072 100644 --- a/server/utilities/turn-management/filter-incomplete-turns.mdx +++ b/api-reference/server/utilities/turn-management/filter-incomplete-turns.mdx @@ -299,6 +299,6 @@ This ensures the feature doesn't break conversations if the LLM occasionally dis ## Related -- [User Turn Strategies](/server/utilities/turn-management/user-turn-strategies) - Configure turn detection -- [Smart Turn Detection](/server/utilities/turn-detection/smart-turn-overview) - AI-powered end-of-turn detection -- [Transcriptions](/server/utilities/turn-management/transcriptions) - Working with conversation transcripts +- [User Turn Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) - Configure turn detection +- [Smart Turn Detection](/api-reference/server/utilities/turn-detection/smart-turn-overview) - AI-powered end-of-turn detection +- [Transcriptions](/api-reference/server/utilities/turn-management/transcriptions) - Working with conversation transcripts diff --git a/server/utilities/turn-management/interruption-strategies.mdx b/api-reference/server/utilities/turn-management/interruption-strategies.mdx similarity index 98% rename from server/utilities/turn-management/interruption-strategies.mdx rename to api-reference/server/utilities/turn-management/interruption-strategies.mdx index 4e1325f30..9f76dcd67 100644 --- a/server/utilities/turn-management/interruption-strategies.mdx +++ b/api-reference/server/utilities/turn-management/interruption-strategies.mdx @@ -5,7 +5,7 @@ description: "Configure when users can interrupt the bot to prevent unwanted int DEPRECATED Interruption strategies have been deprecated in favor of [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies). + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies). ## Overview diff --git a/server/utilities/turn-management/transcriptions.mdx b/api-reference/server/utilities/turn-management/transcriptions.mdx similarity index 87% rename from server/utilities/turn-management/transcriptions.mdx rename to api-reference/server/utilities/turn-management/transcriptions.mdx index d36d9b4cc..6e08ee868 100644 --- a/server/utilities/turn-management/transcriptions.mdx +++ b/api-reference/server/utilities/turn-management/transcriptions.mdx @@ -5,7 +5,7 @@ description: "Collect user and assistant conversation transcripts using turn eve ## Overview -Pipecat provides a straightforward way to collect conversation transcriptions using [turn events](/server/utilities/turn-management/turn-events). When a user or assistant turn ends, the corresponding event includes the complete transcript for that turn. +Pipecat provides a straightforward way to collect conversation transcriptions using [turn events](/api-reference/server/utilities/turn-management/turn-events). When a user or assistant turn ends, the corresponding event includes the complete transcript for that turn. The key events for transcription collection are: @@ -89,9 +89,9 @@ async def on_assistant_turn_stopped(aggregator, message: AssistantTurnStoppedMes ## Message Types -For details on `UserTurnStoppedMessage` and `AssistantTurnStoppedMessage` fields, see [Turn Events - Message Types](/server/utilities/turn-management/turn-events#message-types). +For details on `UserTurnStoppedMessage` and `AssistantTurnStoppedMessage` fields, see [Turn Events - Message Types](/api-reference/server/utilities/turn-management/turn-events#message-types). ## Related -- [Turn Events](/server/utilities/turn-management/turn-events) - Complete reference for turn lifecycle events +- [Turn Events](/api-reference/server/utilities/turn-management/turn-events) - Complete reference for turn lifecycle events - [Saving Transcripts Guide](/pipecat/fundamentals/saving-transcripts) - Guide for saving conversation transcripts diff --git a/server/utilities/turn-management/turn-events.mdx b/api-reference/server/utilities/turn-management/turn-events.mdx similarity index 93% rename from server/utilities/turn-management/turn-events.mdx rename to api-reference/server/utilities/turn-management/turn-events.mdx index 28f361d31..8aab363da 100644 --- a/server/utilities/turn-management/turn-events.mdx +++ b/api-reference/server/utilities/turn-management/turn-events.mdx @@ -32,7 +32,7 @@ User turn events are registered on the `user_aggregator` from an `LLMContextAggr ### on_user_turn_started -Fired when a user turn is detected to have started, based on the configured [start strategies](/server/utilities/turn-management/user-turn-strategies#start-strategies). +Fired when a user turn is detected to have started, based on the configured [start strategies](/api-reference/server/utilities/turn-management/user-turn-strategies#start-strategies). ```python @user_aggregator.event_handler("on_user_turn_started") @@ -49,7 +49,7 @@ async def on_user_turn_started(aggregator, strategy): ### on_user_turn_stopped -Fired when a user turn is detected to have ended, based on the configured [stop strategies](/server/utilities/turn-management/user-turn-strategies#stop-strategies). This event includes the complete user transcript for the turn. +Fired when a user turn is detected to have ended, based on the configured [stop strategies](/api-reference/server/utilities/turn-management/user-turn-strategies#stop-strategies). This event includes the complete user transcript for the turn. ```python @user_aggregator.event_handler("on_user_turn_stopped") @@ -241,7 +241,7 @@ async def on_summary_applied(aggregator, summarizer, event: SummaryAppliedEvent) This event requires `enable_auto_context_summarization=True` in the `LLMAssistantAggregatorParams` or manual triggering via `LLMSummarizeContextFrame`. See [Context - Summarization](/server/utilities/context-summarization) for details. + Summarization](/api-reference/server/utilities/context-summarization) for details. ## Message Types @@ -300,6 +300,6 @@ from pipecat.processors.aggregators.llm_response_universal import AssistantThoug ## Related -- [Transcriptions](/server/utilities/turn-management/transcriptions) - Collect conversation transcripts using turn events -- [User Turn Strategies](/server/utilities/turn-management/user-turn-strategies) - Configure turn detection behavior -- [Turn Tracking Observer](/server/utilities/observers/turn-tracking-observer) - Track complete turn cycles with timing +- [Transcriptions](/api-reference/server/utilities/turn-management/transcriptions) - Collect conversation transcripts using turn events +- [User Turn Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) - Configure turn detection behavior +- [Turn Tracking Observer](/api-reference/server/utilities/observers/turn-tracking-observer) - Track complete turn cycles with timing diff --git a/server/utilities/turn-management/user-mute-strategies.mdx b/api-reference/server/utilities/turn-management/user-mute-strategies.mdx similarity index 98% rename from server/utilities/turn-management/user-mute-strategies.mdx rename to api-reference/server/utilities/turn-management/user-mute-strategies.mdx index b9088a9bc..3ab66ffd2 100644 --- a/server/utilities/turn-management/user-mute-strategies.mdx +++ b/api-reference/server/utilities/turn-management/user-mute-strategies.mdx @@ -224,5 +224,5 @@ async def on_user_mute_stopped(aggregator): ## Related -- [User Turn Strategies](/server/utilities/turn-management/user-turn-strategies) - Configure turn detection behavior +- [User Turn Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) - Configure turn detection behavior - [User Input Muting Guide](/pipecat/fundamentals/user-input-muting) - Guide for controlling user input diff --git a/server/utilities/turn-management/user-turn-strategies.mdx b/api-reference/server/utilities/turn-management/user-turn-strategies.mdx similarity index 98% rename from server/utilities/turn-management/user-turn-strategies.mdx rename to api-reference/server/utilities/turn-management/user-turn-strategies.mdx index 8391ea838..3df7088ad 100644 --- a/server/utilities/turn-management/user-turn-strategies.mdx +++ b/api-reference/server/utilities/turn-management/user-turn-strategies.mdx @@ -257,7 +257,7 @@ strategy = TurnAnalyzerUserTurnStopStrategy( See the [Smart Turn - Detection](/server/utilities/turn-detection/smart-turn-overview) documentation for + Detection](/api-reference/server/utilities/turn-detection/smart-turn-overview) documentation for more information on available turn analyzers. @@ -445,4 +445,4 @@ user_aggregator, assistant_aggregator = LLMContextAggregatorPair( ## Related - [User Input Muting](/pipecat/fundamentals/user-input-muting) - Control when user input is ignored -- [Smart Turn Detection](/server/utilities/turn-detection/smart-turn-overview) - AI-powered turn detection +- [Smart Turn Detection](/api-reference/server/utilities/turn-detection/smart-turn-overview) - AI-powered turn detection diff --git a/server/utilities/user-idle-processor.mdx b/api-reference/server/utilities/user-idle-processor.mdx similarity index 100% rename from server/utilities/user-idle-processor.mdx rename to api-reference/server/utilities/user-idle-processor.mdx diff --git a/client/ios/transports/small-webrtc.mdx b/client/ios/transports/small-webrtc.mdx index a95fc5631..7b2244dca 100644 --- a/client/ios/transports/small-webrtc.mdx +++ b/client/ios/transports/small-webrtc.mdx @@ -5,7 +5,7 @@ description: "A lightweight WebRTC transport for peer-to-peer connections with P `SmallWebRTCTransport` enables peer-to-peer WebRTC connections between clients and your Pipecat application. It implements bidirectional audio and video streaming using WebRTC for real-time communication. -This transport is intended for lightweight implementations. It expects your Pipecat server to include the corresponding [`SmallWebRTCTransport` server-side](/server/services/transport/small-webrtc) implementation. +This transport is intended for lightweight implementations. It expects your Pipecat server to include the corresponding [`SmallWebRTCTransport` server-side](/api-reference/server/services/transport/small-webrtc) implementation. ## Installation diff --git a/client/js/api-reference/callbacks.mdx b/client/js/api-reference/callbacks.mdx index fa2c17a31..1863d5637 100644 --- a/client/js/api-reference/callbacks.mdx +++ b/client/js/api-reference/callbacks.mdx @@ -288,9 +288,9 @@ Callback receives a `TranscriptData` object: Search capabilities are currently only supported by Google Gemini. To take advantage of this event, your pipeline must include a - [`GoogleLLMService`](/server/services/llm/google) and your pipeline task + [`GoogleLLMService`](/api-reference/server/services/llm/google) and your pipeline task should include the - [`GoogleRTVIObserver`](/server/frameworks/rtvi/google-rtvi-observer) in lieu + [`GoogleRTVIObserver`](/api-reference/server/rtvi/google-rtvi-observer) in lieu of the typical `RTVIObserver`. @@ -358,7 +358,7 @@ Callback receives a `TranscriptData` object: A function call has been initiated by the LLM. The metadata included depends - on the server's [`function_call_report_level`](/server/frameworks/rtvi/rtvi-observer#configuration) configuration. + on the server's [`function_call_report_level`](/api-reference/server/rtvi/rtvi-observer#configuration) configuration. diff --git a/client/js/api-reference/messages.mdx b/client/js/api-reference/messages.mdx index 80a965d3a..f1a52b650 100644 --- a/client/js/api-reference/messages.mdx +++ b/client/js/api-reference/messages.mdx @@ -259,7 +259,7 @@ class CustomFrameProcessor(FrameProcessor): ## Handling Custom Messages from the Server -You can handle custom messages sent from the server using the `onServerMessage` callback. This allows you to process messages that the server sends back to the client, such as notifications or updates. For full details on sending server messages from your bot, see the [RTVIProcessor custom messaging docs](/server/frameworks/rtvi/rtvi-processor#custom-messaging). +You can handle custom messages sent from the server using the `onServerMessage` callback. This allows you to process messages that the server sends back to the client, such as notifications or updates. For full details on sending server messages from your bot, see the [RTVIProcessor custom messaging docs](/api-reference/server/rtvi/rtvi-processor#custom-messaging). ```javascript client diff --git a/client/js/transports/daily.mdx b/client/js/transports/daily.mdx index 2b1238fea..f63c5b219 100644 --- a/client/js/transports/daily.mdx +++ b/client/js/transports/daily.mdx @@ -4,7 +4,7 @@ title: "Daily WebRTC Transport" The DailyTransport class provides a WebRTC transport layer using [Daily.co's](https://daily.co) infrastructure. It wraps a Daily-JS call client to handle audio/video device management, WebRTC connections, and real-time communication between clients and bots. For complete documentation on Daily's API, see the [Daily API Reference](https://docs.daily.co/reference/daily-js). -This transport is designed for production use cases, leveraging Daily's global infrastructure for low-latency, high-quality audio and video streaming. It expects your Pipecat server to include the corresponding [`DailyTransport` server-side](/server/services/transport/daily) implementation. +This transport is designed for production use cases, leveraging Daily's global infrastructure for low-latency, high-quality audio and video streaming. It expects your Pipecat server to include the corresponding [`DailyTransport` server-side](/api-reference/server/services/transport/daily) implementation. ## Usage diff --git a/client/js/transports/small-webrtc.mdx b/client/js/transports/small-webrtc.mdx index c130fb3e8..0a1aa6f3a 100644 --- a/client/js/transports/small-webrtc.mdx +++ b/client/js/transports/small-webrtc.mdx @@ -5,7 +5,7 @@ description: "A lightweight WebRTC transport for peer-to-peer connections with P `SmallWebRTCTransport` enables peer-to-peer WebRTC connections between clients and your Pipecat application. It implements bidirectional audio and video streaming using WebRTC for real-time communication. -This transport is intended for lightweight implementations, particularly for local development and testing. It expects your Pipecat server to include the corresponding [`SmallWebRTCTransport` server-side](/server/services/transport/small-webrtc) implementation. +This transport is intended for lightweight implementations, particularly for local development and testing. It expects your Pipecat server to include the corresponding [`SmallWebRTCTransport` server-side](/api-reference/server/services/transport/small-webrtc) implementation. ## Usage diff --git a/client/js/transports/websocket.mdx b/client/js/transports/websocket.mdx index 5d219142a..0ab87a45c 100644 --- a/client/js/transports/websocket.mdx +++ b/client/js/transports/websocket.mdx @@ -5,7 +5,7 @@ description: "A lightweight transport for WebSocket based connections with Pipec `WebSocketTransport` enables a purely WebSocket based connection between clients and your Pipecat application. It implements bidirectional audio and video streaming using a WebSocket for real-time communication. -This transport is intended for lightweight implementations, particularly for local development and testing. It expects your Pipecat server to include the corresponding [`WebSocketTransport` server-side](/server/services/transport/websocket-server) implementation. +This transport is intended for lightweight implementations, particularly for local development and testing. It expects your Pipecat server to include the corresponding [`WebSocketTransport` server-side](/api-reference/server/services/transport/websocket-server) implementation. The `WebSocketTransport` is best suited for server-server applications and prototyping client/server apps. diff --git a/client/react-native/transports/daily.mdx b/client/react-native/transports/daily.mdx index a6988a3a6..c7073dc50 100644 --- a/client/react-native/transports/daily.mdx +++ b/client/react-native/transports/daily.mdx @@ -4,7 +4,7 @@ title: "Daily WebRTC Transport" The DailyTransport class provides a WebRTC transport layer using [Daily.co's](https://daily.co) infrastructure. It wraps a React-Native-Daily-JS call client to handle audio/video device management, WebRTC connections, and real-time communication between clients and bots. For complete documentation on Daily's API, see the [Daily RN API Reference](https://docs.daily.co/reference/rn-daily-js). -This transport is designed for production use cases, leveraging Daily's global infrastructure for low-latency, high-quality audio and video streaming. It expects your Pipecat server to include the corresponding [`DailyTransport` server-side](/server/services/transport/daily) implementation. +This transport is designed for production use cases, leveraging Daily's global infrastructure for low-latency, high-quality audio and video streaming. It expects your Pipecat server to include the corresponding [`DailyTransport` server-side](/api-reference/server/services/transport/daily) implementation. ## Usage diff --git a/client/react-native/transports/small-webrtc.mdx b/client/react-native/transports/small-webrtc.mdx index 92a71ce46..01ab399ce 100644 --- a/client/react-native/transports/small-webrtc.mdx +++ b/client/react-native/transports/small-webrtc.mdx @@ -5,7 +5,7 @@ description: "A lightweight WebRTC transport for peer-to-peer connections with P `SmallWebRTCTransport` enables peer-to-peer WebRTC connections between clients and your Pipecat application. It implements bidirectional audio and video streaming using WebRTC for real-time communication. -This transport is intended for lightweight implementations, particularly for local development and testing. It expects your Pipecat server to include the corresponding [`SmallWebRTCTransport` server-side](/server/services/transport/small-webrtc) implementation. +This transport is intended for lightweight implementations, particularly for local development and testing. It expects your Pipecat server to include the corresponding [`SmallWebRTCTransport` server-side](/api-reference/server/services/transport/small-webrtc) implementation. ## Usage diff --git a/docs.json b/docs.json index 3e9116104..9e43f8360 100644 --- a/docs.json +++ b/docs.json @@ -325,160 +325,160 @@ { "group": "Pipecat Server", "pages": [ - "server/introduction", + "api-reference/server/introduction", { "group": "Services", "pages": [ - "server/services/supported-services", - "server/services/community-integrations", + "api-reference/server/services/supported-services", + "api-reference/server/services/community-integrations", { "group": "Transport", "pages": [ - "server/services/transport/daily", - "server/services/transport/fastapi-websocket", - "server/services/transport/heygen", - "server/services/transport/lemonslice", - "server/services/transport/livekit", - "server/services/transport/small-webrtc", - "server/services/transport/tavus", - "server/services/transport/websocket-server", - "server/services/transport/whatsapp", - "server/services/transport/transport-params" + "api-reference/server/services/transport/daily", + "api-reference/server/services/transport/fastapi-websocket", + "api-reference/server/services/transport/heygen", + "api-reference/server/services/transport/lemonslice", + "api-reference/server/services/transport/livekit", + "api-reference/server/services/transport/small-webrtc", + "api-reference/server/services/transport/tavus", + "api-reference/server/services/transport/websocket-server", + "api-reference/server/services/transport/whatsapp", + "api-reference/server/services/transport/transport-params" ] }, { "group": "Serializers", "pages": [ - "server/services/serializers/introduction", - "server/services/serializers/exotel", - "server/services/serializers/genesys", - "server/services/serializers/plivo", - "server/services/serializers/twilio", - "server/services/serializers/telnyx", - "server/services/serializers/vonage" + "api-reference/server/services/serializers/introduction", + "api-reference/server/services/serializers/exotel", + "api-reference/server/services/serializers/genesys", + "api-reference/server/services/serializers/plivo", + "api-reference/server/services/serializers/twilio", + "api-reference/server/services/serializers/telnyx", + "api-reference/server/services/serializers/vonage" ] }, { "group": "Speech-to-Text", "pages": [ - "server/services/stt/assemblyai", - "server/services/stt/aws", - "server/services/stt/azure", - "server/services/stt/cartesia", - "server/services/stt/deepgram", - "server/services/stt/elevenlabs", - "server/services/stt/fal", - "server/services/stt/gladia", - "server/services/stt/google", - "server/services/stt/groq", - "server/services/stt/nvidia", - "server/services/stt/openai", - "server/services/stt/sarvam", - "server/services/stt/soniox", - "server/services/stt/speechmatics", - "server/services/stt/whisper", - "server/services/stt/gradium" + "api-reference/server/services/stt/assemblyai", + "api-reference/server/services/stt/aws", + "api-reference/server/services/stt/azure", + "api-reference/server/services/stt/cartesia", + "api-reference/server/services/stt/deepgram", + "api-reference/server/services/stt/elevenlabs", + "api-reference/server/services/stt/fal", + "api-reference/server/services/stt/gladia", + "api-reference/server/services/stt/google", + "api-reference/server/services/stt/groq", + "api-reference/server/services/stt/nvidia", + "api-reference/server/services/stt/openai", + "api-reference/server/services/stt/sarvam", + "api-reference/server/services/stt/soniox", + "api-reference/server/services/stt/speechmatics", + "api-reference/server/services/stt/whisper", + "api-reference/server/services/stt/gradium" ] }, { "group": "LLM", "pages": [ - "server/services/llm/anthropic", - "server/services/llm/aws", - "server/services/llm/azure", - "server/services/llm/cerebras", - "server/services/llm/deepseek", - "server/services/llm/fireworks", - "server/services/llm/google", - "server/services/llm/google-vertex", - "server/services/llm/grok", - "server/services/llm/groq", - "server/services/llm/mistral", - "server/services/llm/nvidia", - "server/services/llm/novita", - "server/services/llm/ollama", - "server/services/llm/openai", - "server/services/llm/openai-responses", - "server/services/llm/openpipe", - "server/services/llm/openrouter", - "server/services/llm/perplexity", - "server/services/llm/qwen", - "server/services/llm/sambanova", - "server/services/llm/sarvam", - "server/services/llm/together" + "api-reference/server/services/llm/anthropic", + "api-reference/server/services/llm/aws", + "api-reference/server/services/llm/azure", + "api-reference/server/services/llm/cerebras", + "api-reference/server/services/llm/deepseek", + "api-reference/server/services/llm/fireworks", + "api-reference/server/services/llm/google", + "api-reference/server/services/llm/google-vertex", + "api-reference/server/services/llm/grok", + "api-reference/server/services/llm/groq", + "api-reference/server/services/llm/mistral", + "api-reference/server/services/llm/nvidia", + "api-reference/server/services/llm/novita", + "api-reference/server/services/llm/ollama", + "api-reference/server/services/llm/openai", + "api-reference/server/services/llm/openai-responses", + "api-reference/server/services/llm/openpipe", + "api-reference/server/services/llm/openrouter", + "api-reference/server/services/llm/perplexity", + "api-reference/server/services/llm/qwen", + "api-reference/server/services/llm/sambanova", + "api-reference/server/services/llm/sarvam", + "api-reference/server/services/llm/together" ] }, { "group": "Text-to-Speech", "pages": [ - "server/services/tts/asyncai", - "server/services/tts/aws", - "server/services/tts/azure", - "server/services/tts/camb", - "server/services/tts/cartesia", - "server/services/tts/deepgram", - "server/services/tts/elevenlabs", - "server/services/tts/fish", - "server/services/tts/google", - "server/services/tts/groq", - "server/services/tts/hume", - "server/services/tts/inworld", - "server/services/tts/kokoro", - "server/services/tts/lmnt", - "server/services/tts/minimax", - "server/services/tts/neuphonic", - "server/services/tts/nvidia", - "server/services/tts/openai", - "server/services/tts/piper", - "server/services/tts/resembleai", - "server/services/tts/rime", - "server/services/tts/sarvam", - "server/services/tts/smallest", - "server/services/tts/speechmatics", - "server/services/tts/xai", - "server/services/tts/xtts", - "server/services/tts/gradium" + "api-reference/server/services/tts/asyncai", + "api-reference/server/services/tts/aws", + "api-reference/server/services/tts/azure", + "api-reference/server/services/tts/camb", + "api-reference/server/services/tts/cartesia", + "api-reference/server/services/tts/deepgram", + "api-reference/server/services/tts/elevenlabs", + "api-reference/server/services/tts/fish", + "api-reference/server/services/tts/google", + "api-reference/server/services/tts/groq", + "api-reference/server/services/tts/hume", + "api-reference/server/services/tts/inworld", + "api-reference/server/services/tts/kokoro", + "api-reference/server/services/tts/lmnt", + "api-reference/server/services/tts/minimax", + "api-reference/server/services/tts/neuphonic", + "api-reference/server/services/tts/nvidia", + "api-reference/server/services/tts/openai", + "api-reference/server/services/tts/piper", + "api-reference/server/services/tts/resembleai", + "api-reference/server/services/tts/rime", + "api-reference/server/services/tts/sarvam", + "api-reference/server/services/tts/smallest", + "api-reference/server/services/tts/speechmatics", + "api-reference/server/services/tts/xai", + "api-reference/server/services/tts/xtts", + "api-reference/server/services/tts/gradium" ] }, { "group": "Speech-to-Speech", "pages": [ - "server/services/s2s/aws", - "server/services/s2s/gemini-live", - "server/services/s2s/gemini-live-vertex", - "server/services/s2s/grok", - "server/services/s2s/openai", - "server/services/s2s/ultravox" + "api-reference/server/services/s2s/aws", + "api-reference/server/services/s2s/gemini-live", + "api-reference/server/services/s2s/gemini-live-vertex", + "api-reference/server/services/s2s/grok", + "api-reference/server/services/s2s/openai", + "api-reference/server/services/s2s/ultravox" ] }, { "group": "Image Generation", "pages": [ - "server/services/image-generation/azure", - "server/services/image-generation/fal", - "server/services/image-generation/google", - "server/services/image-generation/openai" + "api-reference/server/services/image-generation/azure", + "api-reference/server/services/image-generation/fal", + "api-reference/server/services/image-generation/google", + "api-reference/server/services/image-generation/openai" ] }, { "group": "Video", "pages": [ - "server/services/video/heygen", - "server/services/video/simli", - "server/services/video/tavus" + "api-reference/server/services/video/heygen", + "api-reference/server/services/video/simli", + "api-reference/server/services/video/tavus" ] }, { "group": "Memory", - "pages": ["server/services/memory/mem0"] + "pages": ["api-reference/server/services/memory/mem0"] }, { "group": "Vision", - "pages": ["server/services/vision/moondream"] + "pages": ["api-reference/server/services/vision/moondream"] }, { "group": "Analytics & Monitoring", - "pages": ["server/services/analytics/sentry"] + "pages": ["api-reference/server/services/analytics/sentry"] } ] }, @@ -488,119 +488,125 @@ { "group": "Advanced Frame Processors", "pages": [ - "server/utilities/frame/llm-text-processor", - "server/utilities/frame/producer-consumer", - "server/utilities/user-idle-processor" + "api-reference/server/utilities/frame/llm-text-processor", + "api-reference/server/utilities/frame/producer-consumer", + "api-reference/server/utilities/user-idle-processor" ] }, { "group": "Audio Processing", "pages": [ - "server/utilities/audio/aic-filter", - "server/utilities/audio/audio-buffer-processor", - "server/utilities/audio/koala-filter", - "server/utilities/audio/krisp-viva-filter", - "server/utilities/audio/krisp-viva-vad-analyzer", - "server/utilities/audio/rnnoise-filter", - "server/utilities/audio/silero-vad-analyzer", - "server/utilities/audio/soundfile-mixer" + "api-reference/server/utilities/audio/aic-filter", + "api-reference/server/utilities/audio/audio-buffer-processor", + "api-reference/server/utilities/audio/koala-filter", + "api-reference/server/utilities/audio/krisp-viva-filter", + "api-reference/server/utilities/audio/krisp-viva-vad-analyzer", + "api-reference/server/utilities/audio/rnnoise-filter", + "api-reference/server/utilities/audio/silero-vad-analyzer", + "api-reference/server/utilities/audio/soundfile-mixer" ] }, { "group": "Context", - "pages": ["server/utilities/context-summarization"] + "pages": [ + "api-reference/server/utilities/context-summarization" + ] }, { "group": "Extensions", "pages": [ - "server/utilities/extensions/ivr", - "server/utilities/extensions/voicemail" + "api-reference/server/utilities/extensions/ivr", + "api-reference/server/utilities/extensions/voicemail" ] }, { "group": "Frame Filters", "pages": [ - "server/utilities/filters/frame-filter", - "server/utilities/filters/function-filter", - "server/utilities/filters/identify-filter", - "server/utilities/filters/null-filter", - "server/utilities/filters/stt-mute", - "server/utilities/filters/wake-check-filter", - "server/utilities/filters/wake-notifier-filter" + "api-reference/server/utilities/filters/frame-filter", + "api-reference/server/utilities/filters/function-filter", + "api-reference/server/utilities/filters/identify-filter", + "api-reference/server/utilities/filters/null-filter", + "api-reference/server/utilities/filters/stt-mute", + "api-reference/server/utilities/filters/wake-check-filter", + "api-reference/server/utilities/filters/wake-notifier-filter" ] }, { "group": "Metrics and Telemetry", - "pages": ["server/utilities/opentelemetry"] + "pages": ["api-reference/server/utilities/opentelemetry"] }, { "group": "MCP", - "pages": ["server/utilities/mcp/mcp"] + "pages": ["api-reference/server/utilities/mcp/mcp"] }, { "group": "Observers", "pages": [ - "server/utilities/observers/observer-pattern", - "server/utilities/observers/debug-observer", - "server/utilities/observers/llm-observer", - "server/utilities/observers/transcription-observer", - "server/utilities/observers/startup-timing-observer", - "server/utilities/observers/turn-tracking-observer", - "server/utilities/observers/user-bot-latency-observer" + "api-reference/server/utilities/observers/observer-pattern", + "api-reference/server/utilities/observers/debug-observer", + "api-reference/server/utilities/observers/llm-observer", + "api-reference/server/utilities/observers/transcription-observer", + "api-reference/server/utilities/observers/startup-timing-observer", + "api-reference/server/utilities/observers/turn-tracking-observer", + "api-reference/server/utilities/observers/user-bot-latency-observer" ] }, { "group": "Runner", "pages": [ - "server/utilities/runner/guide", - "server/utilities/runner/transport-utils" + "api-reference/server/utilities/runner/guide", + "api-reference/server/utilities/runner/transport-utils" ] }, { "group": "Service Utilities", - "pages": ["server/utilities/daily/rest-helper"] + "pages": [ + "api-reference/server/utilities/daily/rest-helper" + ] }, { "group": "Service Switchers", "pages": [ - "server/utilities/service-switchers/service-switcher", - "server/utilities/service-switchers/llm-switcher" + "api-reference/server/utilities/service-switchers/service-switcher", + "api-reference/server/utilities/service-switchers/llm-switcher" ] }, { "group": "Smart Turn Detection", "pages": [ - "server/utilities/turn-detection/smart-turn-overview", - "server/utilities/turn-detection/krisp-viva-turn", - "server/utilities/turn-detection/fal-smart-turn" + "api-reference/server/utilities/turn-detection/smart-turn-overview", + "api-reference/server/utilities/turn-detection/krisp-viva-turn", + "api-reference/server/utilities/turn-detection/fal-smart-turn" ] }, { "group": "Telephony", - "pages": ["server/utilities/dtmf-aggregator"] + "pages": ["api-reference/server/utilities/dtmf-aggregator"] }, { "group": "Text Aggregators and Filters", "pages": [ - "server/utilities/text/overview", - "server/utilities/text/markdown-text-filter", - "server/utilities/text/pattern-pair-aggregator" + "api-reference/server/utilities/text/overview", + "api-reference/server/utilities/text/markdown-text-filter", + "api-reference/server/utilities/text/pattern-pair-aggregator" ] }, { "group": "User and Assistant Transcriptions", - "pages": ["server/utilities/transcript-processor"] + "pages": [ + "api-reference/server/utilities/transcript-processor" + ] }, { "group": "User and Assistant Turn Management", "pages": [ - "server/utilities/turn-management/user-turn-strategies", - "server/utilities/turn-management/user-mute-strategies", - "server/utilities/turn-management/filter-incomplete-turns", - "server/utilities/turn-management/turn-events", - "server/utilities/turn-management/transcriptions", - "server/utilities/turn-management/external-turn-management", - "server/utilities/turn-management/interruption-strategies" + "api-reference/server/utilities/turn-management/user-turn-strategies", + "api-reference/server/utilities/turn-management/user-mute-strategies", + "api-reference/server/utilities/turn-management/filter-incomplete-turns", + "api-reference/server/utilities/turn-management/turn-events", + "api-reference/server/utilities/turn-management/transcriptions", + "api-reference/server/utilities/turn-management/external-turn-management", + "api-reference/server/utilities/turn-management/interruption-strategies" ] } ] @@ -608,38 +614,38 @@ { "group": "Events", "pages": [ - "server/events/overview", - "server/events/frame-processor-events", - "server/events/service-events" + "api-reference/server/events/overview", + "api-reference/server/events/frame-processor-events", + "api-reference/server/events/service-events" ] }, { - "group": "RTVI Framework", + "group": "RTVI", "pages": [ - "server/frameworks/rtvi/introduction", - "server/frameworks/rtvi/rtvi-processor", - "server/frameworks/rtvi/rtvi-observer", - "server/frameworks/rtvi/google-rtvi-observer" + "api-reference/server/rtvi/introduction", + "api-reference/server/rtvi/rtvi-processor", + "api-reference/server/rtvi/rtvi-observer", + "api-reference/server/rtvi/google-rtvi-observer" ] }, { "group": "Frames", "pages": [ - "server/frames/overview", - "server/frames/data-frames", - "server/frames/control-frames", - "server/frames/system-frames", - "server/frames/llm-frames" + "api-reference/server/frames/overview", + "api-reference/server/frames/data-frames", + "api-reference/server/frames/control-frames", + "api-reference/server/frames/system-frames", + "api-reference/server/frames/llm-frames" ] }, { "group": "Pipeline", "pages": [ - "server/pipeline/pipeline-params", - "server/pipeline/pipeline-task", - "server/pipeline/pipeline-idle-detection", - "server/pipeline/heartbeats", - "server/pipeline/parallel-pipeline" + "api-reference/server/pipeline/pipeline-params", + "api-reference/server/pipeline/pipeline-task", + "api-reference/server/pipeline/pipeline-idle-detection", + "api-reference/server/pipeline/heartbeats", + "api-reference/server/pipeline/parallel-pipeline" ] } ] @@ -647,10 +653,10 @@ { "group": "Pipecat Flows", "pages": [ - "pipecat-flows/reference/overview", - "pipecat-flows/reference/flow-manager", - "pipecat-flows/reference/types", - "pipecat-flows/reference/exceptions" + "api-reference/pipecat-flows/overview", + "api-reference/pipecat-flows/flow-manager", + "api-reference/pipecat-flows/types", + "api-reference/pipecat-flows/exceptions" ] }, { @@ -662,50 +668,50 @@ { "group": "Agents", "pages": [ - "pipecat-cloud/rest-reference/endpoint/agent-create", - "pipecat-cloud/rest-reference/endpoint/agent-update", - "pipecat-cloud/rest-reference/endpoint/start", - "pipecat-cloud/rest-reference/endpoint/stop", - "pipecat-cloud/rest-reference/endpoint/session-proxy", - "pipecat-cloud/rest-reference/endpoint/agent-get-logs", - "pipecat-cloud/rest-reference/endpoint/agent-get-sessions", - "pipecat-cloud/rest-reference/endpoint/agent-get-session", - "pipecat-cloud/rest-reference/endpoint/agent-list-all", - "pipecat-cloud/rest-reference/endpoint/agent-list-one", - "pipecat-cloud/rest-reference/endpoint/agent-delete" + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-create", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-update", + "api-reference/pipecat-cloud/rest-reference/endpoint/start", + "api-reference/pipecat-cloud/rest-reference/endpoint/stop", + "api-reference/pipecat-cloud/rest-reference/endpoint/session-proxy", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-logs", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-sessions", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-session", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-all", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-one", + "api-reference/pipecat-cloud/rest-reference/endpoint/agent-delete" ] }, { "group": "Secrets", "pages": [ - "pipecat-cloud/rest-reference/endpoint/secret-create-update", - "pipecat-cloud/rest-reference/endpoint/secret-list-all", - "pipecat-cloud/rest-reference/endpoint/secret-list-one", - "pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set", - "pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret" + "api-reference/pipecat-cloud/rest-reference/endpoint/secret-create-update", + "api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-all", + "api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-one", + "api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set", + "api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret" ] }, { "group": "Builds", "pages": [ - "pipecat-cloud/rest-reference/endpoint/build-upload-url", - "pipecat-cloud/rest-reference/endpoint/build-create", - "pipecat-cloud/rest-reference/endpoint/build-list", - "pipecat-cloud/rest-reference/endpoint/build-get", - "pipecat-cloud/rest-reference/endpoint/build-get-logs" + "api-reference/pipecat-cloud/rest-reference/endpoint/build-upload-url", + "api-reference/pipecat-cloud/rest-reference/endpoint/build-create", + "api-reference/pipecat-cloud/rest-reference/endpoint/build-list", + "api-reference/pipecat-cloud/rest-reference/endpoint/build-get", + "api-reference/pipecat-cloud/rest-reference/endpoint/build-get-logs" ] }, { "group": "Regions", "pages": [ - "pipecat-cloud/rest-reference/endpoint/regions-list" + "api-reference/pipecat-cloud/rest-reference/endpoint/regions-list" ] }, { "group": "Organization", "pages": [ - "pipecat-cloud/rest-reference/endpoint/properties-get", - "pipecat-cloud/rest-reference/endpoint/properties-update" + "api-reference/pipecat-cloud/rest-reference/endpoint/properties-get", + "api-reference/pipecat-cloud/rest-reference/endpoint/properties-update" ] } ] @@ -713,11 +719,11 @@ { "group": "SDK Reference", "pages": [ - "pipecat-cloud/sdk-reference/overview", - "pipecat-cloud/sdk-reference/sessions", - "pipecat-cloud/sdk-reference/session-arguments", - "pipecat-cloud/sdk-reference/exceptions", - "pipecat-cloud/sdk-reference/examples" + "api-reference/pipecat-cloud/sdk-reference/overview", + "api-reference/pipecat-cloud/sdk-reference/sessions", + "api-reference/pipecat-cloud/sdk-reference/session-arguments", + "api-reference/pipecat-cloud/sdk-reference/exceptions", + "api-reference/pipecat-cloud/sdk-reference/examples" ] } ] @@ -725,23 +731,23 @@ { "group": "CLI", "pages": [ - "cli/overview", + "api-reference/cli/overview", { "group": "Commands", "pages": [ - "cli/init", - "cli/tail", + "api-reference/cli/init", + "api-reference/cli/tail", { "group": "cloud", "pages": [ - "cli/cloud/agent", - "cli/cloud/auth", - "cli/cloud/build", - "cli/cloud/docker", - "cli/cloud/deploy", - "cli/cloud/organizations", - "cli/cloud/secrets", - "cli/cloud/regions" + "api-reference/cli/cloud/agent", + "api-reference/cli/cloud/auth", + "api-reference/cli/cloud/build", + "api-reference/cli/cloud/docker", + "api-reference/cli/cloud/deploy", + "api-reference/cli/cloud/organizations", + "api-reference/cli/cloud/secrets", + "api-reference/cli/cloud/regions" ] } ] @@ -819,47 +825,47 @@ "redirects": [ { "source": "/server/services/s2s/gemini", - "destination": "/server/services/s2s/gemini-live" + "destination": "/api-reference/server/services/s2s/gemini-live" }, { "source": "/pipecat-cloud/cli-reference/overview", - "destination": "/cli/overview" + "destination": "/api-reference/cli/overview" }, { "source": "/pipecat-cloud/cli-reference/init", - "destination": "/cli/init" + "destination": "/api-reference/cli/init" }, { "source": "/pipecat-cloud/cli-reference/auth", - "destination": "/cli/cloud/auth" + "destination": "/api-reference/cli/cloud/auth" }, { "source": "/pipecat-cloud/cli-reference/deploy", - "destination": "/cli/cloud/deploy" + "destination": "/api-reference/cli/cloud/deploy" }, { "source": "/pipecat-cloud/cli-reference/docker", - "destination": "/cli/cloud/docker" + "destination": "/api-reference/cli/cloud/docker" }, { "source": "/pipecat-cloud/cli-reference/agent", - "destination": "/cli/cloud/agent" + "destination": "/api-reference/cli/cloud/agent" }, { "source": "/pipecat-cloud/cli-reference/secrets", - "destination": "/cli/cloud/secrets" + "destination": "/api-reference/cli/cloud/secrets" }, { "source": "/pipecat-cloud/cli-reference/organizations", - "destination": "/cli/cloud/organizations" + "destination": "/api-reference/cli/cloud/organizations" }, { "source": "/cli/installation", - "destination": "/cli/overview" + "destination": "/api-reference/cli/overview" }, { "source": "/server/services/llm/gemini", - "destination": "/server/services/llm/google" + "destination": "/api-reference/server/services/llm/google" }, { "source": "/deployment/platforms/pipecat-cloud", @@ -999,19 +1005,19 @@ }, { "source": "/server/frameworks/flows/pipecat-flows", - "destination": "/pipecat-flows/reference/overview" + "destination": "/api-reference/pipecat-flows/overview" }, { "source": "/server/frameworks/flows/flow-manager", - "destination": "/pipecat-flows/reference/flow-manager" + "destination": "/api-reference/pipecat-flows/flow-manager" }, { "source": "/server/frameworks/flows/types", - "destination": "/pipecat-flows/reference/types" + "destination": "/api-reference/pipecat-flows/types" }, { "source": "/server/frameworks/flows/exceptions", - "destination": "/pipecat-flows/reference/exceptions" + "destination": "/api-reference/pipecat-flows/exceptions" }, { "source": "/guides/features/krisp-viva", @@ -1231,23 +1237,895 @@ }, { "source": "/deployment/pipecat-cloud/sdk-reference/overview", - "destination": "/pipecat-cloud/sdk-reference/overview" + "destination": "/api-reference/pipecat-cloud/sdk-reference/overview" }, { "source": "/deployment/pipecat-cloud/sdk-reference/sessions", - "destination": "/pipecat-cloud/sdk-reference/sessions" + "destination": "/api-reference/pipecat-cloud/sdk-reference/sessions" }, { "source": "/deployment/pipecat-cloud/sdk-reference/session-arguments", - "destination": "/pipecat-cloud/sdk-reference/session-arguments" + "destination": "/api-reference/pipecat-cloud/sdk-reference/session-arguments" }, { "source": "/deployment/pipecat-cloud/sdk-reference/exceptions", - "destination": "/pipecat-cloud/sdk-reference/exceptions" + "destination": "/api-reference/pipecat-cloud/sdk-reference/exceptions" }, { "source": "/deployment/pipecat-cloud/sdk-reference/examples", - "destination": "/pipecat-cloud/sdk-reference/examples" + "destination": "/api-reference/pipecat-cloud/sdk-reference/examples" + }, + { + "source": "/server/introduction", + "destination": "/api-reference/server/introduction" + }, + { + "source": "/server/services/supported-services", + "destination": "/api-reference/server/services/supported-services" + }, + { + "source": "/server/services/community-integrations", + "destination": "/api-reference/server/services/community-integrations" + }, + { + "source": "/server/services/transport/daily", + "destination": "/api-reference/server/services/transport/daily" + }, + { + "source": "/server/services/transport/fastapi-websocket", + "destination": "/api-reference/server/services/transport/fastapi-websocket" + }, + { + "source": "/server/services/transport/heygen", + "destination": "/api-reference/server/services/transport/heygen" + }, + { + "source": "/server/services/transport/lemonslice", + "destination": "/api-reference/server/services/transport/lemonslice" + }, + { + "source": "/server/services/transport/livekit", + "destination": "/api-reference/server/services/transport/livekit" + }, + { + "source": "/server/services/transport/small-webrtc", + "destination": "/api-reference/server/services/transport/small-webrtc" + }, + { + "source": "/server/services/transport/tavus", + "destination": "/api-reference/server/services/transport/tavus" + }, + { + "source": "/server/services/transport/websocket-server", + "destination": "/api-reference/server/services/transport/websocket-server" + }, + { + "source": "/server/services/transport/whatsapp", + "destination": "/api-reference/server/services/transport/whatsapp" + }, + { + "source": "/server/services/transport/transport-params", + "destination": "/api-reference/server/services/transport/transport-params" + }, + { + "source": "/server/services/serializers/introduction", + "destination": "/api-reference/server/services/serializers/introduction" + }, + { + "source": "/server/services/serializers/exotel", + "destination": "/api-reference/server/services/serializers/exotel" + }, + { + "source": "/server/services/serializers/genesys", + "destination": "/api-reference/server/services/serializers/genesys" + }, + { + "source": "/server/services/serializers/plivo", + "destination": "/api-reference/server/services/serializers/plivo" + }, + { + "source": "/server/services/serializers/twilio", + "destination": "/api-reference/server/services/serializers/twilio" + }, + { + "source": "/server/services/serializers/telnyx", + "destination": "/api-reference/server/services/serializers/telnyx" + }, + { + "source": "/server/services/serializers/vonage", + "destination": "/api-reference/server/services/serializers/vonage" + }, + { + "source": "/server/services/stt/assemblyai", + "destination": "/api-reference/server/services/stt/assemblyai" + }, + { + "source": "/server/services/stt/aws", + "destination": "/api-reference/server/services/stt/aws" + }, + { + "source": "/server/services/stt/azure", + "destination": "/api-reference/server/services/stt/azure" + }, + { + "source": "/server/services/stt/cartesia", + "destination": "/api-reference/server/services/stt/cartesia" + }, + { + "source": "/server/services/stt/deepgram", + "destination": "/api-reference/server/services/stt/deepgram" + }, + { + "source": "/server/services/stt/elevenlabs", + "destination": "/api-reference/server/services/stt/elevenlabs" + }, + { + "source": "/server/services/stt/fal", + "destination": "/api-reference/server/services/stt/fal" + }, + { + "source": "/server/services/stt/gladia", + "destination": "/api-reference/server/services/stt/gladia" + }, + { + "source": "/server/services/stt/google", + "destination": "/api-reference/server/services/stt/google" + }, + { + "source": "/server/services/stt/groq", + "destination": "/api-reference/server/services/stt/groq" + }, + { + "source": "/server/services/stt/nvidia", + "destination": "/api-reference/server/services/stt/nvidia" + }, + { + "source": "/server/services/stt/openai", + "destination": "/api-reference/server/services/stt/openai" + }, + { + "source": "/server/services/stt/sarvam", + "destination": "/api-reference/server/services/stt/sarvam" + }, + { + "source": "/server/services/stt/soniox", + "destination": "/api-reference/server/services/stt/soniox" + }, + { + "source": "/server/services/stt/speechmatics", + "destination": "/api-reference/server/services/stt/speechmatics" + }, + { + "source": "/server/services/stt/whisper", + "destination": "/api-reference/server/services/stt/whisper" + }, + { + "source": "/server/services/stt/gradium", + "destination": "/api-reference/server/services/stt/gradium" + }, + { + "source": "/server/services/llm/anthropic", + "destination": "/api-reference/server/services/llm/anthropic" + }, + { + "source": "/server/services/llm/aws", + "destination": "/api-reference/server/services/llm/aws" + }, + { + "source": "/server/services/llm/azure", + "destination": "/api-reference/server/services/llm/azure" + }, + { + "source": "/server/services/llm/cerebras", + "destination": "/api-reference/server/services/llm/cerebras" + }, + { + "source": "/server/services/llm/deepseek", + "destination": "/api-reference/server/services/llm/deepseek" + }, + { + "source": "/server/services/llm/fireworks", + "destination": "/api-reference/server/services/llm/fireworks" + }, + { + "source": "/server/services/llm/google", + "destination": "/api-reference/server/services/llm/google" + }, + { + "source": "/server/services/llm/google-vertex", + "destination": "/api-reference/server/services/llm/google-vertex" + }, + { + "source": "/server/services/llm/grok", + "destination": "/api-reference/server/services/llm/grok" + }, + { + "source": "/server/services/llm/groq", + "destination": "/api-reference/server/services/llm/groq" + }, + { + "source": "/server/services/llm/mistral", + "destination": "/api-reference/server/services/llm/mistral" + }, + { + "source": "/server/services/llm/nvidia", + "destination": "/api-reference/server/services/llm/nvidia" + }, + { + "source": "/server/services/llm/novita", + "destination": "/api-reference/server/services/llm/novita" + }, + { + "source": "/server/services/llm/ollama", + "destination": "/api-reference/server/services/llm/ollama" + }, + { + "source": "/server/services/llm/openai", + "destination": "/api-reference/server/services/llm/openai" + }, + { + "source": "/server/services/llm/openai-responses", + "destination": "/api-reference/server/services/llm/openai-responses" + }, + { + "source": "/server/services/llm/openpipe", + "destination": "/api-reference/server/services/llm/openpipe" + }, + { + "source": "/server/services/llm/openrouter", + "destination": "/api-reference/server/services/llm/openrouter" + }, + { + "source": "/server/services/llm/perplexity", + "destination": "/api-reference/server/services/llm/perplexity" + }, + { + "source": "/server/services/llm/qwen", + "destination": "/api-reference/server/services/llm/qwen" + }, + { + "source": "/server/services/llm/sambanova", + "destination": "/api-reference/server/services/llm/sambanova" + }, + { + "source": "/server/services/llm/sarvam", + "destination": "/api-reference/server/services/llm/sarvam" + }, + { + "source": "/server/services/llm/together", + "destination": "/api-reference/server/services/llm/together" + }, + { + "source": "/server/services/tts/asyncai", + "destination": "/api-reference/server/services/tts/asyncai" + }, + { + "source": "/server/services/tts/aws", + "destination": "/api-reference/server/services/tts/aws" + }, + { + "source": "/server/services/tts/azure", + "destination": "/api-reference/server/services/tts/azure" + }, + { + "source": "/server/services/tts/camb", + "destination": "/api-reference/server/services/tts/camb" + }, + { + "source": "/server/services/tts/cartesia", + "destination": "/api-reference/server/services/tts/cartesia" + }, + { + "source": "/server/services/tts/deepgram", + "destination": "/api-reference/server/services/tts/deepgram" + }, + { + "source": "/server/services/tts/elevenlabs", + "destination": "/api-reference/server/services/tts/elevenlabs" + }, + { + "source": "/server/services/tts/fish", + "destination": "/api-reference/server/services/tts/fish" + }, + { + "source": "/server/services/tts/google", + "destination": "/api-reference/server/services/tts/google" + }, + { + "source": "/server/services/tts/groq", + "destination": "/api-reference/server/services/tts/groq" + }, + { + "source": "/server/services/tts/hume", + "destination": "/api-reference/server/services/tts/hume" + }, + { + "source": "/server/services/tts/inworld", + "destination": "/api-reference/server/services/tts/inworld" + }, + { + "source": "/server/services/tts/kokoro", + "destination": "/api-reference/server/services/tts/kokoro" + }, + { + "source": "/server/services/tts/lmnt", + "destination": "/api-reference/server/services/tts/lmnt" + }, + { + "source": "/server/services/tts/minimax", + "destination": "/api-reference/server/services/tts/minimax" + }, + { + "source": "/server/services/tts/neuphonic", + "destination": "/api-reference/server/services/tts/neuphonic" + }, + { + "source": "/server/services/tts/nvidia", + "destination": "/api-reference/server/services/tts/nvidia" + }, + { + "source": "/server/services/tts/openai", + "destination": "/api-reference/server/services/tts/openai" + }, + { + "source": "/server/services/tts/piper", + "destination": "/api-reference/server/services/tts/piper" + }, + { + "source": "/server/services/tts/resembleai", + "destination": "/api-reference/server/services/tts/resembleai" + }, + { + "source": "/server/services/tts/rime", + "destination": "/api-reference/server/services/tts/rime" + }, + { + "source": "/server/services/tts/sarvam", + "destination": "/api-reference/server/services/tts/sarvam" + }, + { + "source": "/server/services/tts/smallest", + "destination": "/api-reference/server/services/tts/smallest" + }, + { + "source": "/server/services/tts/speechmatics", + "destination": "/api-reference/server/services/tts/speechmatics" + }, + { + "source": "/server/services/tts/xai", + "destination": "/api-reference/server/services/tts/xai" + }, + { + "source": "/server/services/tts/xtts", + "destination": "/api-reference/server/services/tts/xtts" + }, + { + "source": "/server/services/tts/gradium", + "destination": "/api-reference/server/services/tts/gradium" + }, + { + "source": "/server/services/s2s/aws", + "destination": "/api-reference/server/services/s2s/aws" + }, + { + "source": "/server/services/s2s/gemini-live", + "destination": "/api-reference/server/services/s2s/gemini-live" + }, + { + "source": "/server/services/s2s/gemini-live-vertex", + "destination": "/api-reference/server/services/s2s/gemini-live-vertex" + }, + { + "source": "/server/services/s2s/grok", + "destination": "/api-reference/server/services/s2s/grok" + }, + { + "source": "/server/services/s2s/openai", + "destination": "/api-reference/server/services/s2s/openai" + }, + { + "source": "/server/services/s2s/ultravox", + "destination": "/api-reference/server/services/s2s/ultravox" + }, + { + "source": "/server/services/image-generation/azure", + "destination": "/api-reference/server/services/image-generation/azure" + }, + { + "source": "/server/services/image-generation/fal", + "destination": "/api-reference/server/services/image-generation/fal" + }, + { + "source": "/server/services/image-generation/google", + "destination": "/api-reference/server/services/image-generation/google" + }, + { + "source": "/server/services/image-generation/openai", + "destination": "/api-reference/server/services/image-generation/openai" + }, + { + "source": "/server/services/video/heygen", + "destination": "/api-reference/server/services/video/heygen" + }, + { + "source": "/server/services/video/simli", + "destination": "/api-reference/server/services/video/simli" + }, + { + "source": "/server/services/video/tavus", + "destination": "/api-reference/server/services/video/tavus" + }, + { + "source": "/server/services/memory/mem0", + "destination": "/api-reference/server/services/memory/mem0" + }, + { + "source": "/server/services/vision/moondream", + "destination": "/api-reference/server/services/vision/moondream" + }, + { + "source": "/server/services/analytics/sentry", + "destination": "/api-reference/server/services/analytics/sentry" + }, + { + "source": "/server/utilities/frame/llm-text-processor", + "destination": "/api-reference/server/utilities/frame/llm-text-processor" + }, + { + "source": "/server/utilities/frame/producer-consumer", + "destination": "/api-reference/server/utilities/frame/producer-consumer" + }, + { + "source": "/server/utilities/user-idle-processor", + "destination": "/api-reference/server/utilities/user-idle-processor" + }, + { + "source": "/server/utilities/audio/aic-filter", + "destination": "/api-reference/server/utilities/audio/aic-filter" + }, + { + "source": "/server/utilities/audio/audio-buffer-processor", + "destination": "/api-reference/server/utilities/audio/audio-buffer-processor" + }, + { + "source": "/server/utilities/audio/koala-filter", + "destination": "/api-reference/server/utilities/audio/koala-filter" + }, + { + "source": "/server/utilities/audio/krisp-viva-filter", + "destination": "/api-reference/server/utilities/audio/krisp-viva-filter" + }, + { + "source": "/server/utilities/audio/krisp-viva-vad-analyzer", + "destination": "/api-reference/server/utilities/audio/krisp-viva-vad-analyzer" + }, + { + "source": "/server/utilities/audio/rnnoise-filter", + "destination": "/api-reference/server/utilities/audio/rnnoise-filter" + }, + { + "source": "/server/utilities/audio/silero-vad-analyzer", + "destination": "/api-reference/server/utilities/audio/silero-vad-analyzer" + }, + { + "source": "/server/utilities/audio/soundfile-mixer", + "destination": "/api-reference/server/utilities/audio/soundfile-mixer" + }, + { + "source": "/server/utilities/context-summarization", + "destination": "/api-reference/server/utilities/context-summarization" + }, + { + "source": "/server/utilities/extensions/ivr", + "destination": "/api-reference/server/utilities/extensions/ivr" + }, + { + "source": "/server/utilities/extensions/voicemail", + "destination": "/api-reference/server/utilities/extensions/voicemail" + }, + { + "source": "/server/utilities/filters/frame-filter", + "destination": "/api-reference/server/utilities/filters/frame-filter" + }, + { + "source": "/server/utilities/filters/function-filter", + "destination": "/api-reference/server/utilities/filters/function-filter" + }, + { + "source": "/server/utilities/filters/identify-filter", + "destination": "/api-reference/server/utilities/filters/identify-filter" + }, + { + "source": "/server/utilities/filters/null-filter", + "destination": "/api-reference/server/utilities/filters/null-filter" + }, + { + "source": "/server/utilities/filters/stt-mute", + "destination": "/api-reference/server/utilities/filters/stt-mute" + }, + { + "source": "/server/utilities/filters/wake-check-filter", + "destination": "/api-reference/server/utilities/filters/wake-check-filter" + }, + { + "source": "/server/utilities/filters/wake-notifier-filter", + "destination": "/api-reference/server/utilities/filters/wake-notifier-filter" + }, + { + "source": "/server/utilities/opentelemetry", + "destination": "/api-reference/server/utilities/opentelemetry" + }, + { + "source": "/server/utilities/mcp/mcp", + "destination": "/api-reference/server/utilities/mcp/mcp" + }, + { + "source": "/server/utilities/observers/observer-pattern", + "destination": "/api-reference/server/utilities/observers/observer-pattern" + }, + { + "source": "/server/utilities/observers/debug-observer", + "destination": "/api-reference/server/utilities/observers/debug-observer" + }, + { + "source": "/server/utilities/observers/llm-observer", + "destination": "/api-reference/server/utilities/observers/llm-observer" + }, + { + "source": "/server/utilities/observers/transcription-observer", + "destination": "/api-reference/server/utilities/observers/transcription-observer" + }, + { + "source": "/server/utilities/observers/startup-timing-observer", + "destination": "/api-reference/server/utilities/observers/startup-timing-observer" + }, + { + "source": "/server/utilities/observers/turn-tracking-observer", + "destination": "/api-reference/server/utilities/observers/turn-tracking-observer" + }, + { + "source": "/server/utilities/observers/user-bot-latency-observer", + "destination": "/api-reference/server/utilities/observers/user-bot-latency-observer" + }, + { + "source": "/server/utilities/runner/guide", + "destination": "/api-reference/server/utilities/runner/guide" + }, + { + "source": "/server/utilities/runner/transport-utils", + "destination": "/api-reference/server/utilities/runner/transport-utils" + }, + { + "source": "/server/utilities/daily/rest-helper", + "destination": "/api-reference/server/utilities/daily/rest-helper" + }, + { + "source": "/server/utilities/service-switchers/service-switcher", + "destination": "/api-reference/server/utilities/service-switchers/service-switcher" + }, + { + "source": "/server/utilities/service-switchers/llm-switcher", + "destination": "/api-reference/server/utilities/service-switchers/llm-switcher" + }, + { + "source": "/server/utilities/turn-detection/smart-turn-overview", + "destination": "/api-reference/server/utilities/turn-detection/smart-turn-overview" + }, + { + "source": "/server/utilities/turn-detection/krisp-viva-turn", + "destination": "/api-reference/server/utilities/turn-detection/krisp-viva-turn" + }, + { + "source": "/server/utilities/turn-detection/fal-smart-turn", + "destination": "/api-reference/server/utilities/turn-detection/fal-smart-turn" + }, + { + "source": "/server/utilities/dtmf-aggregator", + "destination": "/api-reference/server/utilities/dtmf-aggregator" + }, + { + "source": "/server/utilities/text/overview", + "destination": "/api-reference/server/utilities/text/overview" + }, + { + "source": "/server/utilities/text/markdown-text-filter", + "destination": "/api-reference/server/utilities/text/markdown-text-filter" + }, + { + "source": "/server/utilities/text/pattern-pair-aggregator", + "destination": "/api-reference/server/utilities/text/pattern-pair-aggregator" + }, + { + "source": "/server/utilities/transcript-processor", + "destination": "/api-reference/server/utilities/transcript-processor" + }, + { + "source": "/server/utilities/turn-management/user-turn-strategies", + "destination": "/api-reference/server/utilities/turn-management/user-turn-strategies" + }, + { + "source": "/server/utilities/turn-management/user-mute-strategies", + "destination": "/api-reference/server/utilities/turn-management/user-mute-strategies" + }, + { + "source": "/server/utilities/turn-management/filter-incomplete-turns", + "destination": "/api-reference/server/utilities/turn-management/filter-incomplete-turns" + }, + { + "source": "/server/utilities/turn-management/turn-events", + "destination": "/api-reference/server/utilities/turn-management/turn-events" + }, + { + "source": "/server/utilities/turn-management/transcriptions", + "destination": "/api-reference/server/utilities/turn-management/transcriptions" + }, + { + "source": "/server/utilities/turn-management/external-turn-management", + "destination": "/api-reference/server/utilities/turn-management/external-turn-management" + }, + { + "source": "/server/utilities/turn-management/interruption-strategies", + "destination": "/api-reference/server/utilities/turn-management/interruption-strategies" + }, + { + "source": "/server/events/overview", + "destination": "/api-reference/server/events/overview" + }, + { + "source": "/server/events/frame-processor-events", + "destination": "/api-reference/server/events/frame-processor-events" + }, + { + "source": "/server/events/service-events", + "destination": "/api-reference/server/events/service-events" + }, + { + "source": "/server/frameworks/rtvi/introduction", + "destination": "/api-reference/server/rtvi/introduction" + }, + { + "source": "/server/frameworks/rtvi/rtvi-processor", + "destination": "/api-reference/server/rtvi/rtvi-processor" + }, + { + "source": "/server/frameworks/rtvi/rtvi-observer", + "destination": "/api-reference/server/rtvi/rtvi-observer" + }, + { + "source": "/server/frameworks/rtvi/google-rtvi-observer", + "destination": "/api-reference/server/rtvi/google-rtvi-observer" + }, + { + "source": "/server/frames/overview", + "destination": "/api-reference/server/frames/overview" + }, + { + "source": "/server/frames/data-frames", + "destination": "/api-reference/server/frames/data-frames" + }, + { + "source": "/server/frames/control-frames", + "destination": "/api-reference/server/frames/control-frames" + }, + { + "source": "/server/frames/system-frames", + "destination": "/api-reference/server/frames/system-frames" + }, + { + "source": "/server/frames/llm-frames", + "destination": "/api-reference/server/frames/llm-frames" + }, + { + "source": "/server/pipeline/pipeline-params", + "destination": "/api-reference/server/pipeline/pipeline-params" + }, + { + "source": "/server/pipeline/pipeline-task", + "destination": "/api-reference/server/pipeline/pipeline-task" + }, + { + "source": "/server/pipeline/pipeline-idle-detection", + "destination": "/api-reference/server/pipeline/pipeline-idle-detection" + }, + { + "source": "/server/pipeline/heartbeats", + "destination": "/api-reference/server/pipeline/heartbeats" + }, + { + "source": "/server/pipeline/parallel-pipeline", + "destination": "/api-reference/server/pipeline/parallel-pipeline" + }, + { + "source": "/pipecat-flows/reference/overview", + "destination": "/api-reference/pipecat-flows/overview" + }, + { + "source": "/pipecat-flows/reference/flow-manager", + "destination": "/api-reference/pipecat-flows/flow-manager" + }, + { + "source": "/pipecat-flows/reference/types", + "destination": "/api-reference/pipecat-flows/types" + }, + { + "source": "/pipecat-flows/reference/exceptions", + "destination": "/api-reference/pipecat-flows/exceptions" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-create", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-create" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-update", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-update" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/start", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/start" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/stop", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/stop" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/session-proxy", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/session-proxy" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-get-logs", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-logs" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-get-sessions", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-sessions" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-get-session", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-get-session" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-list-all", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-all" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-list-one", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-list-one" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/agent-delete", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/agent-delete" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/secret-create-update", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/secret-create-update" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/secret-list-all", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-all" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/secret-list-one", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/secret-list-one" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-secret-set" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/secret-delete-specific-secret" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/build-upload-url", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/build-upload-url" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/build-create", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/build-create" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/build-list", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/build-list" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/build-get", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/build-get" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/build-get-logs", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/build-get-logs" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/regions-list", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/regions-list" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/properties-get", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/properties-get" + }, + { + "source": "/pipecat-cloud/rest-reference/endpoint/properties-update", + "destination": "/api-reference/pipecat-cloud/rest-reference/endpoint/properties-update" + }, + { + "source": "/pipecat-cloud/sdk-reference/overview", + "destination": "/api-reference/pipecat-cloud/sdk-reference/overview" + }, + { + "source": "/pipecat-cloud/sdk-reference/sessions", + "destination": "/api-reference/pipecat-cloud/sdk-reference/sessions" + }, + { + "source": "/pipecat-cloud/sdk-reference/session-arguments", + "destination": "/api-reference/pipecat-cloud/sdk-reference/session-arguments" + }, + { + "source": "/pipecat-cloud/sdk-reference/exceptions", + "destination": "/api-reference/pipecat-cloud/sdk-reference/exceptions" + }, + { + "source": "/pipecat-cloud/sdk-reference/examples", + "destination": "/api-reference/pipecat-cloud/sdk-reference/examples" + }, + { + "source": "/cli/overview", + "destination": "/api-reference/cli/overview" + }, + { + "source": "/cli/init", + "destination": "/api-reference/cli/init" + }, + { + "source": "/cli/tail", + "destination": "/api-reference/cli/tail" + }, + { + "source": "/cli/cloud/agent", + "destination": "/api-reference/cli/cloud/agent" + }, + { + "source": "/cli/cloud/auth", + "destination": "/api-reference/cli/cloud/auth" + }, + { + "source": "/cli/cloud/build", + "destination": "/api-reference/cli/cloud/build" + }, + { + "source": "/cli/cloud/docker", + "destination": "/api-reference/cli/cloud/docker" + }, + { + "source": "/cli/cloud/deploy", + "destination": "/api-reference/cli/cloud/deploy" + }, + { + "source": "/cli/cloud/organizations", + "destination": "/api-reference/cli/cloud/organizations" + }, + { + "source": "/cli/cloud/secrets", + "destination": "/api-reference/cli/cloud/secrets" + }, + { + "source": "/cli/cloud/regions", + "destination": "/api-reference/cli/cloud/regions" + }, + { + "source": "/api-reference/server/frameworks/rtvi/introduction", + "destination": "/api-reference/server/rtvi/introduction" + }, + { + "source": "/api-reference/server/frameworks/rtvi/rtvi-processor", + "destination": "/api-reference/server/rtvi/rtvi-processor" + }, + { + "source": "/api-reference/server/frameworks/rtvi/rtvi-observer", + "destination": "/api-reference/server/rtvi/rtvi-observer" + }, + { + "source": "/api-reference/server/frameworks/rtvi/google-rtvi-observer", + "destination": "/api-reference/server/rtvi/google-rtvi-observer" } ] } diff --git a/overview/flows.mdx b/overview/flows.mdx index ff5bad492..38d9327c4 100644 --- a/overview/flows.mdx +++ b/overview/flows.mdx @@ -34,7 +34,7 @@ Pipecat Flows is best suited for use cases where: Complete reference docs and technical details diff --git a/overview/pipecat.mdx b/overview/pipecat.mdx index 3e99484a5..143a305d6 100644 --- a/overview/pipecat.mdx +++ b/overview/pipecat.mdx @@ -93,7 +93,7 @@ In most cases, the entire round-trip interaction happens between 500-800ms, crea Browse the complete list of 100+ AI service integrations diff --git a/pipecat-cloud/fundamentals/deploy.mdx b/pipecat-cloud/fundamentals/deploy.mdx index a0f1ced20..8ce46b637 100644 --- a/pipecat-cloud/fundamentals/deploy.mdx +++ b/pipecat-cloud/fundamentals/deploy.mdx @@ -29,7 +29,7 @@ pipecat cloud deploy --region us-east Once the deployment completes, you will be able to run your agent on-demand. -For a complete list of deployment configuration options, see the [CLI deploy reference](/cli/cloud/deploy). +For a complete list of deployment configuration options, see the [CLI deploy reference](/api-reference/cli/cloud/deploy). ### Deploying with a custom image @@ -80,7 +80,7 @@ secret_set = "my-agent-secrets" For a complete reference of all configuration options, see the [deploy command - documentation](/cli/cloud/deploy#configuration-file-pcc-deploytoml). + documentation](/api-reference/cli/cloud/deploy#configuration-file-pcc-deploytoml). ### Agent Profiles diff --git a/pipecat-cloud/fundamentals/logging.mdx b/pipecat-cloud/fundamentals/logging.mdx index 2f0252f63..bd7edd3c0 100644 --- a/pipecat-cloud/fundamentals/logging.mdx +++ b/pipecat-cloud/fundamentals/logging.mdx @@ -77,11 +77,11 @@ Use the `sessions` command with a specific session ID to see CPU and memory usag pipecat cloud agent sessions my-agent --id ``` -See the [CLI reference](/cli/cloud/agent#sessions) for more details. +See the [CLI reference](/api-reference/cli/cloud/agent#sessions) for more details. ## Built-in pipeline observability -The base image automatically adds [StartupTimingObserver](/server/utilities/observers/startup-timing-observer) and [UserBotLatencyObserver](/server/utilities/observers/user-bot-latency-observer) to every `PipelineTask`. These observers log structured timing data that helps you understand your agent's performance: +The base image automatically adds [StartupTimingObserver](/api-reference/server/utilities/observers/startup-timing-observer) and [UserBotLatencyObserver](/api-reference/server/utilities/observers/user-bot-latency-observer) to every `PipelineTask`. These observers log structured timing data that helps you understand your agent's performance: - **Startup timing** — how long each processor takes to initialize - **Transport timing** — time to connect the bot and client to the transport diff --git a/pipecat-cloud/guides/cloud-builds.mdx b/pipecat-cloud/guides/cloud-builds.mdx index c7004c2ec..f9a24df6b 100644 --- a/pipecat-cloud/guides/cloud-builds.mdx +++ b/pipecat-cloud/guides/cloud-builds.mdx @@ -8,7 +8,7 @@ Pipecat Cloud Build lets you deploy agents directly from your source code. Inste ## Prerequisites - A [Pipecat Cloud account](/pipecat-cloud/fundamentals/accounts-and-organizations) with an active organization -- The [Pipecat CLI](/cli/overview) installed and authenticated (`pipecat cloud auth login`) +- The [Pipecat CLI](/api-reference/cli/overview) installed and authenticated (`pipecat cloud auth login`) - A Python project using uv, pip, or poetry ## Quick start @@ -103,7 +103,7 @@ In CI/CD mode, the CLI will: ## Build management -Monitor and manage your builds using the [`pipecat cloud build`](/cli/cloud/build) commands: +Monitor and manage your builds using the [`pipecat cloud build`](/api-reference/cli/cloud/build) commands: ```shell # List recent builds @@ -147,7 +147,7 @@ dockerfile = "Dockerfile" # Dockerfile path (default: "Dockerfile") patterns = ["*.md", "tests/"] # Additional exclusion patterns ``` -See the [deploy command reference](/cli/cloud/deploy#configuration-file-pcc-deploytoml) for the full list of configuration options. +See the [deploy command reference](/api-reference/cli/cloud/deploy#configuration-file-pcc-deploytoml) for the full list of configuration options. ## Next steps @@ -161,7 +161,7 @@ See the [deploy command reference](/cli/cloud/deploy#configuration-file-pcc-depl Use your own container registry for advanced image management. - + Full reference for build management commands. diff --git a/pipecat-cloud/guides/daily-webrtc.mdx b/pipecat-cloud/guides/daily-webrtc.mdx index 510ed8acb..bd477d373 100644 --- a/pipecat-cloud/guides/daily-webrtc.mdx +++ b/pipecat-cloud/guides/daily-webrtc.mdx @@ -144,7 +144,7 @@ The basic flow is handled for you, allowing you to focus on building your agent' Explore Pipecat's DailyTransport documentation diff --git a/pipecat-cloud/guides/krisp-viva.mdx b/pipecat-cloud/guides/krisp-viva.mdx index 914f7bb22..98b945395 100644 --- a/pipecat-cloud/guides/krisp-viva.mdx +++ b/pipecat-cloud/guides/krisp-viva.mdx @@ -109,7 +109,7 @@ curl -X POST https://api.pipecat.daily.co/v1/agents/voice-starter \ }' ``` -See the [REST API reference](/pipecat-cloud/rest-reference/endpoint/agent-create) for more details. +See the [REST API reference](/api-reference/pipecat-cloud/rest-reference/endpoint/agent-create) for more details. diff --git a/pipecat-cloud/guides/regions.mdx b/pipecat-cloud/guides/regions.mdx index 59c13cf4b..e4ce408d3 100644 --- a/pipecat-cloud/guides/regions.mdx +++ b/pipecat-cloud/guides/regions.mdx @@ -13,7 +13,7 @@ You can view all available regions using the CLI: pipecat cloud regions list ``` -Or via the [REST API](/pipecat-cloud/rest-reference/endpoint/regions-list). +Or via the [REST API](/api-reference/pipecat-cloud/rest-reference/endpoint/regions-list). Available regions include: @@ -74,7 +74,7 @@ wss://eu-central.api.pipecat.daily.co/ws/twilio ## Setting a Default Region -You can specify a default region for your organization via the [REST API](/pipecat-cloud/rest-reference/endpoint/properties-update) or the [CLI](/cli/cloud/organizations#default-region). If you don't specify a region, resources are created in your organization's default region. +You can specify a default region for your organization via the [REST API](/api-reference/pipecat-cloud/rest-reference/endpoint/properties-update) or the [CLI](/api-reference/cli/cloud/organizations#default-region). If you don't specify a region, resources are created in your organization's default region. ## Deploying an Agent to a Region @@ -113,7 +113,7 @@ max_agents = 10 See the [deploy command - reference](/cli/cloud/deploy#configuration-file-pcc-deploytoml) for all + reference](/api-reference/cli/cloud/deploy#configuration-file-pcc-deploytoml) for all available configuration options. diff --git a/pipecat-cloud/guides/session-api.mdx b/pipecat-cloud/guides/session-api.mdx index 39571ea37..d25fbf5d4 100644 --- a/pipecat-cloud/guides/session-api.mdx +++ b/pipecat-cloud/guides/session-api.mdx @@ -79,8 +79,8 @@ async def update_context(data: dict): Most Session API use cases require your endpoint to interact with the running pipeline. The pattern is: -1. Store a reference to your [`PipelineTask`](/server/pipeline/pipeline-task) in a module-level variable -2. Access it from your endpoint handler to [queue frames](/server/pipeline/pipeline-task#frame-management) into the pipeline +1. Store a reference to your [`PipelineTask`](/api-reference/server/pipeline/pipeline-task) in a module-level variable +2. Access it from your endpoint handler to [queue frames](/api-reference/server/pipeline/pipeline-task#frame-management) into the pipeline ```python from pipecatcloud_system import app @@ -118,7 +118,7 @@ async def update_context(data: dict): ### Update Conversation Context -Use [`LLMMessagesAppendFrame`](/server/pipeline/pipeline-task#frame-management) to add messages to the LLM's conversation context from an HTTP request. Setting `run_llm=True` tells the pipeline to immediately send the updated context to the LLM for a response. +Use [`LLMMessagesAppendFrame`](/api-reference/server/pipeline/pipeline-task#frame-management) to add messages to the LLM's conversation context from an HTTP request. Setting `run_llm=True` tells the pipeline to immediately send the updated context to the LLM for a response. ```python from pipecatcloud_system import app @@ -179,7 +179,7 @@ curl -X POST \ ### Trigger the Bot to Speak -Use [`TTSSpeakFrame`](/server/pipeline/pipeline-task#frame-management) to make the bot say something on demand: +Use [`TTSSpeakFrame`](/api-reference/server/pipeline/pipeline-task#frame-management) to make the bot say something on demand: ```python from pipecatcloud_system import app diff --git a/pipecat-flows/guides/quickstart.mdx b/pipecat-flows/guides/quickstart.mdx index a842df75b..94cea47c7 100644 --- a/pipecat-flows/guides/quickstart.mdx +++ b/pipecat-flows/guides/quickstart.mdx @@ -177,7 +177,7 @@ That's it! When a user connects, the bot greets them, asks for their favorite co Complete technical reference diff --git a/pipecat-flows/introduction.mdx b/pipecat-flows/introduction.mdx index a25b9bad7..a6f494d7d 100644 --- a/pipecat-flows/introduction.mdx +++ b/pipecat-flows/introduction.mdx @@ -50,7 +50,7 @@ The [Pipecat Flows Visual Editor](https://flows.pipecat.ai/) lets you design con Complete reference docs and technical details diff --git a/pipecat/deployment/overview.mdx b/pipecat/deployment/overview.mdx index 68bf48a68..37bf8e712 100644 --- a/pipecat/deployment/overview.mdx +++ b/pipecat/deployment/overview.mdx @@ -25,7 +25,7 @@ The best choice depends on your specific requirements, scale, and expertise. ### Things you'll need -- **Transport service** - Pipecat has existing services for various different [media transport](/server/services/supported-services#transports) modes, such as WebRTC or WebSockets. If you're not using a third-party service for handling media transport, you'll want to make sure that infrastructure is hosted and ready to receive connections. +- **Transport service** - Pipecat has existing services for various different [media transport](/api-reference/server/services/supported-services#transports) modes, such as WebRTC or WebSockets. If you're not using a third-party service for handling media transport, you'll want to make sure that infrastructure is hosted and ready to receive connections. - **Deployment target** - You can deploy and run Pipecat bots anywhere that can run Python code - Google Cloud Run, AWS, Fly.io etc. We recommend providers that offer APIs, so you can programmatically spawn new bot agents on-demand. diff --git a/pipecat/deployment/pattern.mdx b/pipecat/deployment/pattern.mdx index 84835ce9d..59f4c0e4e 100644 --- a/pipecat/deployment/pattern.mdx +++ b/pipecat/deployment/pattern.mdx @@ -100,7 +100,7 @@ A client will typically require some information regarding the newly spawned bot ### Data transport -Your [transport layer](/server/services/transport/daily) is responsible for sending and receiving audio and video data over the internet. +Your [transport layer](/api-reference/server/services/transport/daily) is responsible for sending and receiving audio and video data over the internet. You will have implemented a transport layer as part of your `bot.py` pipeline. This may be a service that you want to host and include in your deployment, or it may be a third-party service waiting for peers to connect (such as [Daily](https://www.daily.co), or a websocket.) diff --git a/pipecat/features/gemini-live.mdx b/pipecat/features/gemini-live.mdx index 0811d7c34..633681c90 100644 --- a/pipecat/features/gemini-live.mdx +++ b/pipecat/features/gemini-live.mdx @@ -9,11 +9,11 @@ Gemini Live is Google's speech-to-speech API that enables natural, real-time voi Gemini Live service documentation - + Scaffold and deploy projects diff --git a/pipecat/features/krisp-viva.mdx b/pipecat/features/krisp-viva.mdx index 244646060..7fc5165bc 100644 --- a/pipecat/features/krisp-viva.mdx +++ b/pipecat/features/krisp-viva.mdx @@ -9,7 +9,7 @@ description: "Learn how to integrate Krisp's VIVA voice isolation and turn detec Krisp's VIVA SDK provides three capabilities for Pipecat applications: - **Voice Isolation** — Filter out background noise and voices from the user's audio input stream, yielding clearer audio for fewer false interruptions and better transcription. -- **Turn Detection** — Determine when a user has finished speaking using Krisp's streaming turn detection model, as an alternative to the [Smart Turn model](/server/utilities/turn-detection/smart-turn-overview). +- **Turn Detection** — Determine when a user has finished speaking using Krisp's streaming turn detection model, as an alternative to the [Smart Turn model](/api-reference/server/utilities/turn-detection/smart-turn-overview). - **Voice Activity Detection** — Detect speech in audio streams using Krisp's VAD model, supporting sample rates from 8kHz to 48kHz. You can use any combination of these features together. @@ -18,21 +18,21 @@ You can use any combination of these features together. API reference for voice isolation API reference for turn detection API reference for voice activity detection @@ -149,11 +149,11 @@ transport = SmallWebRTCTransport( ) ``` -See the [KrispVivaFilter reference](/server/utilities/audio/krisp-viva-filter) for configuration options. +See the [KrispVivaFilter reference](/api-reference/server/utilities/audio/krisp-viva-filter) for configuration options. ## Turn Detection -`KrispVivaTurn` uses Krisp's streaming turn detection model to determine when a user has finished speaking. Unlike the [Smart Turn model](/server/utilities/turn-detection/smart-turn-overview) which analyzes audio in batches, `KrispVivaTurn` processes each audio frame in real time. +`KrispVivaTurn` uses Krisp's streaming turn detection model to determine when a user has finished speaking. Unlike the [Smart Turn model](/api-reference/server/utilities/turn-detection/smart-turn-overview) which analyzes audio in batches, `KrispVivaTurn` processes each audio frame in real time. Configure it as a user turn stop strategy: @@ -180,7 +180,7 @@ user_aggregator, assistant_aggregator = LLMContextAggregatorPair( ) ``` -See the [KrispVivaTurn reference](/server/utilities/turn-detection/krisp-viva-turn) for configuration options. +See the [KrispVivaTurn reference](/api-reference/server/utilities/turn-detection/krisp-viva-turn) for configuration options. ## Voice Activity Detection @@ -204,4 +204,4 @@ user_aggregator, assistant_aggregator = LLMContextAggregatorPair( ) ``` -See the [KrispVivaVadAnalyzer reference](/server/utilities/audio/krisp-viva-vad-analyzer) for configuration options. +See the [KrispVivaVadAnalyzer reference](/api-reference/server/utilities/audio/krisp-viva-vad-analyzer) for configuration options. diff --git a/pipecat/features/openai-audio-models-and-apis.mdx b/pipecat/features/openai-audio-models-and-apis.mdx index 13e79ac3a..094bbf895 100644 --- a/pipecat/features/openai-audio-models-and-apis.mdx +++ b/pipecat/features/openai-audio-models-and-apis.mdx @@ -58,25 +58,25 @@ Which approach should you choose? ### Transcription API - Models: `gpt-4o-transcribe`, `gpt-4o-mini-transcribe` -- Pipecat service: `OpenAISTTService` ([reference docs](/server/services/stt/openai)) +- Pipecat service: `OpenAISTTService` ([reference docs](/api-reference/server/services/stt/openai)) - OpenAI endpoint: `/v1/audio/transcriptions` ([docs](https://platform.openai.com/docs/api-reference/audio/createTranscription)) ### Chat Completions API - Models: `gpt-4o`, `gpt-4o-mini`, `gpt-4o-audio-preview` -- Pipecat service: `OpenAILLMService` ([reference docs](/server/services/llm/openai)) +- Pipecat service: `OpenAILLMService` ([reference docs](/api-reference/server/services/llm/openai)) - OpenAI endpoint: `/v1/chat/completions` ([docs](https://platform.openai.com/docs/api-reference/chat)) ### Realtime API - Models: `gpt-realtime-1.5`, `gpt-realtime` -- Pipecat service: `OpenAIRealtimeBetaLLMService` ([reference docs](/server/services/s2s/openai)) +- Pipecat service: `OpenAIRealtimeBetaLLMService` ([reference docs](/api-reference/server/services/s2s/openai)) - OpenAI docs ([overview](https://platform.openai.com/docs/guides/realtime)) ### Speech API - Models: `gpt-4o-mini-tts` -- Pipecat service: `OpenAITTSService` ([reference docs](/server/services/tts/openai)) +- Pipecat service: `OpenAITTSService` ([reference docs](/api-reference/server/services/tts/openai)) - OpenAI endpoint: `/v1/audio/speech` ([docs](https://platform.openai.com/docs/api-reference/audio/createSpeech)) ## Sample code and starter kits diff --git a/pipecat/fundamentals/context-summarization.mdx b/pipecat/fundamentals/context-summarization.mdx index 413b91cb3..7e420a78c 100644 --- a/pipecat/fundamentals/context-summarization.mdx +++ b/pipecat/fundamentals/context-summarization.mdx @@ -77,7 +77,7 @@ user_aggregator, assistant_aggregator = LLMContextAggregatorPair( ) ``` -See the [reference page](/server/utilities/context-summarization) for all available configuration parameters. +See the [reference page](/api-reference/server/utilities/context-summarization) for all available configuration parameters. ## What Gets Preserved @@ -207,7 +207,7 @@ if summarizer: title="Context Summarization Reference" icon="file-lines" iconType="duotone" - href="/server/utilities/context-summarization" + href="/api-reference/server/utilities/context-summarization" > Full reference for configuration parameters, events, and classes. diff --git a/pipecat/fundamentals/detecting-user-idle.mdx b/pipecat/fundamentals/detecting-user-idle.mdx index 62d0e4f73..4055b2645 100644 --- a/pipecat/fundamentals/detecting-user-idle.mdx +++ b/pipecat/fundamentals/detecting-user-idle.mdx @@ -141,7 +141,7 @@ This is useful when you want to enable idle detection only at certain points in title="Turn Events" icon="book" iconType="duotone" - href="/server/utilities/turn-management/turn-events" + href="/api-reference/server/utilities/turn-management/turn-events" > Learn about all available turn events and their parameters. diff --git a/pipecat/fundamentals/evaluations/overview.mdx b/pipecat/fundamentals/evaluations/overview.mdx index 068f1e627..adc48ca99 100644 --- a/pipecat/fundamentals/evaluations/overview.mdx +++ b/pipecat/fundamentals/evaluations/overview.mdx @@ -60,7 +60,7 @@ Continuous evaluation of live calls lets you catch regressions, track quality ov - Submitting call recordings and transcripts for automated quality scoring - Tracking evaluation metrics over time to detect quality drift -- Using [OpenTelemetry traces](/server/utilities/opentelemetry) to monitor latency and execution flow +- Using [OpenTelemetry traces](/api-reference/server/utilities/opentelemetry) to monitor latency and execution flow Together, simulations and observability form a feedback loop: simulations validate changes before deployment, and observability surfaces issues that inform your next round of tests. @@ -110,8 +110,8 @@ Pipecat provides several building blocks that feed into any evaluation workflow: - **[Metrics](/pipecat/fundamentals/metrics)**: Built-in TTFB, processing time, and usage tracking for LLM and TTS services - **[Saving transcripts](/pipecat/fundamentals/saving-transcripts)**: Capture conversation transcripts for offline analysis and evaluation -- **[OpenTelemetry](/server/utilities/opentelemetry)**: Export traces to any OTel-compatible backend for latency and performance monitoring -- **[Observers](/server/utilities/observers/observer-pattern)**: Monitor frame flow without modifying the pipeline, useful for custom instrumentation +- **[OpenTelemetry](/api-reference/server/utilities/opentelemetry)**: Export traces to any OTel-compatible backend for latency and performance monitoring +- **[Observers](/api-reference/server/utilities/observers/observer-pattern)**: Monitor frame flow without modifying the pipeline, useful for custom instrumentation ## Next steps @@ -138,7 +138,7 @@ Pipecat provides several building blocks that feed into any evaluation workflow: title="OpenTelemetry" icon="tower-broadcast" iconType="duotone" - href="/server/utilities/opentelemetry" + href="/api-reference/server/utilities/opentelemetry" > Export traces for performance monitoring and debugging. diff --git a/pipecat/fundamentals/metrics.mdx b/pipecat/fundamentals/metrics.mdx index 3865f7317..8ea7ab1e9 100644 --- a/pipecat/fundamentals/metrics.mdx +++ b/pipecat/fundamentals/metrics.mdx @@ -118,7 +118,7 @@ When metrics are enabled, Pipecat emits a `MetricsFrame` for each interaction. T - `TextAggregationMetricsData` — Sentence aggregation latency (TTS) - `TurnMetricsData` — Turn completion predictions -You can access the metrics data by either adding a custom [FrameProcessor](/pipecat/fundamentals/custom-frame-processor) to your pipeline or adding an [observer](/server/utilities/observers/observer-pattern) to monitor `MetricsFrame`s. +You can access the metrics data by either adding a custom [FrameProcessor](/pipecat/fundamentals/custom-frame-processor) to your pipeline or adding an [observer](/api-reference/server/utilities/observers/observer-pattern) to monitor `MetricsFrame`s. ### Example: Using MetricsLogObserver diff --git a/pipecat/fundamentals/recording-audio.mdx b/pipecat/fundamentals/recording-audio.mdx index 3cc32eea0..952e333bc 100644 --- a/pipecat/fundamentals/recording-audio.mdx +++ b/pipecat/fundamentals/recording-audio.mdx @@ -10,7 +10,7 @@ Recording audio from conversations provides valuable data for analysis, debuggin ### Option 1: Record using your transport service provider -Record without writing custom code by using your [transport](/server/services/supported-services#transports) provider's recording capabilities. In addition to saving you development time, some providers offer unique recording capabilities. +Record without writing custom code by using your [transport](/api-reference/server/services/supported-services#transports) provider's recording capabilities. In addition to saving you development time, some providers offer unique recording capabilities. Refer to your service provider's documentation to learn more. @@ -224,7 +224,7 @@ ffmpeg -f concat -safe 0 -i filelist.txt -c copy final_recording.wav title="AudioBufferProcessor Reference" icon="book" iconType="duotone" - href="/server/utilities/audio/audio-buffer-processor" + href="/api-reference/server/utilities/audio/audio-buffer-processor" > Read the complete API reference documentation for advanced configuration options and event handlers. diff --git a/pipecat/fundamentals/saving-transcripts.mdx b/pipecat/fundamentals/saving-transcripts.mdx index 929983f6a..96ec39aee 100644 --- a/pipecat/fundamentals/saving-transcripts.mdx +++ b/pipecat/fundamentals/saving-transcripts.mdx @@ -84,7 +84,7 @@ async def on_assistant_turn_stopped(aggregator, message: AssistantTurnStoppedMes title="Turn Events Reference" icon="book" iconType="duotone" - href="/server/utilities/turn-management/turn-events" + href="/api-reference/server/utilities/turn-management/turn-events" > Learn about all available turn events and their parameters. @@ -93,7 +93,7 @@ async def on_assistant_turn_stopped(aggregator, message: AssistantTurnStoppedMes title="Transcriptions Reference" icon="scroll" iconType="duotone" - href="/server/utilities/turn-management/transcriptions" + href="/api-reference/server/utilities/turn-management/transcriptions" > See more examples for collecting and processing transcriptions. diff --git a/pipecat/fundamentals/service-settings.mdx b/pipecat/fundamentals/service-settings.mdx index 6162df740..5f3176fa3 100644 --- a/pipecat/fundamentals/service-settings.mdx +++ b/pipecat/fundamentals/service-settings.mdx @@ -88,7 +88,7 @@ Each service type has a base set of settings. Individual services may extend the Individual services extend these base settings with provider-specific fields. For example, Deepgram STT adds `endpointing`, `smart_format`, `diarize`, and more. See the individual [service - documentation](/server/services/supported-services) for the full list of + documentation](/api-reference/server/services/supported-services) for the full list of available settings. diff --git a/pipecat/fundamentals/stt-latency-tuning.mdx b/pipecat/fundamentals/stt-latency-tuning.mdx index f6e5a15b1..3b0eff583 100644 --- a/pipecat/fundamentals/stt-latency-tuning.mdx +++ b/pipecat/fundamentals/stt-latency-tuning.mdx @@ -15,7 +15,7 @@ Every STT service has a different TTFS profile based on its architecture, model ## Why TTFS matters -TTFS feeds directly into [turn stop strategies](/server/utilities/turn-management/user-turn-strategies), which decide when the user has finished speaking and the bot should respond. +TTFS feeds directly into [turn stop strategies](/api-reference/server/utilities/turn-management/user-turn-strategies), which decide when the user has finished speaking and the bot should respond. - **Value too low**: The turn stop strategy gives up waiting before the final transcript arrives. The bot responds based on incomplete text, or misses the user's input entirely. - **Value too high**: The bot waits longer than necessary after the user stops speaking, creating awkward pauses in the conversation. diff --git a/pipecat/fundamentals/user-input-muting.mdx b/pipecat/fundamentals/user-input-muting.mdx index 4fad67f7f..d812720a3 100644 --- a/pipecat/fundamentals/user-input-muting.mdx +++ b/pipecat/fundamentals/user-input-muting.mdx @@ -186,7 +186,7 @@ pcClient.on(RTVIEvent.UserMuteStopped, () => { title="User Mute Strategies Reference" icon="book" iconType="duotone" - href="/server/utilities/turn-management/user-mute-strategies" + href="/api-reference/server/utilities/turn-management/user-mute-strategies" > Read the complete API reference documentation for all available mute strategies and their behavior. @@ -196,7 +196,7 @@ pcClient.on(RTVIEvent.UserMuteStopped, () => { title="User Turn Strategies" icon="arrows-turn-to-dots" iconType="duotone" - href="/server/utilities/turn-management/user-turn-strategies" + href="/api-reference/server/utilities/turn-management/user-turn-strategies" > Learn how to configure turn detection behavior for more control over conversation flow. diff --git a/pipecat/get-started/build-your-next-bot.mdx b/pipecat/get-started/build-your-next-bot.mdx index 166656f69..bfd860d99 100644 --- a/pipecat/get-started/build-your-next-bot.mdx +++ b/pipecat/get-started/build-your-next-bot.mdx @@ -37,7 +37,7 @@ pipecat init The CLI will guide you through selecting your platform (phone or web/mobile), transport provider, AI services (STT, LLM, TTS), and deployment target. - + See detailed options and generated project structure diff --git a/pipecat/get-started/introduction.mdx b/pipecat/get-started/introduction.mdx index 8aa72588c..9419fb28d 100644 --- a/pipecat/get-started/introduction.mdx +++ b/pipecat/get-started/introduction.mdx @@ -93,7 +93,7 @@ In most cases, the entire round-trip interaction happens between 500-800ms, crea Browse the complete list of 100+ AI service integrations diff --git a/pipecat/get-started/quickstart.mdx b/pipecat/get-started/quickstart.mdx index 4a9344014..66152d97f 100644 --- a/pipecat/get-started/quickstart.mdx +++ b/pipecat/get-started/quickstart.mdx @@ -233,7 +233,7 @@ llm = OpenAILLMService( Pipecat supports many different AI services. You can swap out Deepgram for Soniox, OpenAI for Anthropic, or Cartesia for ElevenLabs without changing the rest of your code. -See the [supported services documentation](/server/services/supported-services) for all available options. +See the [supported services documentation](/api-reference/server/services/supported-services) for all available options. ### Context and Messages @@ -287,7 +287,7 @@ task = PipelineTask( ) ``` -The task handles pipeline execution, collects metrics, and manages RTVI events through [observers](/server/utilities/observers/observer-pattern). +The task handles pipeline execution, collects metrics, and manages RTVI events through [observers](/api-reference/server/utilities/observers/observer-pattern). ### Event Handlers diff --git a/pipecat/learn/context-management.mdx b/pipecat/learn/context-management.mdx index 202b56096..a10e8c6e5 100644 --- a/pipecat/learn/context-management.mdx +++ b/pipecat/learn/context-management.mdx @@ -71,8 +71,8 @@ user_aggregator, assistant_aggregator = LLMContextAggregatorPair(context) The context aggregator also supports configuring [user turn - strategies](/server/utilities/turn-management/user-turn-strategies) and [user - mute strategies](/server/utilities/turn-management/user-mute-strategies) via + strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) and [user + mute strategies](/api-reference/server/utilities/turn-management/user-mute-strategies) via `LLMUserAggregatorParams`. diff --git a/pipecat/learn/llm.mdx b/pipecat/learn/llm.mdx index 7d024d72c..d9c22fc8f 100644 --- a/pipecat/learn/llm.mdx +++ b/pipecat/learn/llm.mdx @@ -76,7 +76,7 @@ For a complete list of supported LLM services, see the Supported Services page: View the complete list of supported language model providers @@ -129,7 +129,7 @@ For detailed configuration options specific to each provider: Explore configuration options for each supported LLM provider diff --git a/pipecat/learn/pipeline-termination.mdx b/pipecat/learn/pipeline-termination.mdx index df89e3a9a..3bb5f8778 100644 --- a/pipecat/learn/pipeline-termination.mdx +++ b/pipecat/learn/pipeline-termination.mdx @@ -143,7 +143,7 @@ You can further configure the idle detection behavior. To learn more, refer to t Learn how to configure and customize idle detection for your use case diff --git a/pipecat/learn/pipeline.mdx b/pipecat/learn/pipeline.mdx index facf97387..ae6ad3624 100644 --- a/pipecat/learn/pipeline.mdx +++ b/pipecat/learn/pipeline.mdx @@ -348,7 +348,7 @@ These configuration options enable you to optimize performance, debug issues, an Configure execution parameters, audio settings, and debugging options @@ -362,7 +362,7 @@ These configuration options enable you to optimize performance, debug issues, an Monitor pipeline events, frame processing, and custom application events diff --git a/pipecat/learn/session-initialization.mdx b/pipecat/learn/session-initialization.mdx index 95846e40a..68b11b10a 100644 --- a/pipecat/learn/session-initialization.mdx +++ b/pipecat/learn/session-initialization.mdx @@ -71,7 +71,7 @@ The development runner automatically: Learn more about building with the development runner in the [runner - guide](/server/utilities/runner/guide). + guide](/api-reference/server/utilities/runner/guide). ## Connection Types Under the Hood diff --git a/pipecat/learn/speech-input.mdx b/pipecat/learn/speech-input.mdx index 709fbff72..cc2729ae9 100644 --- a/pipecat/learn/speech-input.mdx +++ b/pipecat/learn/speech-input.mdx @@ -7,7 +7,7 @@ A key to natural conversations is properly detecting when the user starts and st ## Overview -Pipecat uses [user turn strategies](/server/utilities/turn-management/user-turn-strategies) to determine when user turns start and end. These strategies can use different techniques: +Pipecat uses [user turn strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) to determine when user turns start and end. These strategies can use different techniques: **For detecting turn start:** @@ -26,7 +26,7 @@ Custom strategies can also be implemented for specific use cases. By combining t ### What VAD Does -VAD is responsible for detecting when a user starts and stops speaking. Pipecat includes [Silero VAD](https://github.com/snakers4/silero-vad), an open-source model that runs locally on CPU with minimal overhead. [Krisp VIVA VAD](/server/utilities/audio/krisp-viva-vad-analyzer) is also available for applications requiring support for higher sample rates. +VAD is responsible for detecting when a user starts and stops speaking. Pipecat includes [Silero VAD](https://github.com/snakers4/silero-vad), an open-source model that runs locally on CPU with minimal overhead. [Krisp VIVA VAD](/api-reference/server/utilities/audio/krisp-viva-vad-analyzer) is also available for applications requiring support for higher sample rates. **Silero VAD performance characteristics:** @@ -130,7 +130,7 @@ stop_strategy = SpeechTimeoutUserTurnStopStrategy(user_speech_timeout=0.6) Complete reference for start and stop strategies @@ -138,7 +138,7 @@ stop_strategy = SpeechTimeoutUserTurnStopStrategy(user_speech_timeout=0.6) Smart Turn model implementation guide diff --git a/pipecat/learn/speech-to-text.mdx b/pipecat/learn/speech-to-text.mdx index 2c9f59329..153c4c5ea 100644 --- a/pipecat/learn/speech-to-text.mdx +++ b/pipecat/learn/speech-to-text.mdx @@ -59,7 +59,7 @@ Pipecat supports a wide range of STT providers to fit different needs and budget View the complete list of supported speech-to-text providers @@ -67,29 +67,29 @@ Pipecat supports a wide range of STT providers to fit different needs and budget Popular options include: - + Fast, accurate streaming STT with excellent real-time performance Advanced speech recognition with strong accent and dialect handling - + AI-powered transcription with speaker diarization and sentiment analysis - + High-performance STT with multilingual support and custom models - + Microsoft's enterprise-grade STT service with extensive language support Reliable transcription with strong language model integration @@ -104,7 +104,7 @@ Each STT service has its own customization options. Refer to specific service do Explore configuration options for each supported STT provider @@ -207,7 +207,7 @@ stt = DeepgramSTTService( ) ``` -**Language array** — Google Cloud STT accepts a list of languages for multi-language recognition. See the [Google STT docs](/server/services/stt/google) for details. +**Language array** — Google Cloud STT accepts a list of languages for multi-language recognition. See the [Google STT docs](/api-reference/server/services/stt/google) for details. Some services have additional multilingual features. For example, Soniox diff --git a/pipecat/learn/text-to-speech.mdx b/pipecat/learn/text-to-speech.mdx index 4ba28dd9c..f2ecb370e 100644 --- a/pipecat/learn/text-to-speech.mdx +++ b/pipecat/learn/text-to-speech.mdx @@ -55,7 +55,7 @@ Pipecat supports a wide range of TTS providers with different capabilities and p View the complete list of supported text-to-speech providers @@ -112,7 +112,7 @@ tts = CartesiaTTSService( Explore configuration options for each supported TTS provider @@ -141,11 +141,11 @@ task = PipelineTask( ### Custom Text Aggregation -By default, TTS services have a built-in text aggregator that collects streaming text into sentences before passing them to the underlying service. However, you can customize this behavior by inserting an [`LLMTextProcessor`](/server/utilities/frame/llm-text-processor) with a different text aggregator before the TTS in your pipeline. This allows the ability to categorize and structure text into logical units beyond simple sentences, such as code blocks, URLs, or custom tags. You can then configure the TTS to handle these different text types appropriately, such as skipping code blocks or transforming them in a just-in-time manner before speaking. +By default, TTS services have a built-in text aggregator that collects streaming text into sentences before passing them to the underlying service. However, you can customize this behavior by inserting an [`LLMTextProcessor`](/api-reference/server/utilities/frame/llm-text-processor) with a different text aggregator before the TTS in your pipeline. This allows the ability to categorize and structure text into logical units beyond simple sentences, such as code blocks, URLs, or custom tags. You can then configure the TTS to handle these different text types appropriately, such as skipping code blocks or transforming them in a just-in-time manner before speaking. ### Skipping Text Aggregations -To skip certain text aggregations (e.g., code snippets or URLs) and keep them from being spoken, use a custom text aggregator like [`PatternPairAggregator`](/server/utilities/text/pattern-pair-aggregator) within an [`LLMTextProcessor`](/server/utilities/frame/llm-text-processor), and configure it to identify and handle specific patterns in the text stream. With this, you can then pass any aggregated types you want to skip (like "code") to the TTS service's `skip_aggregator_types` parameter. +To skip certain text aggregations (e.g., code snippets or URLs) and keep them from being spoken, use a custom text aggregator like [`PatternPairAggregator`](/api-reference/server/utilities/text/pattern-pair-aggregator) within an [`LLMTextProcessor`](/api-reference/server/utilities/frame/llm-text-processor), and configure it to identify and handle specific patterns in the text stream. With this, you can then pass any aggregated types you want to skip (like "code") to the TTS service's `skip_aggregator_types` parameter. ```python # Create pattern aggregator @@ -299,7 +299,7 @@ await self.push_frame(frame) ### Common Use Cases -**Encoding structured output from the LLM.** You can instruct the LLM to include markers or metadata in its response that should be processed by pipeline logic but not spoken. For example, Pipecat's [turn completion detection](/server/utilities/turn-management/filter-incomplete-turns) uses this approach — the LLM outputs completion markers (`✓`, `○`, `◐`) that are pushed with `skip_tts=True` so they update the context but aren't spoken. +**Encoding structured output from the LLM.** You can instruct the LLM to include markers or metadata in its response that should be processed by pipeline logic but not spoken. For example, Pipecat's [turn completion detection](/api-reference/server/utilities/turn-management/filter-incomplete-turns) uses this approach — the LLM outputs completion markers (`✓`, `○`, `◐`) that are pushed with `skip_tts=True` so they update the context but aren't spoken. **Switching between voice and text input.** When a client sends text input instead of speech, you may want the bot to respond with text only. The client SDKs support this via `sendText()` with `audio_response: false`, which uses `LLMConfigureOutputFrame` internally to temporarily disable TTS for that response. diff --git a/pipecat/learn/transports.mdx b/pipecat/learn/transports.mdx index 12ec3a92d..50374015d 100644 --- a/pipecat/learn/transports.mdx +++ b/pipecat/learn/transports.mdx @@ -13,7 +13,7 @@ Pipecat supports multiple transport types to fit different use cases and deploym WebRTC-based transport using Daily's infrastructure for video calls and conferencing @@ -21,42 +21,42 @@ Pipecat supports multiple transport types to fit different use cases and deploym WebSocket transport for telephony providers and custom WebSocket connections Specialized transport for HeyGen LiveAvatar video generation and streaming WebRTC transport using LiveKit's real-time communication platform Direct peer-to-peer WebRTC connections without cloud infrastructure Specialized transport for Tavus video generation and streaming General-purpose WebSocket transport for custom implementations @@ -129,7 +129,7 @@ params = TransportParams( For advanced turn detection (like Smart Turn), configure [User Turn - Strategies](/server/utilities/turn-management/user-turn-strategies) on the + Strategies](/api-reference/server/utilities/turn-management/user-turn-strategies) on the context aggregator instead of using the transport's turn_analyzer parameter. @@ -148,16 +148,16 @@ Telephony services (phone calls) use WebSocket connections with specialized seri ### Supported Telephony Providers - + Media Streams over WebSocket with TwilioFrameSerializer - + Real-time media streaming with TelnyxFrameSerializer - + Voice streaming API with PlivoFrameSerializer - + Voice streaming integration with ExotelFrameSerializer diff --git a/server/services/supported-services.mdx b/server/services/supported-services.mdx deleted file mode 100644 index 30b761570..000000000 --- a/server/services/supported-services.mdx +++ /dev/null @@ -1,179 +0,0 @@ ---- -title: "Supported Services" -description: "AI services integrated with Pipecat and their setup requirements" ---- - -## Transports - -Transports exchange audio and video streams between the user and bot. - -| Service | Setup | -| ------------------------------------------------------------------------- | -------------------------------------- | -| [DailyTransport](/server/services/transport/daily) | `pip install "pipecat-ai[daily]"` | -| [FastAPIWebSocketTransport](/server/services/transport/fastapi-websocket) | `pip install "pipecat-ai[websocket]"` | -| [HeyGenTransport](/server/services/transport/heygen) | `pip install "pipecat-ai[heygen]"` | -| [LemonSliceTransport](/server/services/transport/lemonslice) | `pip install "pipecat-ai[lemonslice]"` | -| [LiveKitTransport](/server/services/transport/livekit) | `pip install "pipecat-ai[livekit]"` | -| [SmallWebRTCTransport](/server/services/transport/small-webrtc) | `pip install "pipecat-ai[webrtc]"` | -| [TavusTransport](/server/services/transport/tavus) | `pip install "pipecat-ai[tavus]"` | -| [WebSocket Transports](/server/services/transport/websocket-server) | `pip install "pipecat-ai[websocket]"` | -| [WhatsAppTransport](/server/services/transport/whatsapp) | `pip install "pipecat-ai[webrtc]"` | - -## Serializers - -Serializers convert between frames and media streams, enabling real-time communication over a websocket. - -| Service | Setup | -| ----------------------------------------------- | ------------------------ | -| [Exotel](/server/services/serializers/exotel) | No dependencies required | -| [Genesys](/server/services/serializers/genesys) | No dependencies required | -| [Plivo](/server/services/serializers/plivo) | No dependencies required | -| [Telnyx](/server/services/serializers/telnyx) | No dependencies required | -| [Twilio](/server/services/serializers/twilio) | No dependencies required | -| [Vonage](/server/services/serializers/vonage) | No dependencies required | - -## Speech-to-Text - -Speech-to-Text services receive and audio input and output transcriptions. - -| Service | Setup | -| ------------------------------------------------- | ---------------------------------------- | -| [AssemblyAI](/server/services/stt/assemblyai) | `pip install "pipecat-ai[assemblyai]"` | -| [AWS Transcribe](/server/services/stt/aws) | `pip install "pipecat-ai[aws]"` | -| [Azure](/server/services/stt/azure) | `pip install "pipecat-ai[azure]"` | -| [Cartesia](/server/services/stt/cartesia) | `pip install "pipecat-ai[cartesia]"` | -| [Deepgram](/server/services/stt/deepgram) | `pip install "pipecat-ai[deepgram]"` | -| [ElevenLabs](/server/services/stt/elevenlabs) | `pip install "pipecat-ai[elevenlabs]"` | -| [Fal Wizper](/server/services/stt/fal) | `pip install "pipecat-ai[fal]"` | -| [Gladia](/server/services/stt/gladia) | `pip install "pipecat-ai[gladia]"` | -| [Google](/server/services/stt/google) | `pip install "pipecat-ai[google]"` | -| [Gradium](/server/services/stt/gradium) | `pip install "pipecat-ai[gradium]"` | -| [Groq (Whisper)](/server/services/stt/groq) | `pip install "pipecat-ai[groq]"` | -| [NVIDIA](/server/services/stt/nvidia) | `pip install "pipecat-ai[nvidia]"` | -| [OpenAI](/server/services/stt/openai) | `pip install "pipecat-ai[openai]"` | -| [Sarvam](/server/services/stt/sarvam) | `pip install "pipecat-ai[sarvam]"` | -| [Soniox](/server/services/stt/soniox) | `pip install "pipecat-ai[soniox]"` | -| [Speechmatics](/server/services/stt/speechmatics) | `pip install "pipecat-ai[speechmatics]"` | -| [Whisper](/server/services/stt/whisper) | `pip install "pipecat-ai[whisper]"` | - -## Large Language Models - -LLMs receive text or audio based input and output a streaming text response. - -| Service | Setup | -| --------------------------------------------------------- | -------------------------------------- | -| [Anthropic](/server/services/llm/anthropic) | `pip install "pipecat-ai[anthropic]"` | -| [AWS Bedrock](/server/services/llm/aws) | `pip install "pipecat-ai[aws]"` | -| [Azure](/server/services/llm/azure) | `pip install "pipecat-ai[azure]"` | -| [Cerebras](/server/services/llm/cerebras) | `pip install "pipecat-ai[cerebras]"` | -| [DeepSeek](/server/services/llm/deepseek) | `pip install "pipecat-ai[deepseek]"` | -| [Fireworks AI](/server/services/llm/fireworks) | `pip install "pipecat-ai[fireworks]"` | -| [Google Gemini](/server/services/llm/google) | `pip install "pipecat-ai[google]"` | -| [Google Vertex AI](/server/services/llm/google-vertex) | `pip install "pipecat-ai[google]"` | -| [Grok](/server/services/llm/grok) | `pip install "pipecat-ai[grok]"` | -| [Groq](/server/services/llm/groq) | `pip install "pipecat-ai[groq]"` | -| [Mistral](/server/services/llm/mistral) | `pip install "pipecat-ai[mistral]"` | -| [NVIDIA](/server/services/llm/nvidia) | `pip install "pipecat-ai[nvidia]"` | -| [Novita AI](/server/services/llm/novita) | `pip install "pipecat-ai[novita]"` | -| [Ollama](/server/services/llm/ollama) | `pip install "pipecat-ai[ollama]"` | -| [OpenAI](/server/services/llm/openai) | `pip install "pipecat-ai[openai]"` | -| [OpenAI Responses](/server/services/llm/openai-responses) | `pip install "pipecat-ai[openai]"` | -| [OpenPipe](/server/services/llm/openpipe) | `pip install "pipecat-ai[openpipe]"` | -| [OpenRouter](/server/services/llm/openrouter) | `pip install "pipecat-ai[openrouter]"` | -| [Perplexity](/server/services/llm/perplexity) | `pip install "pipecat-ai[perplexity]"` | -| [Qwen](/server/services/llm/qwen) | `pip install "pipecat-ai[qwen]"` | -| [SambaNova](/server/services/llm/sambanova) | `pip install "pipecat-ai[sambanova]"` | -| [Sarvam](/server/services/llm/sarvam) | `pip install "pipecat-ai[sarvam]"` | -| [Together AI](/server/services/llm/together) | `pip install "pipecat-ai[together]"` | - -## Text-to-Speech - -Text-to-Speech services receive text input and output audio streams or chunks. - -| Service | Setup | -| ------------------------------------------------- | ---------------------------------------- | -| [Async](/server/services/tts/asyncai) | `pip install "pipecat-ai[asyncai]"` | -| [AWS Polly](/server/services/tts/aws) | `pip install "pipecat-ai[aws]"` | -| [Azure](/server/services/tts/azure) | `pip install "pipecat-ai[azure]"` | -| [Camb AI](/server/services/tts/camb) | `pip install "pipecat-ai[camb]"` | -| [Cartesia](/server/services/tts/cartesia) | `pip install "pipecat-ai[cartesia]"` | -| [Deepgram](/server/services/tts/deepgram) | `pip install "pipecat-ai[deepgram]"` | -| [ElevenLabs](/server/services/tts/elevenlabs) | `pip install "pipecat-ai[elevenlabs]"` | -| [Fish](/server/services/tts/fish) | `pip install "pipecat-ai[fish]"` | -| [Google](/server/services/tts/google) | `pip install "pipecat-ai[google]"` | -| [Gradium](/server/services/tts/gradium) | `pip install "pipecat-ai[gradium]"` | -| [Groq](/server/services/tts/groq) | `pip install "pipecat-ai[groq]"` | -| [Hume](/server/services/tts/hume) | `pip install "pipecat-ai[hume]"` | -| [Inworld](/server/services/tts/inworld) | No dependencies required | -| [Kokoro](/server/services/tts/kokoro) | `pip install "pipecat-ai[kokoro]"` | -| [LMNT](/server/services/tts/lmnt) | `pip install "pipecat-ai[lmnt]"` | -| [MiniMax](/server/services/tts/minimax) | No dependencies required | -| [Neuphonic](/server/services/tts/neuphonic) | `pip install "pipecat-ai[neuphonic]"` | -| [NVIDIA](/server/services/tts/nvidia) | `pip install "pipecat-ai[nvidia]"` | -| [OpenAI](/server/services/tts/openai) | `pip install "pipecat-ai[openai]"` | -| [Piper](/server/services/tts/piper) | No dependencies required | -| [ResembleAI](/server/services/tts/resembleai) | `pip install "pipecat-ai[resembleai]"` | -| [Rime](/server/services/tts/rime) | `pip install "pipecat-ai[rime]"` | -| [Sarvam](/server/services/tts/sarvam) | No dependencies required | -| [Smallest AI](/server/services/tts/smallest) | `pip install "pipecat-ai[smallest]"` | -| [Speechmatics](/server/services/tts/speechmatics) | `pip install "pipecat-ai[speechmatics]"` | -| [xAI](/server/services/tts/xai) | `pip install "pipecat-ai[xai]"` | -| [XTTS](/server/services/tts/xtts) | `pip install "pipecat-ai[xtts]"` | - -## Speech-to-Speech - -Speech-to-Speech services are multi-modal LLM services that take in audio, video, or text and output audio or text. - -| Service | Setup | -| ---------------------------------------------------------------- | ------------------------------------------ | -| [AWS Nova Sonic](/server/services/s2s/aws) | `pip install "pipecat-ai[aws-nova-sonic]"` | -| [Gemini Live](/server/services/s2s/gemini-live) | `pip install "pipecat-ai[google]"` | -| [Gemini Live Vertex AI](/server/services/s2s/gemini-live-vertex) | `pip install "pipecat-ai[google]"` | -| [Grok Voice Agent](/server/services/s2s/grok) | `pip install "pipecat-ai[grok]"` | -| [OpenAI Realtime](/server/services/s2s/openai) | `pip install "pipecat-ai[openai]"` | -| [Ultravox](/server/services/s2s/ultravox) | `pip install "pipecat-ai[ultravox]"` | - -## Image Generation - -Image generation services receive text inputs and output images. - -| Service | Setup | -| -------------------------------------------------- | ---------------------------------- | -| [Azure](/server/services/image-generation/azure) | `pip install "pipecat-ai[azure]"` | -| [fal](/server/services/image-generation/fal) | `pip install "pipecat-ai[fal]"` | -| [Google](/server/services/image-generation/google) | `pip install "pipecat-ai[google]"` | -| [OpenAI](/server/services/image-generation/openai) | `pip install "pipecat-ai[openai]"` | - -## Video - -Video services enable you to build an avatar where audio and video are synchronized. - -| Service | Setup | -| --------------------------------------- | ---------------------------------- | -| [HeyGen](/server/services/video/heygen) | `pip install "pipecat-ai[heygen]"` | -| [Simli](/server/services/video/simli) | `pip install "pipecat-ai[simli]"` | -| [Tavus](/server/services/video/tavus) | `pip install "pipecat-ai[tavus]"` | - -## Memory - -Memory services can be used to store and retrieve conversations. - -| Service | Setup | -| ------------------------------------ | -------------------------------- | -| [mem0](/server/services/memory/mem0) | `pip install "pipecat-ai[mem0]"` | - -## Vision - -Vision services receive a streaming video input and output text describing the video input. - -| Service | Setup | -| ---------------------------------------------- | ------------------------------------- | -| [Moondream](/server/services/vision/moondream) | `pip install "pipecat-ai[moondream]"` | - -## Analytics & Monitoring - -Analytics services help you better understand how your service operates. - -| Service | Setup | -| ------------------------------------------- | ---------------------------------- | -| [Sentry](/server/services/analytics/sentry) | `pip install "pipecat-ai[sentry]"` |