playground.yaml

# Examples metadata consumed by livekit/agents-jukebox.
#
# Each top-level key under `examples` is the agent name — used as
#   - the directory name under examples/
#   - the LIVEKIT_AGENT_NAME injected at deploy time
#   - the dispatch target in the jukebox's token endpoint
#
# Pixel art icons: `1` = accent color, `2` = lighter accent (highlight
# / secondary detail), `0` = transparent.

version: 1

# All examples deploy to this LiveKit Cloud project. The CI regenerates
# each example's livekit.toml from this subdomain + the per-example
# agent_id below before invoking `lk agent deploy`.
project:
  subdomain: demo-agents-omk31qjj

examples:
  frontdesk:
    title: Front Desk
    description: A receptionist agent wired up to a live calendar. Answers questions about availability, books appointments in real time, and confirms back to the caller.
    # brand palette — indigo-500
    accent: "#1F44F9"
    agent_id: CA_y5MnZwagLJMp
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/frontdesk"
    tags: [tools, scheduling]
    icon:
      # Calendar with the top header strip in the highlight tone.
      size: 12
      pixels: |
        000000000000
        000100010000
        001111111000
        012222222100
        011111111100
        010000000100
        010000000100
        010000000100
        010000000100
        010000000100
        001111111000
        000000000000
    views:
      - rpc: set_appointment_status
        title: "\uf073 Schedule"

  healthcare:
    title: Healthcare
    description: A medical front-desk agent that handles intake, authenticates returning patients, books appointments, and hands the conversation off to a human when it needs to.
    # LiveKit brand palette (raw-colors.ts) — green-500
    accent: "#009E4F"
    agent_id: CA_6xRtj8dRsa6j
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/healthcare"
    tags: [multi-agent, scheduling]
    icon:
      # Heart with a top-left specular highlight on the left lobe.
      size: 12
      pixels: |
        000000000000
        002100011000
        022210111100
        211111111110
        111111111110
        111111111110
        011111111100
        001111111000
        000111110000
        000011100000
        000001000000
        000000000000

  survey:
    title: Survey
    description: A structured interview agent that walks candidates through a software engineer screening flow, captures answers as they go, and writes a graded summary to disk.
    # brand palette — amber-500
    accent: "#EF8B01"
    agent_id: CA_jWtLpVb87Xwx
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/survey"
    tags: [multi-agent]
    icon:
      # Speech bubble outline with two highlight "text lines" inside.
      size: 12
      pixels: |
        000000000000
        001111111100
        010000000010
        010000000010
        010222200010
        010000000010
        010220000010
        010000000010
        010111111100
        011000000000
        010000000000
        000000000000

  drive_thru:
    title: Drive Thru
    description: A drive-thru ordering agent that takes the order over voice, builds a structured cart with dynamically-generated tools per menu item, and reads back the total.
    # brand palette — red-500
    accent: "#FA4C39"
    agent_id: CA_F8gohFoh4BMw
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/drive_thru"
    tags: [tools]
    icon:
      # Side-view car: cabin pillars in accent, windshield + side
      # windows in the lighter tone, body and wheels in accent.
      size: 12
      pixels: |
        000000000000
        000000000000
        001111110000
        012221221000
        012222111110
        100000000001
        101110011101
        011011110110
        001110011100
        000000000000
        000000000000
        000000000000
    # The playground reads these `views` and renders a read-only
    # markdown card per entry on the right of the orb. The agent fills
    # them at runtime by RPC'ing the matching `id` with a markdown
    # payload — the card stays hidden until the first payload arrives.
    # The agent fills these `views` at runtime by RPC'ing the
    # declared method name (e.g. `set_cart_content`) with a markdown
    # payload. Each entry renders as a card on the right of the orb,
    # hidden until the first non-empty payload, re-hidden on empty.
    views:
      - rpc: set_cart_content
        # Card title is rendered in the body font, which has the
        # FA Solid range merged in — so YAML `\u` escapes for any
        # FA codepoint render inline. `\uf07a` is shopping-cart.
        title: "\uf07a Current order"

  inference:
    title: Inference
    description: A voice agent powered end-to-end by LiveKit Inference. Pick the STT, LLM, and TTS provider live to hear how each one feels in the same conversation.
    # brand palette — purple-500
    accent: "#9B5CFF"
    agent_id: CA_vW8xVewx3AgJ
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/inference"
    tags: [inference]
    icon:
      # Three stacked bars: the STT → LLM → TTS pipeline, with the
      # middle bar in the highlight tone.
      size: 12
      pixels: |
        000000000000
        000000000000
        011111111110
        011111111110
        000000000000
        022222222220
        022222222220
        000000000000
        011111111110
        011111111110
        000000000000
        000000000000
    # The playground reads these `controls` and renders one widget per
    # entry. `type` selects the widget — defaults to `dropdown` for
    # backwards-compat with the other examples. Picking an option fires
    # an RPC on the agent participant: `rpc` is the method name,
    # payload is `{"value": "…"}`. Defaults match the agent's
    # DEFAULT_* constants in agent.py.
    #
    # Supported types:
    #   - dropdown (default): pill with options list
    #   - textarea: multiline string editor. Fires `rpc` with the
    #     current text on every edit-commit (debounced by the FE)
    #     so the agent can apply it live.
    #   - link: a button-styled action. On click fires `rpc` on the
    #     agent (no payload) and opens the returned string as a URL
    #     in a new tab. The agent owns the URL — useful for deep
    #     links into Builder, dashboards, etc. where the params
    #     depend on the agent's current state.
    controls:
      - rpc: set_system_prompt
        type: textarea
        label: System prompt
        # Keep in sync with INSTRUCTIONS in examples/inference/agent.py.
        default: "You're a friendly agent in the LiveKit Playground. The person talking to you is prototyping their own voice agent — they can edit this prompt in the side panel and swap the STT / LLM / TTS models live. Keep replies short, natural, and conversational, and be expressive so they can hear what the selected voice can do. If the conversation lulls or they're not sure what to try, offer to tell them a short joke — and if they say yes, deliver it with good comic timing. If asked which models you're using, answer honestly."
        rows: 8
      - rpc: set_stt_model
        label: STT
        default: deepgram/nova-3
        options:
          - { value: deepgram/nova-3, label: Deepgram Nova-3 }
          - { value: deepgram/nova-3-medical, label: Deepgram Nova-3 Medical }
          - { value: deepgram/flux-general-en, label: Deepgram Flux (English) }
          - { value: deepgram/flux-general-multi, label: Deepgram Flux (Multilingual) }
          - { value: assemblyai/u3-rt-pro, label: AssemblyAI Universal-3 Pro }
          - { value: assemblyai/universal-streaming, label: AssemblyAI Universal-Streaming }
          - { value: assemblyai/universal-streaming-multilingual, label: AssemblyAI Universal-Streaming Multilingual }
          - { value: cartesia/ink-whisper, label: Cartesia Ink Whisper }
          - { value: elevenlabs/scribe_v2_realtime, label: ElevenLabs Scribe v2 Realtime }
          - { value: speechmatics/enhanced, label: Speechmatics Enhanced }
          - { value: speechmatics/standard, label: Speechmatics Standard }
          - { value: xai/stt-1, label: xAI Speech-to-Text }
      - rpc: set_llm_model
        label: LLM
        default: google/gemma-4-31b-it
        options:
          - { value: google/gemma-4-31b-it, label: Gemma 4 31B }
          - { value: openai/gpt-4.1, label: OpenAI GPT-4.1 }
          - { value: openai/gpt-4.1-mini, label: OpenAI GPT-4.1 mini }
          - { value: openai/gpt-4.1-nano, label: OpenAI GPT-4.1 nano }
          - { value: openai/gpt-4o, label: OpenAI GPT-4o }
          - { value: openai/gpt-4o-mini, label: OpenAI GPT-4o mini }
          - { value: openai/gpt-5, label: OpenAI GPT-5 }
          - { value: openai/gpt-5-mini, label: OpenAI GPT-5 mini }
          - { value: openai/gpt-5-nano, label: OpenAI GPT-5 nano }
          - { value: openai/gpt-5.1, label: OpenAI GPT-5.1 }
          - { value: openai/gpt-5.1-chat-latest, label: OpenAI GPT-5.1 Chat }
          - { value: openai/gpt-5.2, label: OpenAI GPT-5.2 }
          - { value: openai/gpt-5.2-chat-latest, label: OpenAI GPT-5.2 Chat }
          - { value: openai/gpt-5.3-chat-latest, label: OpenAI GPT-5.3 Chat }
          - { value: openai/gpt-5.4, label: OpenAI GPT-5.4 }
          - { value: openai/gpt-5.4-mini, label: OpenAI GPT-5.4 mini }
          - { value: openai/gpt-5.4-nano, label: OpenAI GPT-5.4 nano }
          - { value: openai/gpt-5.5, label: OpenAI GPT-5.5 }
          - { value: openai/gpt-oss-120b, label: OpenAI GPT OSS 120B }
          - { value: google/gemini-2.0-flash, label: Gemini 2.0 Flash }
          - { value: google/gemini-2.0-flash-lite, label: Gemini 2.0 Flash-Lite }
          - { value: google/gemini-2.5-flash, label: Gemini 2.5 Flash }
          - { value: google/gemini-2.5-flash-lite, label: Gemini 2.5 Flash-Lite }
          - { value: google/gemini-2.5-pro, label: Gemini 2.5 Pro }
          - { value: google/gemini-3-flash-preview, label: Gemini 3 Flash }
          - { value: google/gemini-3-pro-preview, label: Gemini 3 Pro }
          - { value: google/gemini-3.1-flash-lite, label: Gemini 3.1 Flash Lite }
          - { value: google/gemini-3.1-pro-preview, label: Gemini 3.1 Pro }
          - { value: xai/grok-4-1-fast-non-reasoning, label: Grok 4.1 Fast }
          - { value: xai/grok-4-1-fast-reasoning, label: Grok 4.1 Fast Reasoning }
          - { value: xai/grok-4.20-0309-non-reasoning, label: Grok 4.20 }
          - { value: xai/grok-4.20-0309-reasoning, label: Grok 4.20 Reasoning }
          - { value: xai/grok-4.20-multi-agent-0309, label: Grok 4.20 Multi-Agent }
          - { value: xai/grok-4.3, label: Grok 4.3 }
          - { value: xai/grok-4.5, label: Grok 4.5 }
          - { value: deepseek-ai/deepseek-v3, label: DeepSeek-V3 }
          - { value: deepseek-ai/deepseek-v3.1, label: DeepSeek-V3.1 }
          - { value: deepseek-ai/deepseek-v3.2, label: DeepSeek-V3.2 }
          - { value: moonshotai/kimi-k2-instruct, label: Kimi K2 Instruct }
          - { value: moonshotai/kimi-k2.5, label: Kimi K2.5 }
      - rpc: set_tts_model
        label: TTS
        default: inworld/inworld-tts-2
        options:
          - { value: cartesia/sonic, label: Cartesia Sonic }
          - { value: cartesia/sonic-2, label: Cartesia Sonic-2 }
          - { value: cartesia/sonic-3, label: Cartesia Sonic-3 }
          - { value: cartesia/sonic-3-latest, label: Cartesia Sonic-3 Latest }
          - { value: cartesia/sonic-turbo, label: Cartesia Sonic Turbo }
          - { value: deepgram/aura, label: Deepgram Aura }
          - { value: deepgram/aura-2, label: Deepgram Aura-2 }
          - { value: elevenlabs/eleven_flash_v2, label: ElevenLabs Flash v2 }
          - { value: elevenlabs/eleven_flash_v2_5, label: ElevenLabs Flash v2.5 }
          - { value: elevenlabs/eleven_multilingual_v2, label: ElevenLabs Multilingual v2 }
          - { value: elevenlabs/eleven_turbo_v2, label: ElevenLabs Turbo v2 }
          - { value: elevenlabs/eleven_turbo_v2_5, label: ElevenLabs Turbo v2.5 }
          - { value: elevenlabs/eleven_v3, label: ElevenLabs v3 }
          - { value: inworld/inworld-tts-1, label: Inworld TTS 1 }
          - { value: inworld/inworld-tts-1-max, label: Inworld TTS 1 Max }
          - { value: inworld/inworld-tts-1.5-mini, label: Inworld TTS 1.5 Mini }
          - { value: inworld/inworld-tts-1.5-max, label: Inworld TTS 1.5 Max }
          - { value: inworld/inworld-tts-2, label: Inworld TTS 2 }
          - { value: rime/coda, label: Rime Coda }
          - { value: rime/mist, label: Rime Mist }
          - { value: rime/mistv2, label: Rime Mist v2 }
          - { value: rime/mistv3, label: Rime Mist v3 }
          - { value: xai/tts-1, label: xAI Text-to-Speech }
      # "Open in Builder" CTA. `type: link` fires `rpc` on the agent
      # and opens the returned string as a URL in a new tab. The
      # agent (examples/inference/agent.py :: open_in_builder) reads
      # its current instructions + STT/LLM/TTS model strings and
      # builds the Cloud Builder deep-link from there, so the
      # frontend doesn't have to know the schema.
      - rpc: open_in_builder
        type: link
        label: "Open in Builder \u2192"
        primary: true
    # Live conversation transcript. The agent doesn't push to this view
    # by RPC the way other examples push markdown cards — the frontend
    # subscribes to LiveKit `TranscriptionReceived` events and renders
    # both sides of the conversation as text. `source: transcript` is
    # the trigger; `rpc` is a sentinel value and isn't actually called.
    views:
      - rpc: __transcript
        source: transcript
        title: "\uf075 Transcript"

  hotel_receptionist:
    title: Hotel Receptionist
    description: A hotel front-desk agent that books rooms and restaurant reservations, modifies and verifies existing bookings, and confirms guest details — all backed by a live database.
    # brand palette — teal-500
    accent: "#14B8A6"
    agent_id: CA_4svEd8aaowSr
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/hotel_receptionist"
    tags: [multi-agent, tools]
    icon:
      # Concierge service bell: domed bell with a top-left specular
      # highlight, sitting on a full-width base plate.
      size: 12
      pixels: |
        000000000000
        000000000000
        000001100000
        000011110000
        000221111000
        002211111100
        011111111110
        011111111110
        111111111111
        000000000000
        000000000000
        000000000000

  avatar:
    title: Avatar
    description: Talk to a LemonSlice avatar. Pick anyone from the dropdown to swap who you're chatting with, from Leila to a Pixar fox.
    # LemonSlice brand \u2014 yellow-500 from the LK palette.
    accent: "#F9E71F"
    agent_id: CA_hj4mhpfNt47i
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/avatar"
    tags: [avatar, video, multi-persona]
    # Tells the jukebox frontend to render the AvatarFrame and drive
    # the connect-time orb \u2192 video reveal animation. Without this
    # flag the example renders like every other one (orb only).
    avatar: true
    icon:
      # Head + shoulders. Head is filled with '2' (highlight tone) and
      # the shoulders are '1' (full accent), so the two regions read as
      # two distinct shades instead of a single blob.
      size: 12
      pixels: |
        000000000000
        000022220000
        000222222000
        002222222200
        002222222200
        002222222200
        000222222000
        000022220000
        000000000000
        001111111100
        011111111110
        111111111111
    # The playground reads these `controls` and renders one widget
    # per entry. The persona dropdown fires `set_avatar` on the
    # agent with the chosen id as the payload value. The agent
    # updates voice + system prompt live; the avatar image stays
    # on the current persona until the session reconnects.
    controls:
      - rpc: set_avatar
        label: Persona
        default: leila
        options:
          - { value: leila, label: Leila }
          - { value: jess, label: Jess }
          - { value: software_engineer, label: Software Engineer }
          - { value: social_worker, label: Social Worker }
          - { value: ai_therapist, label: AI Therapist }
          - { value: management_consultant, label: Management Consultant }
          - { value: shopping_assistant, label: Shopping Assistant }
          - { value: cat_girl, label: Cat Girl }
          - { value: mr_fox, label: Mr Fox }

  expressive_agent:
    title: Expressive
    description: A free-form companion agent running Expressive Mode. Tell it good news or bad news and hear the delivery change — emotion, pacing, and non-verbal sounds, all chosen from context.
    # brand palette — cyan-500
    accent: "#1FD5F9"
    agent_id: CA_LdKBYTBXNNt9
    entry: agent.py
    github: "https://github.com/livekit/agents/tree/main/examples/expressive_agent"
    tags: [expressive, inference]
    icon:
      # Sound wave rising then falling, with the tall centre bars in the
      # highlight tone: quiet, loud, quiet — the shape of a spoken phrase.
      size: 12
      pixels: |
        000000000000
        000000000000
        000001100000
        000012210000
        000122221000
        001222222100
        001222222100
        000122221000
        000012210000
        000001100000
        000000000000
        000000000000