Skip to content

Commit eaa4546

Browse files
authored
Update README.md with Agents block (#1022)
Added information about LiveKit Agents SDK for Voice AI, including usage examples and links to documentation.
1 parent 923ce1d commit eaa4546

1 file changed

Lines changed: 35 additions & 0 deletions

File tree

‎README.md‎

Lines changed: 35 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -14,6 +14,41 @@
1414
Use this SDK to add realtime video, audio and data features to your Android/Kotlin app. By connecting to <a href="https://livekit.io/">LiveKit</a> Cloud or a self-hosted server, you can quickly build applications such as multi-modal AI, live streaming, or video calls with just a few lines of code.
1515
<!--END_DESCRIPTION-->
1616

17+
<!--BEGIN_AGENTS_INFO-->
18+
> [!IMPORTANT]
19+
> If you're building Voice AI, [LiveKit Agents](https://github.com/livekit/agents) is the SDK for code-first realtime voice agents. STT, LLM, TTS, turn detection, [expressive speech](https://docs.livekit.io/agents/models/tts/expressive/), [keyterm accuracy](https://docs.livekit.io/agents/models/stt/keyterms/), tool usage, and telephony all come bundled in the framework. It's available in both [Python](https://github.com/livekit/agents) and [Node.js](https://github.com/livekit/agents-js).
20+
>
21+
> ```python
22+
> # agent.py
23+
> from livekit import agents
24+
> from livekit.agents import Agent, AgentServer, AgentSession, STTContextOptions, TurnHandlingOptions, inference
25+
>
26+
> server = AgentServer()
27+
>
28+
>
29+
> @server.rtc_session(agent_name="my-agent")
30+
> async def my_agent(ctx: agents.JobContext):
31+
> session = AgentSession(
32+
> stt=inference.STT(model="deepgram/nova-3", language="multi"),
33+
> llm=inference.LLM(model="google/gemma-4-31b-it"),
34+
> tts=inference.TTS(model="inworld/inworld-tts-2", voice="Ashley"),
35+
> turn_handling=TurnHandlingOptions(turn_detection=inference.TurnDetector()),
36+
> stt_context_options=STTContextOptions(keyterms=["LiveKit", "Acme Corp"]),
37+
> expressive=True,
38+
> )
39+
> await session.start(room=ctx.room, agent=Agent(instructions="You are a helpful voice AI assistant."))
40+
> await session.generate_reply(instructions="Greet the user and offer your assistance.")
41+
>
42+
>
43+
> if __name__ == "__main__":
44+
> agents.cli.run_app(server)
45+
> ```
46+
>
47+
> Models come from [LiveKit Inference](https://docs.livekit.io/agents/models/) with no per-provider API keys, and LiveKit Cloud handles [deployment](https://docs.livekit.io/deploy/agents/) and [observability](https://docs.livekit.io/deploy/observability/). Visit the docs for more info at [docs.livekit.io/agents](https://docs.livekit.io/agents/).
48+
>
49+
> Using a coding agent? Install the LiveKit skill with `npx skills add livekit/agent-skills` and add the docs MCP at `https://docs.livekit.io/mcp/` (see [coding agent support](https://docs.livekit.io/intro/coding-agents/)).
50+
<!--END_AGENTS_INFO-->
51+
1752
# Table of Contents
1853
1954
- [Docs](#docs)

0 commit comments

Comments
 (0)