To create a virtual assistant avatar with LiveKit Agent, follow these steps: 1. Choose an avatar provider: Options include Beyond Presence, bitHuman, and Tavus. 2. Install the selected plugin: Set up API keys for your chosen provider. 3. Implement the avatar integration: Use the following basic pattern in your code:

from livekit import agents
from livekit.agents import AgentSession, RoomOutputOptions
from livekit.plugins import tavus  # or your chosen provider

async def entrypoint(ctx: agents.JobContext):
    await ctx.connect()

    session = AgentSession(
        # Configure your STT, LLM, TTS components
    )

    avatar = tavus.AvatarSession(
        replica_id="...",  # Provider-specific configuration
        persona_id="...",
    )

    # Start the avatar and wait for it to join
    await avatar.start(session, room=ctx.room)

    # Start your agent session with audio disabled (avatar handles it)
    await session.start(
        room=ctx.room,
        room_output_options=RoomOutputOptions(
            audio_enabled=False,
        ),
        # Other agent configuration
    )

1. In your frontend: Use the

useVoiceAssistant

hook to display the avatar:

const { state, audioTrack } = useVoiceAssistant();
return (
  <div classname="h-80">
    <barvisualizer state="{state}" barcount="{5}" trackref="{audioTrack}" style="{{}}"/>
    <p classname="text-center">{state}</p>
  </div>
);

1. Handle authentication: Generate a token for your application to connect to LiveKit rooms. The avatar worker joins your LiveKit room as a separate participant to publish synchronized audio and video, creating a more engaging user experience. Sources: Virtual avatar integrations | LiveKit Docs | Web and mobile frontends | LiveKit Docs