LiveKit Cloud Plugin: Zero-GPU Avatar Setup

import asyncio
import os
from livekit.agents import (
    Agent,
    AgentSession,
    JobContext,
    RoomOutputOptions,
    WorkerOptions,
    cli,
    llm,
)
from livekit.plugins import openai, silero, bithuman

class MyAgent(Agent):
    def __init__(self):
        super().__init__(
            instructions="""You are a friendly assistant.
            Keep responses to 1-2 sentences.""",
        )

async def entrypoint(ctx: JobContext):
    # Connect to the LiveKit room
    await ctx.connect()

    # Wait for a human to join
    await ctx.wait_for_participant()

    # Create a cloud-hosted avatar
    avatar = bithuman.AvatarSession(
        avatar_id=os.getenv("BITHUMAN_AGENT_ID"),
        api_secret=os.getenv("BITHUMAN_API_SECRET"),
    )

    # Wire up the AI pipeline
    session = AgentSession(
        stt=openai.STT(),              # Listens to the user
        llm=openai.LLM(),              # Generates responses
        tts=openai.TTS(),              # Converts text to speech
        vad=silero.VAD.load(),         # Detects when user is speaking
    )

    # Start — avatar joins room and begins animating
    await avatar.start(session, room=ctx.room)

    await session.start(
        agent=MyAgent(),
        room=ctx.room,
        room_output_options=RoomOutputOptions(audio_enabled=False),
    )

if __name__ == "__main__":
    cli.run_app(WorkerOptions(entrypoint_fnc=entrypoint))

python agent.py dev

avatar = bithuman.AvatarSession(
    avatar_id="A78WKV4515",
    api_secret="your_api_secret",
)

avatar = bithuman.AvatarSession(
    avatar_id="A78WKV4515",
    api_secret="your_api_secret",
    model="expression",
)

from PIL import Image

avatar = bithuman.AvatarSession(
    avatar_image=Image.open("face.jpg"),
    api_secret="your_api_secret",
    model="expression",
)