A simple implementation of a Realtime Agent using LiveKit.

realtime_agent.py

from __future__ import annotations
import logging
from livekit import rtc
from livekit.agents import (
    AutoSubscribe,
    JobContext,
    WorkerOptions,
    cli,
    llm,
)

from livekit.agents.multimodal import MultimodalAgent
from livekit.plugins import openai
logger = logging.getLogger("myagent")
logger.setLevel(logging.INFO)

async def entrypoint(ctx: JobContext):
    logger.info("starting entrypoint")
    await ctx.connect(auto_subscribe=AutoSubscribe.AUDIO_ONLY)
    participant = await ctx.wait_for_participant()
    model = openai.realtime.RealtimeModel(
        instructions="You are a helpful assistant and you love kittens",
        voice="shimmer",
        temperature=0.8,
        modalities=["audio", "text"],
    )

    assistant = MultimodalAgent(model=model)
    assistant.start(ctx.room)
    logger.info("starting agent")
    session = model.sessions[0]
    session.conversation.item.create(
      llm.ChatMessage(
        role="user",
        content="Please begin the interaction with the user in a manner consistent with your instructions.",
      )
    )
    session.response.create()

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