deepgram-flux-agent.py

import logging

from dotenv import load_dotenv

from livekit.agents import (
    Agent,
    AgentSession,
    JobContext,
    WorkerOptions,
    cli,
)
from livekit.plugins import deepgram, silero

logger = logging.getLogger("flux-agent")

load_dotenv()


class MyAgent(Agent):
    def __init__(self) -> None:
        super().__init__(
            instructions="Your name is Flux. You would interact with users via voice."
            "with that in mind keep your responses concise and to the point."
            "do not use emojis, asterisks, markdown, or other special characters in your responses."
            "You are curious and friendly, and have a sense of humor."
            "you will speak english to the user",
        )

    async def on_enter(self):
        # when the agent is added to the session, it'll generate a reply
        # according to its instructions
        self.session.generate_reply(instructions="introduce yourself to the user")


async def entrypoint(ctx: JobContext):
    # each log entry will include these fields
    ctx.log_context_fields = {
        "room": ctx.room.name,
    }

    session = AgentSession(
        # a VAD for the best interruption handling
        # Flux also has VAD builtin, so you can try disabling this
        vad=silero.VAD.load(),
        llm="openai/gpt-4.1",
        stt=deepgram.STTv2(model="flux-general-en", eager_eot_threshold=0.4),
        tts="cartesia/sonic-2",
        # allow the LLM to generate a response while waiting for the end of turn
        # this works with Flux's EagerEndOfTurn events to start LLM generation earlier
        preemptive_generation=True,
        # sometimes background noise could interrupt the agent session, these are considered false positive interruptions
        # when it's detected, you may resume the agent's speech
        resume_false_interruption=True,
    )

    await session.start(
        agent=MyAgent(),
        room=ctx.room,
    )


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

whats the version of livekit that supports this

whats the version of livekit that supports this

+1