LiveKit 통합

pip install "livekit-agents" "livekit-api" "elevenlabs" "aiohttp" "python-dotenv"

from elevenlabs import AsyncElevenLabs
elevenlabs = AsyncElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"])
async def signed_url() -> str:
    response = await elevenlabs.conversational_ai.conversations.get_signed_url(
        agent_id=os.environ["SPEECH_ENGINE_ID"],
    )
    return response.signed_url

import asyncio
import base64
import json
import os
import aiohttp
from dotenv import load_dotenv
from elevenlabs import AsyncElevenLabs
from livekit import agents, rtc
from livekit.agents import JobContext, WorkerOptions, cli
load_dotenv()
elevenlabs = AsyncElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"])
SPEECH_ENGINE_ID = os.environ["SPEECH_ENGINE_ID"]
USER_INPUT_RATE = 16000
AGENT_OUTPUT_RATE = 24000
async def signed_url() -> str:
    response = await elevenlabs.conversational_ai.conversations.get_signed_url(
        agent_id=SPEECH_ENGINE_ID,
    )
    return response.signed_url
async def entrypoint(ctx: JobContext):
    el_ws_ready: asyncio.Future[aiohttp.ClientWebSocketResponse] = (
        asyncio.get_running_loop().create_future()
    )
    async def pump_user_audio(track: rtc.Track):
        el_ws = await el_ws_ready
        stream = rtc.AudioStream(
            track, sample_rate=USER_INPUT_RATE, num_channels=1,
        )
        async for event in stream:
            payload = base64.b64encode(bytes(event.frame.data)).decode()
            await el_ws.send_str(json.dumps({"user_audio_chunk": payload}))
    # Register the subscriber BEFORE ctx.connect() so we don't miss tracks
    # that get auto-subscribed during the connection handshake.
    @ctx.room.on("track_subscribed")
    def on_track_subscribed(track, publication, participant):
        if track.kind != rtc.TrackKind.KIND_AUDIO:
            return
        if participant.identity == ctx.room.local_participant.identity:
            return
        asyncio.create_task(pump_user_audio(track))
    await ctx.connect()
    # Publish a track for the agent's synthesized audio.
    source = rtc.AudioSource(sample_rate=AGENT_OUTPUT_RATE, num_channels=1)
    track = rtc.LocalAudioTrack.create_audio_track("elevenlabs-agent", source)
    await ctx.room.local_participant.publish_track(
        track,
        rtc.TrackPublishOptions(source=rtc.TrackSource.SOURCE_MICROPHONE),
    )
    # Open the Speech Engine conversation WebSocket.
    http = aiohttp.ClientSession()
    el_ws = await http.ws_connect(await signed_url())
    await el_ws.send_str(json.dumps({"type": "conversation_initiation_client_data"}))
    el_ws_ready.set_result(el_ws)
    async def el_to_room():
        async for msg in el_ws:
            if msg.type != aiohttp.WSMsgType.TEXT:
                continue
            event = json.loads(msg.data)
            etype = event.get("type")
            if etype == "audio":
                pcm = base64.b64decode(event["audio_event"]["audio_base_64"])
                samples_per_channel = len(pcm) // 2
                frame = rtc.AudioFrame(
                    pcm, AGENT_OUTPUT_RATE, 1, samples_per_channel,
                )
                await source.capture_frame(frame)
            elif etype == "interruption":
                source.clear_queue()
            elif etype == "ping":
                event_id = event.get("ping_event", {}).get("event_id")
                await el_ws.send_str(json.dumps({
                    "type": "pong", "event_id": event_id,
                }))
    pump_task = asyncio.create_task(el_to_room())
    async def cleanup():
        pump_task.cancel()
        await el_ws.close()
        await http.close()
    ctx.add_shutdown_callback(cleanup)
if __name__ == "__main__":
    cli.run_app(WorkerOptions(
        entrypoint_fnc=entrypoint,
        agent_name="elevenlabs-bridge",
    ))

python bridge.py dev