Bot Audio Out Cracking and Missing Frames

[skelleex]

When using ElevenLabs it seems that audio is cracking and dropping frames. Is there anyway to stop this from happening? The code used is below my only difference is that I have the FrameLogger enabled for logging. Running on Replit but not a deployment.

`import asyncio import aiohttp import os import sys

from pipecat.frames.frames import LLMMessagesFrame from pipecat.pipeline.pipeline import Pipeline from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.task import PipelineParams, PipelineTask from pipecat.processors.aggregators.llm_response import ( LLMAssistantResponseAggregator, LLMUserResponseAggregator) from pipecat.services.elevenlabs import ElevenLabsTTSService from pipecat.services.openai import OpenAILLMService from pipecat.transports.services.daily import DailyParams, DailyTransport from pipecat.vad.silero import SileroVADAnalyzer

from runner import configure

from loguru import logger

from dotenv import load_dotenv load_dotenv(override=True)

logger.remove(0) logger.add(sys.stderr, level="DEBUG")

async def main(room_url: str, token): async with aiohttp.ClientSession() as session: transport = DailyTransport( room_url, token, "Respond bot", DailyParams( audio_out_enabled=True, transcription_enabled=True, vad_enabled=True, vad_analyzer=SileroVADAnalyzer() ) )

    tts = ElevenLabsTTSService(
        aiohttp_session=session,
        api_key=os.getenv("ELEVENLABS_API_KEY"),
        voice_id=os.getenv("ELEVENLABS_VOICE_ID"),
    )

    llm = OpenAILLMService(
        api_key=os.getenv("OPENAI_API_KEY"),
        model="gpt-4o")

    messages = [
        {
            "role": "system",
            "content": "You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities in a succinct way. Your output will be converted to audio so don't include special characters in your answers. Respond to what the user said in a creative and helpful way.",
        },
    ]

    tma_in = LLMUserResponseAggregator(messages)
    tma_out = LLMAssistantResponseAggregator(messages)

    pipeline = Pipeline([
        transport.input(),   # Transport user input
        tma_in,              # User responses
        llm,                 # LLM
        tts,                 # TTS
        transport.output(),  # Transport bot output
        tma_out              # Assistant spoken responses
    ])

    task = PipelineTask(pipeline, PipelineParams(
        allow_interruptions=True,
        enable_metrics=True,
        report_only_initial_ttfb=True,
    ))

    @transport.event_handler("on_first_participant_joined")
    async def on_first_participant_joined(transport, participant):
        transport.capture_participant_transcription(participant["id"])
        # Kick off the conversation.
        messages.append(
            {"role": "system", "content": "Please introduce yourself to the user."})
        await task.queue_frames([LLMMessagesFrame(messages)])

    runner = PipelineRunner()

    await runner.run(task)

if name == "main": (url, token) = configure() asyncio.run(main(url, token))`