Pipecat: 创建语音对话agent的开源框架，支持多模态！

# install the modulepip install pipecat-ai
# set up an .env file with API keyscp dot-env.template .env

pip install "pipecat-ai[option,...]"

#app.py
import asyncioimport aiohttp
from pipecat.frames.frames import EndFrame, TextFramefrom pipecat.pipeline.pipeline import Pipelinefrom pipecat.pipeline.task import PipelineTaskfrom pipecat.pipeline.runner import PipelineRunnerfrom pipecat.services.elevenlabs import ElevenLabsTTSServicefrom pipecat.transports.services.daily import DailyParams, DailyTransport
async def main():async with aiohttp.ClientSession() as session:# Use Daily as a real-time media transport (WebRTC)transport = DailyTransport(room_url=...,token=...,"Bot Name",DailyParams(audio_out_enabled=True))
# Use Eleven Labs for Text-to-Speechtts = ElevenLabsTTSService(aiohttp_session=session,api_key=...,voice_id=...,)
# Simple pipeline that will process text to speech and output the resultpipeline = Pipeline([tts, transport.output()])
# Create Pipecat processor that can run one or more pipelines tasksrunner = PipelineRunner()
# Assign the task callable to run the pipelinetask = PipelineTask(pipeline)
# Register an event handler to play audio when a# participant joins the transport WebRTC session@transport.event_handler("on_participant_joined")async def on_new_participant_joined(transport, participant):participant_name = participant["info"]["userName"] or ''# Queue a TextFrame that will get spoken by the TTS service (Eleven Labs)await task.queue_frames([TextFrame(f"Hello there, {participant_name}!"), EndFrame()])
# Run the pipeline taskawait runner.run(task)
if __name__ == "__main__":asyncio.run(main())

python app.py

pip install pipecat-ai[silero]

python3 -m venv venvsource venv/bin/activate

pip install -r dev-requirements.txt -r {env}-requirements.txtpython -m build

pip install --editable .

pytest --doctest-modules --ignore-glob="*to_be_updated*" src tests