# # Copyright (c) 2024–2025, Daily # # SPDX-License-Identifier: BSD 2-Clause License # import asyncio import os import sys from typing import Any, Mapping import aiohttp from dotenv import load_dotenv from loguru import logger from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.pipeline.pipeline import Pipeline from pipecat.pipeline.runner import PipelineRunner from pipecat.pipeline.task import PipelineParams, PipelineTask from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext from pipecat.services.cartesia import CartesiaTTSService from pipecat.services.deepgram import DeepgramSTTService from pipecat.services.openai import OpenAILLMService from pipecat.services.tavus import TavusVideoService from pipecat.transports.services.daily import DailyParams, DailyTransport load_dotenv(override=True) logger.remove(0) logger.add(sys.stderr, level="DEBUG") async def main(): async with aiohttp.ClientSession() as session: tavus = TavusVideoService( api_key=os.getenv("TAVUS_API_KEY"), replica_id=os.getenv("TAVUS_REPLICA_ID"), session=session, ) # get persona, look up persona_name, set this as the bot name to ignore persona_name = await tavus.get_persona_name() room_url = await tavus.initialize() transport = DailyTransport( room_url=room_url, token=None, bot_name="Pipecat bot", params=DailyParams( vad_enabled=True, vad_analyzer=SileroVADAnalyzer(), vad_audio_passthrough=True, ), ) stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY")) tts = CartesiaTTSService( api_key=os.getenv("CARTESIA_API_KEY"), voice_id="a167e0f3-df7e-4d52-a9c3-f949145efdab", ) llm = OpenAILLMService(model="gpt-4o-mini") 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.", }, ] context = OpenAILLMContext(messages) context_aggregator = llm.create_context_aggregator(context) pipeline = Pipeline( [ transport.input(), # Transport user input stt, # STT context_aggregator.user(), # User responses llm, # LLM tts, # TTS tavus, # Tavus output layer transport.output(), # Transport bot output context_aggregator.assistant(), # Assistant spoken responses ] ) task = PipelineTask( pipeline, params=PipelineParams( # We just use 16000 because that's what Tavus is expecting and # we avoid resampling. audio_in_sample_rate=16000, audio_out_sample_rate=16000, allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True, report_only_initial_ttfb=True, ), ) @transport.event_handler("on_participant_joined") async def on_participant_joined( transport: DailyTransport, participant: Mapping[str, Any] ) -> None: # Ignore the Tavus replica's microphone if participant.get("info", {}).get("userName", "") == persona_name: logger.debug(f"Ignoring {participant['id']}'s microphone") await transport.update_subscriptions( participant_settings={ participant["id"]: { "media": {"microphone": "unsubscribed"}, } } ) if participant.get("info", {}).get("userName", "") != persona_name: # Kick off the conversation. messages.append( {"role": "system", "content": "Please introduce yourself to the user."} ) await task.queue_frames([context_aggregator.user().get_context_frame()]) @transport.event_handler("on_participant_left") async def on_participant_left(transport, participant, reason): await task.cancel() runner = PipelineRunner() await runner.run(task) if __name__ == "__main__": asyncio.run(main())