# # Copyright (c) 2024–2025, Daily # # SPDX-License-Identifier: BSD 2-Clause License # import asyncio import os import sys 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.tts import CartesiaTTSService from pipecat.services.openai.llm import OpenAILLMService from pipecat.transports.services.daily import DailyParams, DailyTransport load_dotenv(override=True) logger.remove(0) logger.add(sys.stderr, level="DEBUG") async def main(room_url: str, token: str): transport = DailyTransport( room_url, token, "bot", DailyParams( audio_out_enabled=True, transcription_enabled=True, vad_enabled=True, vad_analyzer=SileroVADAnalyzer(), ), ) tts = CartesiaTTSService( api_key=os.getenv("CARTESIA_API_KEY", ""), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121" ) llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY")) 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(), context_aggregator.user(), llm, tts, transport.output(), context_aggregator.assistant(), ] ) task = PipelineTask( pipeline, params=PipelineParams( allow_interruptions=True, enable_metrics=True, enable_usage_metrics=True, report_only_initial_ttfb=True, ), ) @transport.event_handler("on_first_participant_joined") async def on_first_participant_joined(transport, participant): await transport.capture_participant_transcription(participant["id"]) 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) def _voice_bot_process(room_url: str, token: str): asyncio.run(main(room_url, token))