# # Copyright (c) 2024–2025, Daily # # SPDX-License-Identifier: BSD 2-Clause License # import asyncio import os import sys import aiohttp from dotenv import load_dotenv from loguru import logger from runner import configure from pipecat.audio.vad.silero import SileroVADAnalyzer from pipecat.audio.vad.vad_analyzer import VADParams 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.gemini_multimodal_live.gemini import ( GeminiMultimodalLiveLLMService, GeminiMultimodalModalities, InputParams, ) from pipecat.transports.services.daily import DailyParams, DailyTransport load_dotenv(override=True) logger.remove(0) logger.add(sys.stderr, level="DEBUG") SYSTEM_INSTRUCTION = f""" "You are Gemini Chatbot, a friendly, helpful robot. 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. Keep your responses brief. One or two sentences at most. """ async def main(): async with aiohttp.ClientSession() as session: (room_url, token) = await configure(session) transport = DailyTransport( room_url, token, "Respond bot", DailyParams( audio_out_enabled=True, vad_enabled=True, vad_audio_passthrough=True, # set stop_secs to something roughly similar to the internal setting # of the Multimodal Live api, just to align events. This doesn't really # matter because we can only use the Multimodal Live API's phrase # endpointing, for now. vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.5)), ), ) llm = GeminiMultimodalLiveLLMService( api_key=os.getenv("GOOGLE_API_KEY"), transcribe_user_audio=True, transcribe_model_audio=True, system_instruction=SYSTEM_INSTRUCTION, tools=[{"google_search": {}}, {"code_execution": {}}], params=InputParams(modalities=GeminiMultimodalModalities.TEXT), ) # Optionally, you can set the response modalities via a function # llm.set_model_modalities( # GeminiMultimodalModalities.TEXT # ) tts = CartesiaTTSService( api_key=os.getenv("CARTESIA_API_KEY"), voice_id="71a7ad14-091c-4e8e-a314-022ece01c121" ) messages = [ { "role": "user", "content": 'Start by saying "Hello, I\'m Gemini".', }, ] # Set up conversation context and management # The context_aggregator will automatically collect conversation context 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, ), ) @transport.event_handler("on_first_participant_joined") async def on_first_participant_joined(transport, participant): await transport.capture_participant_transcription(participant["id"]) await task.queue_frames([context_aggregator.user().get_context_frame()]) @transport.event_handler("on_participant_left") async def on_participant_left(transport, participant, reason): print(f"Participant left: {participant}") await task.cancel() runner = PipelineRunner() await runner.run(task) if __name__ == "__main__": asyncio.run(main())