pipecat/examples/realtime/realtime-gemini-live-local-vad.py

#
# Copyright (c) 2024-2026, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#


import os

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import LLMRunFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineParams, PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
    AssistantTurnStoppedMessage,
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
    UserMessageFinalizedMessage,
    UserTurnStoppedMessage,
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.gemini_live.llm import GeminiLiveLLMService, GeminiVADParams
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams

load_dotenv(override=True)


# We use lambdas to defer transport parameter creation until the transport
# type is selected at runtime.
transport_params = {
    "daily": lambda: DailyParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "twilio": lambda: FastAPIWebsocketParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
    ),
}


async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    logger.info(f"Starting bot")

    llm = GeminiLiveLLMService(
        api_key=os.environ["GOOGLE_API_KEY"],
        settings=GeminiLiveLLMService.Settings(
            voice="Aoede",  # Puck, Charon, Kore, Fenrir, Aoede
            vad=GeminiVADParams(disabled=True),
        ),
        # inference_on_context_initialization=False,
    )

    context = LLMContext(
        [
            {
                "role": "user",
                "content": "Say hello. Then ask if I want to hear a joke.",
            },
        ],
    )
    # `wait_for_transcript_to_end_user_turn=False` is the right setting
    # for pipelines like this one — local turn detection driving a
    # realtime service. It avoids unnecessary latency from transcript
    # delay: the realtime service consumes user audio directly, so
    # we don't need user transcripts in context before it can respond.
    # With this option:
    #
    # - Turn strategies do not consider user transcripts, so the user
    #   turn ends sooner.
    # - User transcripts are handled by the aggregator: a simple timer
    #   gives it time to gather them after the user turn ends, then
    #   the aggregator emits `on_user_turn_message_finalized` with the
    #   new user context message.
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            vad_analyzer=SileroVADAnalyzer(),
            wait_for_transcript_to_end_user_turn=False,
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),
            user_aggregator,
            llm,
            transport.output(),
            assistant_aggregator,
        ]
    )

    task = PipelineTask(
        pipeline,
        params=PipelineParams(
            enable_metrics=True,
            enable_usage_metrics=True,
        ),
        idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
    )

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        logger.info(f"Client connected")
        # Kick off the conversation.
        await task.queue_frames([LLMRunFrame()])

    @transport.event_handler("on_client_disconnected")
    async def on_client_disconnected(transport, client):
        logger.info(f"Client disconnected")
        await task.cancel()

    # `on_user_turn_stopped` fires at the end of the user turn. With
    # `wait_for_transcript_to_end_user_turn=False`, the aggregator
    # hasn't gathered user transcripts yet at this point, so
    # `message.content` is empty. Logged here to make the end-of-turn
    # signal visible alongside the later finalization event.
    @user_aggregator.event_handler("on_user_turn_stopped")
    async def on_user_turn_stopped(aggregator, strategy, message: UserTurnStoppedMessage):
        logger.info(f"User turn ended (strategy: {type(strategy).__name__})")

    # `on_user_turn_message_finalized` fires when the user message has
    # been finalized into the context. Here it fires later than
    # `on_user_turn_stopped`, after the aggregator has gathered the
    # realtime service's user transcripts.
    @user_aggregator.event_handler("on_user_turn_message_finalized")
    async def on_user_turn_message_finalized(
        aggregator, strategy, message: UserMessageFinalizedMessage
    ):
        timestamp = f"[{message.timestamp}] " if message.timestamp else ""
        line = f"{timestamp}user: {message.content}"
        logger.info(f"Transcript: {line}")

    @assistant_aggregator.event_handler("on_assistant_turn_stopped")
    async def on_assistant_turn_stopped(aggregator, message: AssistantTurnStoppedMessage):
        timestamp = f"[{message.timestamp}] " if message.timestamp else ""
        line = f"{timestamp}assistant: {message.content}"
        logger.info(f"Transcript: {line}")

    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)

    await runner.run(task)


async def bot(runner_args: RunnerArguments):
    """Main bot entry point compatible with Pipecat Cloud."""
    transport = await create_transport(runner_args, transport_params)
    await run_bot(transport, runner_args)


if __name__ == "__main__":
    from pipecat.runner.run import main

    main()