pipecat/examples/foundational/07n-interruptible-gemini-image.py

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

"""
A conversational AI bot using Gemini for both LLM, STT and TTS.

This example demonstrates how to use Gemini's image generation capabilities.

Features showcased:
- Gemini LLM for conversation and image generation
- Google TTS and STT

Run with:
    python examples/foundational/07n-interruptible-gemini-image.py

Make sure to set your environment variables:
    export GOOGLE_API_KEY=your_api_key_here
"""

import os

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
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 (
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.google.llm import GoogleLLMService
from pipecat.services.google.stt import GoogleSTTService
from pipecat.services.google.tts import GoogleTTSService
from pipecat.transcriptions.language import Language
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
from pipecat.turns.user_turn_strategies import UserTurnStrategies

load_dotenv(override=True)

# We store functions so objects (e.g. SileroVADAnalyzer) don't get
# instantiated. The function will be called when the desired transport gets
# selected.
transport_params = {
    "daily": lambda: DailyParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_out_enabled=True,
        video_out_width=1024,
        video_out_height=1024,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_out_enabled=True,
        video_out_width=1024,
        video_out_height=1024,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
}


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

    stt = GoogleSTTService(
        params=GoogleSTTService.InputParams(languages=Language.EN_US),
        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
    )

    tts = GoogleTTSService(
        voice_id="en-US-Chirp3-HD-Charon",
        params=GoogleTTSService.InputParams(language=Language.EN_US),
        credentials=os.getenv("GOOGLE_TEST_CREDENTIALS"),
    )

    llm = GoogleLLMService(
        api_key=os.getenv("GOOGLE_API_KEY"),
        model="gemini-2.5-flash-image",
        # model="gemini-3-pro-image-preview", # A more powerful model, but slower
    )

    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 spoken aloud, so avoid special characters that can't easily be spoken, such as emojis or bullet points. Respond to what the user said in a creative and helpful way.",
        },
    ]

    context = LLMContext(messages)
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            user_turn_strategies=UserTurnStrategies(
                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
            ),
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,  # STT
            user_aggregator,  # User responses
            llm,  # LLM
            tts,  # Gemini TTS
            transport.output(),  # Transport bot output
            assistant_aggregator,  # Assistant spoken responses
        ]
    )

    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 with a styled introduction
        messages.append({"role": "system", "content": "Please introduce yourself to the user."})
        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()

    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()