pipecat/examples/getting-started/05-speaking-state.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 PIL import Image

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
    BotStartedSpeakingFrame,
    BotStoppedSpeakingFrame,
    Frame,
    LLMRunFrame,
    OutputImageRawFrame,
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.worker import PipelineParams, PipelineWorker
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
    LLMContextAggregatorPair,
    LLMUserAggregatorParams,
)
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.cartesia.tts import CartesiaTTSService
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.transports.daily.transport import DailyParams

load_dotenv(override=True)


class ImageSyncAggregator(FrameProcessor):
    def __init__(self, speaking_path: str, waiting_path: str):
        super().__init__()
        self._speaking_image = Image.open(speaking_path)
        self._speaking_image_format = self._speaking_image.format
        self._speaking_image_bytes = self._speaking_image.tobytes()

        self._waiting_image = Image.open(waiting_path)
        self._waiting_image_format = self._waiting_image.format
        self._waiting_image_bytes = self._waiting_image.tobytes()

    async def process_frame(self, frame: Frame, direction: FrameDirection):
        await super().process_frame(frame, direction)

        if isinstance(frame, BotStartedSpeakingFrame):
            await self.push_frame(
                OutputImageRawFrame(
                    image=self._speaking_image_bytes,
                    size=(1024, 1024),
                    format=self._speaking_image_format,
                )
            )

        elif isinstance(frame, BotStoppedSpeakingFrame):
            await self.push_frame(
                OutputImageRawFrame(
                    image=self._waiting_image_bytes,
                    size=(1024, 1024),
                    format=self._waiting_image_format,
                )
            )

        await self.push_frame(frame, direction)


# 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,
        video_out_enabled=True,
        video_out_width=1024,
        video_out_height=1024,
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        video_out_enabled=True,
        video_out_width=1024,
        video_out_height=1024,
    ),
}


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

    stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])

    tts = CartesiaTTSService(
        api_key=os.environ["CARTESIA_API_KEY"],
        settings=CartesiaTTSService.Settings(
            voice="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
        ),
    )

    llm = OpenAILLMService(
        api_key=os.environ["OPENAI_API_KEY"],
        settings=OpenAILLMService.Settings(
            system_instruction="You are a helpful assistant in a voice conversation. Your responses will be spoken aloud, so avoid emojis, bullet points, or other formatting that can't be spoken. Respond to what the user said in a creative, helpful, and brief way.",
        ),
    )

    context = LLMContext()
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(vad_analyzer=SileroVADAnalyzer()),
    )

    image_sync_aggregator = ImageSyncAggregator(
        os.path.join(os.path.dirname(__file__), "..", "assets", "speaking.png"),
        os.path.join(os.path.dirname(__file__), "..", "assets", "waiting.png"),
    )

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

    worker = PipelineWorker(
        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 worker.queue_frames([LLMRunFrame()])

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

    runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
    await runner.run(worker)


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()