pipecat/examples/foundational/11-sound-effects.py

#
# Copyright (c) 2024–2025, Daily
#
# SPDX-License-Identifier: BSD 2-Clause License
#

import os
import wave

from dotenv import load_dotenv
from loguru import logger

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import (
    Frame,
    LLMFullResponseEndFrame,
    OutputAudioRawFrame,
    TTSSpeakFrame,
)
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.openai_llm_context import (
    OpenAILLMContext,
    OpenAILLMContextFrame,
)
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
from pipecat.processors.logger import FrameLogger
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.network.fastapi_websocket import FastAPIWebsocketParams
from pipecat.transports.services.daily import DailyParams

load_dotenv(override=True)


sounds = {}
sound_files = ["ding1.wav", "ding2.wav"]

script_dir = os.path.dirname(__file__)

for file in sound_files:
    # Build the full path to the image file
    full_path = os.path.join(script_dir, "assets", file)
    # Get the filename without the extension to use as the dictionary key
    filename = os.path.splitext(os.path.basename(full_path))[0]
    # Open the image and convert it to bytes
    with wave.open(full_path) as audio_file:
        sounds[file] = OutputAudioRawFrame(
            audio_file.readframes(-1), audio_file.getframerate(), audio_file.getnchannels()
        )


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

        if isinstance(frame, LLMFullResponseEndFrame):
            await self.push_frame(sounds["ding1.wav"])
            # In case anything else downstream needs it
            await self.push_frame(frame, direction)
        else:
            await self.push_frame(frame, direction)


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

        if isinstance(frame, OpenAILLMContextFrame):
            await self.push_frame(sounds["ding2.wav"])
            # In case anything else downstream needs it
            await self.push_frame(frame, direction)
        else:
            await self.push_frame(frame, direction)


# 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,
        vad_analyzer=SileroVADAnalyzer(),
    ),
    "twilio": lambda: FastAPIWebsocketParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        vad_analyzer=SileroVADAnalyzer(),
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        vad_analyzer=SileroVADAnalyzer(),
    ),
}


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

    stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))

    llm = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))

    tts = CartesiaTTSService(
        api_key=os.getenv("CARTESIA_API_KEY"),
        voice_id="71a7ad14-091c-4e8e-a314-022ece01c121",  # British Reading Lady
    )

    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. Respond to what the user said in a creative and helpful way.",
        },
    ]

    context = OpenAILLMContext(messages)
    context_aggregator = llm.create_context_aggregator(context)
    out_sound = OutboundSoundEffectWrapper()
    in_sound = InboundSoundEffectWrapper()
    fl = FrameLogger("LLM Out")
    fl2 = FrameLogger("Transcription In")

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            context_aggregator.user(),
            in_sound,
            fl2,
            llm,
            fl,
            tts,
            out_sound,
            transport.output(),
            context_aggregator.assistant(),
        ]
    )

    task = PipelineTask(
        pipeline,
        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_frame(TTSSpeakFrame("Hi, I'm listening!"))
        await transport.send_audio(sounds["ding1.wav"])

    @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()