pipecat/examples/foundational/44-voicemail-detection.py

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

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.extensions.voicemail.voicemail_detector import VoicemailDetector
from pipecat.frames.frames import TTSSpeakFrame
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.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
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,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
    "twilio": lambda: FastAPIWebsocketParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
    "webrtc": lambda: TransportParams(
        audio_in_enabled=True,
        audio_out_enabled=True,
        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
    ),
}


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

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

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

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

    voicemail = VoicemailDetector(llm=classifier_llm)

    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)
    context_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            user_turn_strategies=UserTurnStrategies(
                stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
            ),
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            voicemail.detector(),  # Voicemail detection — between STT and User context aggregator
            context_aggregator.user(),
            llm,
            tts,
            voicemail.gate(),  # TTS gating — Immediately after the TTS service
            transport.output(),
            context_aggregator.assistant(),
        ]
    )

    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")

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

    @voicemail.event_handler("on_conversation_detected")
    async def on_conversation_detected(processor):
        logger.info("Conversation detected!")

    @voicemail.event_handler("on_voicemail_detected")
    async def on_voicemail_detected(processor):
        logger.info("Voicemail detected! Leaving a message...")

        # Push frames using standard Pipecat pattern
        await processor.push_frame(
            TTSSpeakFrame(
                "Hello, this is Jamie calling about your appointment. Please call me back at 555-0123 when you get this."
            )
        )

        # NOTE: A common pattern is to end pipeline after the voicemail is left.
        # Uncomment the following line to end the pipeline after leaving the voicemail.
        # await processor.push_frame(EndTaskFrame(), FrameDirection.UPSTREAM)

    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()