pipecat/examples/foundational/15-switch-voices.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.adapters.schemas.function_schema import FunctionSchema
from pipecat.adapters.schemas.tools_schema import ToolsSchema
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import Frame, LLMRunFrame
from pipecat.pipeline.parallel_pipeline import ParallelPipeline
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.processors.filters.function_filter import FunctionFilter
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.llm_service import FunctionCallParams
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

load_dotenv(override=True)


class SwitchVoices(ParallelPipeline):
    def __init__(self):
        self._current_voice = "News Lady"

        news_lady = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
            settings=CartesiaTTSService.Settings(
                voice="bf991597-6c13-47e4-8411-91ec2de5c466",  # Newslady
            ),
        )

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

        barbershop_man = CartesiaTTSService(
            api_key=os.getenv("CARTESIA_API_KEY"),
            settings=CartesiaTTSService.Settings(
                voice="a0e99841-438c-4a64-b679-ae501e7d6091",  # Barbershop Man
            ),
        )

        super().__init__(
            # News Lady voice
            [FunctionFilter(self.news_lady_filter), news_lady],
            # British Reading Lady voice
            [FunctionFilter(self.british_lady_filter), british_lady],
            # Barbershop Man voice
            [FunctionFilter(self.barbershop_man_filter), barbershop_man],
        )

    @property
    def current_voice(self):
        return self._current_voice

    async def switch_voice(self, params: FunctionCallParams):
        self._current_voice = params.arguments["voice"]
        await params.result_callback(
            {
                "voice": f"You are now using your {self.current_voice} voice. Your responses should now be as if you were a {self.current_voice}."
            }
        )

    async def news_lady_filter(self, _: Frame) -> bool:
        return self.current_voice == "News Lady"

    async def british_lady_filter(self, _: Frame) -> bool:
        return self.current_voice == "British Lady"

    async def barbershop_man_filter(self, _: Frame) -> bool:
        return self.current_voice == "Barbershop Man"


# 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")

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

    tts = SwitchVoices()

    llm = OpenAILLMService(
        api_key=os.getenv("OPENAI_API_KEY"),
        settings=OpenAILLMService.Settings(
            system_instruction="You are a helpful LLM in a WebRTC call. Your goal is to demonstrate your capabilities. Respond to what the user said in a creative and helpful way. Your output should not include non-alphanumeric characters. You can do the following voices: 'News Lady', 'British Lady' and 'Barbershop Man'.",
        ),
    )
    llm.register_function("switch_voice", tts.switch_voice)

    switch_voice_function = FunctionSchema(
        name="switch_voice",
        description="Switch your voice only when the user asks you to",
        properties={
            "voice": {
                "type": "string",
                "description": "The voice the user wants you to use",
            },
        },
        required=["voice"],
    )
    tools = ToolsSchema(standard_tools=[switch_voice_function])

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

    pipeline = Pipeline(
        [
            transport.input(),  # Transport user input
            stt,
            user_aggregator,  # User responses
            llm,  # LLM
            tts,  # TTS with switch voice functionality
            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.
        context.add_message(
            {
                "role": "user",
                "content": f"Please introduce yourself to the user and let them know the voices you can do. Your initial responses should be as if you were a {tts.current_voice}.",
            }
        )
        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()