Streaming TTS on Pipecat

pip install "pipecat-ai[assemblyai,openai,silero,runner,webrtc]>=1.14.0" python-dotenv

ASSEMBLYAI_API_KEY=your_assemblyai_key

import os

from dotenv import load_dotenv
from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.audio.vad.vad_analyzer import VADParams
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
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.runner.types import RunnerArguments
from pipecat.runner.utils import create_transport
from pipecat.services.assemblyai.stt import AssemblyAISTTService
from pipecat.services.assemblyai.tts import AssemblyAITTSService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.base_transport import BaseTransport, TransportParams
from pipecat.workers.runner import WorkerRunner

load_dotenv()

# Silero (used for barge-in) should agree with AssemblyAI's own VAD on what
# counts as speech, so both use the STT's default threshold.
VAD_THRESHOLD = 0.2

transport_params = {
    "webrtc": lambda: TransportParams(audio_in_enabled=True, audio_out_enabled=True),
}


async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
    api_key = os.environ["ASSEMBLYAI_API_KEY"]

    stt = AssemblyAISTTService(
        api_key=api_key,
        # AssemblyAI decides when the user has finished speaking
        vad_force_turn_endpoint=False,
        settings=AssemblyAISTTService.Settings(
            model="universal-3-6-pro",
            mode="balanced",
            vad_threshold=VAD_THRESHOLD,
        ),
    )
    # The LLM Gateway, through its OpenAI-compatible API
    llm = OpenAILLMService(
        api_key=api_key,
        base_url="https://llm-gateway.assemblyai.com/v1",
        settings=OpenAILLMService.Settings(
            model="gemma-4-31b",
            system_instruction=(
                "You are a friendly voice assistant. Keep replies to one or two "
                "short sentences, with no lists, markdown, or emojis."
            ),
        ),
    )
    tts = AssemblyAITTSService(
        api_key=api_key,
        settings=AssemblyAITTSService.Settings(
            model="assemblyai-tts-1",
            voice="49c443a4-8a1d-5f7e-b70b-98bdbd9823c3",  # Audrey
        ),
    )

    context = LLMContext()
    user_aggregator, assistant_aggregator = LLMContextAggregatorPair(
        context,
        user_params=LLMUserAggregatorParams(
            vad_analyzer=SileroVADAnalyzer(params=VADParams(confidence=VAD_THRESHOLD))
        ),
    )

    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            user_aggregator,
            llm,
            tts,
            transport.output(),
            assistant_aggregator,
        ]
    )
    worker = PipelineWorker(pipeline, params=PipelineParams(enable_metrics=True))
    runner = WorkerRunner(handle_sigint=runner_args.handle_sigint)
    await runner.add_workers(worker)

    @transport.event_handler("on_client_connected")
    async def on_client_connected(transport, client):
        # A fixed greeting is spoken right away, without waiting on the LLM
        await worker.queue_frames([TTSSpeakFrame("Hi, I'm Audrey. How can I help?")])

    @transport.event_handler("on_client_disconnected")
    async def on_client_disconnected(transport, client):
        await runner.cancel()

    await runner.run()


async def bot(runner_args: RunnerArguments):
    transport = await create_transport(runner_args, transport_params)
    await run_bot(transport, runner_args)


if __name__ == "__main__":
    from pipecat.runner.run import main

    main()

python bot.py