Texto a voz de KugelAudio para Pipecat

pip install "kugelaudio[pipecat]" "pipecat-ai[deepgram,local,openai,silero]"

import asyncio
import os

from pipecat.audio.vad.silero import SileroVADAnalyzer
from pipecat.frames.frames import TTSSpeakFrame
from pipecat.pipeline.pipeline import Pipeline
from pipecat.pipeline.runner import PipelineRunner
from pipecat.pipeline.task import PipelineTask
from pipecat.processors.aggregators.llm_context import LLMContext
from pipecat.processors.aggregators.llm_response_universal import (
    LLMContextAggregatorPair,
)
from pipecat.services.deepgram.stt import DeepgramSTTService
from pipecat.services.openai.llm import OpenAILLMService
from pipecat.transports.local.audio import (
    LocalAudioTransport,
    LocalAudioTransportParams,
)

from kugelaudio.pipecat import KugelAudioTTSService


async def main():
    transport = LocalAudioTransport(
        LocalAudioTransportParams(
            audio_in_enabled=True,
            audio_out_enabled=True,
            audio_out_sample_rate=24000,
            vad_enabled=True,
            vad_analyzer=SileroVADAnalyzer(),
        )
    )
    stt = DeepgramSTTService(api_key=os.environ["DEEPGRAM_API_KEY"])
    llm = OpenAILLMService(
        api_key=os.environ["OPENAI_API_KEY"],
        settings=OpenAILLMService.Settings(
            model="gpt-4o-mini",
            system_instruction="You are a helpful voice assistant. Keep answers short.",
        ),
    )
    tts = KugelAudioTTSService(
        model="kugel-3.5",
        voice_id=1071,
        sample_rate=24000,  # must match the transport's output rate
        language="en",      # normalization language (default: the voice's)
    )
    tts.prewarm()  # needs the running event loop, so call it inside main()

    context_aggregator = LLMContextAggregatorPair(LLMContext())
    pipeline = Pipeline(
        [
            transport.input(),
            stt,
            context_aggregator.user(),
            llm,
            tts,
            transport.output(),
            context_aggregator.assistant(),
        ]
    )

    task = PipelineTask(pipeline)
    await task.queue_frames([TTSSpeakFrame("Hi! How can I help you?")])
    await PipelineRunner().run(task)


if __name__ == "__main__":
    asyncio.run(main())