LLM Tokens to Streaming TTS

import asyncio
import gradium


async def play_pcm(chunk: bytes):
    # Replace with your audio playback sink.
    ...


async def phrase_chunks(llm_tokens):
    buffer = []
    async for token in llm_tokens:
        buffer.append(token)
        text = "".join(buffer)
        if text.endswith((".", "?", "!", ", ")) or len(text) > 80:
            yield text
            buffer = []
    if buffer:
        yield "".join(buffer) + " <flush>"


async def speak_llm(llm_tokens):
    client = gradium.client.GradiumClient(api_key="your-api-key")

    async with client.tts_realtime(
        voice_id="YTpq7expH9539ERJ",
        output_format="pcm",
    ) as tts:
        async def sender():
            async for chunk in phrase_chunks(llm_tokens):
                await tts.send_text(chunk)
            await tts.send_eos()

        async def receiver():
            async for msg in tts:
                if msg["type"] == "audio":
                    await play_pcm(msg["audio"])
                elif msg["type"] == "end_of_stream":
                    return

        await asyncio.gather(sender(), receiver())