첫 청크부터 재생

import os
import shutil
import subprocess
import time

import httpx

API = "https://api.elevenlabs.io/v1/text-to-speech/{voice_id}/stream"


def speak_streaming(voice_id: str, text: str, model_id: str = "eleven_v3") -> None:
    """One unit, one request; audio starts as soon as the first bytes land."""
    if shutil.which("ffplay") is None:
        raise SystemExit("install ffmpeg (for ffplay) to hear the stream")
    player = subprocess.Popen(
        ["ffplay", "-nodisp", "-autoexit", "-loglevel", "quiet", "-i", "pipe:0"],
        stdin=subprocess.PIPE,
    )
    started = time.perf_counter()
    first_chunk = None
    total = 0
    with httpx.stream(
        "POST",
        API.format(voice_id=voice_id),
        params={"output_format": "mp3_44100_128"},
        headers={"xi-api-key": os.environ["ELEVENLABS_API_KEY"]},
        json={"text": text, "model_id": model_id},
        timeout=httpx.Timeout(10.0, read=600.0),   # patience per chunk, sized for speech
    ) as response:
        response.raise_for_status()
        for chunk in response.iter_bytes():
            if first_chunk is None:
                first_chunk = time.perf_counter() - started
            total += len(chunk)
            player.stdin.write(chunk)                 # play while the rest arrives
            player.stdin.flush()                      # now, not when a buffer fills
    player.stdin.close()
    player.wait()
    print(f"first chunk {first_chunk:.2f}s, {total:,} bytes, "
          f"done {time.perf_counter() - started:.2f}s")


if __name__ == "__main__":
    speak_streaming(os.environ["VOICE_ID"], "This whole paragraph is one unit. "
                    "It is synthesized once, and you hear it from the first chunk.")