feat(tts): Chatterbox-Provider (hohe Qualitaet + Voice-Cloning) anbinden

Loest #7. Der chatterbox-Stub wird durch eine echte Anbindung an den lokalen
Chatterbox-HTTP-Dienst ersetzt (POST /speak -> /status pollen -> GET /audio, WAV).
no_playback=true -> der Dienst spielt nicht lokal ab, liefert nur Bytes. WAV->PCM
(24 kHz, Resampling bei Bedarf). Waehlbar via tts_provider=chatterbox; piper bleibt
der schnelle Default (chatterbox ist ~echtzeit-langsam, dafuer klonbare Stimme).

- config: CHATTERBOX_BASE_URL/_VOICE/_LANG/_SPEED/_TIMEOUT; Registry verdrahtet
- Tests: gemockter httpx (Synthese, WAV/Resample, Job-Fehler, Stimmenwahl)
- Doku: README, Architektur (#7), deploy/README (GPU-Pinning per UUID, no_playback)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter 2026-06-18 09:44:31 +02:00
commit 5f01607b79
7 changed files with 223 additions and 7 deletions

View file

@ -1,5 +1,113 @@
"""TTS über den lokalen Chatterbox-HTTP-Service (Resemble AI, hohe Qualitaet + Voice-Cloning).
Architektur wie beim llama.cpp-LLM: ein separater Dienst (eigene Conda-Env, GPU) haelt
das Modell geladen; dieser Provider ruft ihn per HTTP auf. Der Dienst ist job-basiert:
POST /speak -> /status pollen -> GET /audio/{id} (WAV).
Wichtig: `no_playback=true` -> der Dienst spielt NICHT lokal ab, sondern liefert nur die
WAV (fuer Remote-/Gateway-Nutzung). Chatterbox ist neural und ~Echtzeit langsam -> als
QUALITAETS-Provider gedacht (piper bleibt der schnelle Default).
"""
from __future__ import annotations
import asyncio
import io
import time
import wave
import httpx
from app.providers.tts.base import TTSProvider
from app.providers.tts.piper import _resample, _wrap_wav
class ChatterboxTTSProvider(TTSProvider):
async def synthesize(self, text: str, voice: str | None = None, audio_format: str = "pcm") -> bytes:
return b""
def __init__(
self,
base_url: str = "http://127.0.0.1:9999",
voice: str = "",
lang: str = "de",
speed: float = 1.0,
target_rate: int = 24000,
timeout: int = 180,
):
self.base_url = base_url.rstrip("/")
self.voice = (voice or "").strip() # Pfad zu Referenz-WAV (Voice-Cloning) oder leer
self.lang = lang
self.speed = speed
self.target_rate = int(target_rate)
self.timeout = timeout
def _ref_voice(self, voice: str | None) -> str | None:
# Eine angefragte Stimme gilt nur, wenn sie wie ein WAV-Pfad aussieht
# (Cloud-Stimmennamen wie "Zephyr"/"alloy" ignorieren -> Default nehmen).
cand = (voice or "").strip()
if cand.endswith(".wav"):
return cand
return self.voice or None
async def synthesize(
self,
text: str,
voice: str | None = None,
audio_format: str = "pcm",
) -> bytes:
if not text or not text.strip():
raise ValueError("TTS input text is empty")
payload = {
"text": text.strip(),
"lang": self.lang,
"speed": self.speed,
"keep_audio": True,
"no_playback": True,
}
ref = self._ref_voice(voice)
if ref:
payload["voice"] = ref
async with httpx.AsyncClient(timeout=self.timeout) as client:
resp = await client.post(f"{self.base_url}/speak", json=payload)
resp.raise_for_status()
job_id = resp.json()["job_id"]
wav_bytes = await self._await_audio(client, job_id)
pcm, rate = self._wav_to_pcm(wav_bytes)
if rate != self.target_rate:
pcm = await asyncio.to_thread(_resample, pcm, rate, self.target_rate)
if audio_format == "wav":
return _wrap_wav(pcm, self.target_rate)
return pcm
async def _await_audio(self, client: httpx.AsyncClient, job_id: str) -> bytes:
"""Wartet (via /status) bis der Job fertig ist und laedt dann die WAV."""
deadline = time.monotonic() + self.timeout
while True:
status = await client.get(f"{self.base_url}/status")
status.raise_for_status()
match = next(
(j for j in status.json().get("recent_jobs", []) if j["id"] == job_id),
None,
)
if match:
if match["status"] == "done":
break
raise RuntimeError(
f"Chatterbox-Job {match['status']}: {match.get('error') or ''}"
)
if time.monotonic() > deadline:
raise RuntimeError("Chatterbox-Timeout (Job nicht rechtzeitig fertig)")
await asyncio.sleep(0.3)
audio = await client.get(f"{self.base_url}/audio/{job_id}")
if audio.status_code != 200 or not audio.content:
raise RuntimeError(f"Chatterbox-Audio {audio.status_code}: {audio.text[:200]}")
return audio.content
@staticmethod
def _wav_to_pcm(wav_bytes: bytes) -> tuple[bytes, int]:
with wave.open(io.BytesIO(wav_bytes)) as w:
rate = w.getframerate()
frames = w.readframes(w.getnframes())
return frames, rate