Feat: Chatterbox-Klon-Referenz hochladen (eigene Stimme via ElevenLabs → lokal unbegrenzt klonen)

Sidecar: /reference (POST Upload → 24kHz-Mono-WAV via PyAV/faster-whisper, kein System-ffmpeg;
GET/DELETE). Chatterbox nutzt aktive Referenz (active.txt, überlebt Restart). Backend: /api/voice/
reference-Proxy. Picker (Chatterbox): „Referenz-Stimme hochladen (mp3/wav)" → setzt Stimme auf
»deine Referenz«. Ermöglicht den User-Plan: Stimme besorgen → EL erzeugen → Chatterbox klont.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Hitonabi
2026-06-28 00:55:40 +02:00
parent 75727c6b36
commit eeb397f066
6 changed files with 304 additions and 159 deletions
+36
View File
@@ -79,6 +79,42 @@ async def voice_stt(audio: UploadFile = File(...), language: str = Form(default=
raise HTTPException(502, f"STT fehlgeschlagen: {exc}")
@router.post("/voice/reference")
async def voice_set_reference(audio: UploadFile = File(...)) -> dict:
"""Klon-Referenz (z.B. ElevenLabs-Erzeugnis) hochladen → Chatterbox nutzt sie. Proxy → Sidecar."""
data = await audio.read()
if not data:
raise HTTPException(400, "Leeres Audio.")
files = {"audio": (audio.filename or "ref.wav", data, audio.content_type or "audio/mpeg")}
try:
async with httpx.AsyncClient(timeout=_TIMEOUT) as client:
r = await client.post(f"{VOICE_SERVICE_URL}/reference", files=files)
r.raise_for_status()
return r.json()
except httpx.HTTPError as exc:
raise HTTPException(502, f"Referenz-Upload fehlgeschlagen: {exc}")
@router.get("/voice/reference")
def voice_get_reference() -> dict:
try:
r = httpx.get(f"{VOICE_SERVICE_URL}/reference", timeout=httpx.Timeout(8.0))
r.raise_for_status()
return r.json()
except Exception as exc: # noqa: BLE001
return {"active": False, "error": str(exc)}
@router.delete("/voice/reference")
def voice_clear_reference() -> dict:
try:
r = httpx.delete(f"{VOICE_SERVICE_URL}/reference", timeout=httpx.Timeout(8.0))
r.raise_for_status()
return r.json()
except httpx.HTTPError as exc:
raise HTTPException(502, f"Löschen fehlgeschlagen: {exc}")
@router.post("/voice/tts")
async def voice_tts(body: TTSIn) -> Response:
"""Text → Sprache (Proxy auf Sidecar /tts), liefert WAV-Bytes."""