Add XTTS-v2 as first TTS backend, extensible for more

Mirrors the ASR backend pattern exactly: a BACKENDS dict in
tts/router.py maps a backend name to its worker URL, so adding the
next backend is just a new worker file + venv + supervisord entry +
one dict line. XTTS-v2 runs in its own venv (--system-site-packages,
inherits base image torch/CUDA) as a new supervisord program on
port 8005.

XTTS is zero-shot voice cloning, so a reference-voice library was
added (/tts/voices CRUD, stored under /srv/tts/voices) — synthesis
requires picking a previously uploaded voice. Results and model
cache live under /srv/tts/{results,models-cache}, new quadlet
volumes, owned by the same 983:983 user as the existing /srv/asr
dirs.

Fixed two environment issues uncovered while getting XTTS to
actually run inside the container (non-root user, root-built venvs):
- coqui-tts only pins transformers>=4.57 with no ceiling, so pip
  installed an incompatible 5.x; pinned to the last 4.x release.
- HOME defaults to /app (owned by root) for the container's runtime
  user, so numba/matplotlib/torch cache writes failed; HOME is now
  forced to /tmp in all three workers (faster_whisper, qwen3, xtts)
  before any of those libraries get imported.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
du5t
2026-06-18 18:46:45 +09:00
parent ac49bfc7f9
commit acdf098c41
13 changed files with 761 additions and 24 deletions

View File

@@ -9,11 +9,12 @@ from fastapi.responses import FileResponse, HTMLResponse, JSONResponse
from fastapi.staticfiles import StaticFiles
from starlette.middleware.sessions import SessionMiddleware
from asr.config import ensure_runtime_dirs
from asr.config import ensure_runtime_dirs as ensure_asr_dirs
from asr.router import router as asr_router
from asr.router import ws_router as asr_ws_router
from core.auth import SESSION_SECRET_KEY, require_login
from core.auth import router as auth_router
from tts.config import ensure_runtime_dirs as ensure_tts_dirs
from tts.router import router as tts_router
app = FastAPI(title="Speech Gateway", docs_url="/docs", redoc_url="/redoc")
@@ -42,7 +43,8 @@ app.include_router(tts_router, prefix="/tts", tags=["tts"], dependencies=[Depend
@app.on_event("startup")
def startup() -> None:
ensure_runtime_dirs()
ensure_asr_dirs()
ensure_tts_dirs()
if UI_DIR.exists():
app.mount("/ui", StaticFiles(directory=str(UI_DIR), html=True), name="ui")
app.mount("/assets", StaticFiles(directory=str(UI_DIR / "assets")), name="assets")