Spaces:
Sleeping
Sleeping
| from typing import Literal | |
| from fastapi import APIRouter, Depends, HTTPException | |
| from fastapi.responses import Response | |
| from pydantic import BaseModel, Field | |
| from services.auth import require_service_key | |
| from services.tts_service import synthesize, is_available, backend_status | |
| router = APIRouter(prefix="/tts", tags=["tts"]) | |
| class TtsRequest(BaseModel): | |
| text: str = Field(..., min_length=1, max_length=1200) | |
| voice: str | None = None | |
| # "ogg" = Ogg/Opus (~10x smaller than WAV; not playable in Safari, so the | |
| # client negotiates via canPlayType and asks for "wav" when needed). | |
| format: Literal["wav", "ogg"] = "wav" | |
| def tts_health(): | |
| """Reports whether Kokoro TTS is installed/usable and which backend runs it.""" | |
| return {"available": is_available(), "backend": backend_status()} | |
| def tts(req: TtsRequest): | |
| """ | |
| Synthesize interviewer speech with Kokoro. Returns audio (WAV or Ogg/Opus) | |
| on success, or 503 when TTS is unavailable so the caller falls back to | |
| browser speech. Responses are LRU-cached per (text, voice, format). | |
| """ | |
| try: | |
| audio, mime = synthesize(req.text, req.voice, req.format) | |
| return Response(content=audio, media_type=mime) | |
| except Exception as e: # noqa: BLE001 — TTS is optional; never hard-fail | |
| raise HTTPException(status_code=503, detail=f"TTS unavailable: {e}") | |