model-ml/ml-api/app/tts.py

from pathlib import Path
from typing import Optional
import tempfile

from TTS.api import TTS


_TTS_CACHE = {}


def _get_tts_model(lang_code: str) -> TTS:
    """
    Retourne un modèle TTS en fonction de la langue.
    - Français: modèle VITS fr
    - Sinon: modèle multilingue générique
    """
    if lang_code not in _TTS_CACHE:
        if lang_code.startswith("fr"):
            model_name = "tts_models/fr/css10/vits"
        else:
            # Multilingue par défaut
            model_name = "tts_models/multilingual/multi-dataset/your_tts"
        _TTS_CACHE[lang_code] = TTS(model_name=model_name)
    return _TTS_CACHE[lang_code]


def synthesize(text: str, lang_code: str, out_dir: Path) -> Path:
    out_dir.mkdir(parents=True, exist_ok=True)
    tmp = Path(tempfile.mkstemp(suffix=".wav")[1])
    tts = _get_tts_model(lang_code)
    tts.tts_to_file(text=text, file_path=str(tmp))
    # Renomme vers un nom stable
    target = out_dir / f"output_{tmp.name.split('.')[-2]}.wav"
    tmp.rename(target)
    return target