tts_engine.py

import os
import httpx

MODAL_ENDPOINT = os.environ.get("MODAL_ENDPOINT_MISTRAL_TTS", "")
MISTRAL_API_KEY = os.environ.get("MISTRAL_API_KEY", "")
MODAL_AUTH_TOKEN = os.environ.get("MODAL_AUTH_TOKEN", "")

VOICE = "french_female"
MODEL = "mistral-tts"


def synthesize(text: str) -> bytes | None:
    """Tier-1: call Mistral API directly from the Space (simplest, free tier)."""
    if not MISTRAL_API_KEY:
        return _fallback_modal(text)

    resp = httpx.post(
        "https://api.mistral.ai/v1/audio/speech",
        headers={"Authorization": f"Bearer {MISTRAL_API_KEY}"},
        json={
            "model": MODEL,
            "input": text,
            "voice": VOICE,
            "response_format": "wav",
        },
        timeout=25,
    )
    if resp.is_error:
        return _fallback_modal(text)
    return resp.content


def _fallback_modal(text: str) -> bytes | None:
    """Tier-2: fall back to Modal-hosted Mistral TTS."""
    if not MODAL_ENDPOINT:
        raise RuntimeError("No TTS endpoint available")

    resp = httpx.post(
        MODAL_ENDPOINT,
        json={"text": text, "token": MODAL_AUTH_TOKEN},
        timeout=30,
    )
    resp.raise_for_status()
    return resp.content