app/main.py

import os
import requests
from fastapi import FastAPI, HTTPException
from fastapi.responses import Response
from pydantic import BaseModel

from app.config import (
    ELEVENLABS_API_KEY,
    ELEVENLABS_BASE_URL,
    MODEL_ID,
    VOICE_IDS,
    DEFAULT_LANGUAGE,
)
   
from app.voice_languag_detector import detect_language

app = FastAPI(title="Africa TTS - Auto Language Voice Cloning")


class TTSRequest(BaseModel):
    text: str
    stability: float = 0.5
    similarity_boost: float = 0.75


@app.get("/")
def root():
    return {"status": "ok", "message": "Africa TTS API is running"}


@app.post("/tts")
def text_to_speech(request: TTSRequest):
    if not request.text or not request.text.strip():
        raise HTTPException(status_code=400, detail="Text cannot be empty")

    if not ELEVENLABS_API_KEY:
        raise HTTPException(status_code=500, detail="ELEVENLABS_API_KEY not set")

    lang_code, confidence = detect_language(request.text)
    voice_id = VOICE_IDS.get(lang_code, VOICE_IDS[DEFAULT_LANGUAGE])

    url = f"{ELEVENLABS_BASE_URL}/text-to-speech/{voice_id}"

    headers = {
        "xi-api-key": ELEVENLABS_API_KEY,
        "Content-Type": "application/json",
        "Accept": "audio/mpeg",
    }

    payload = {
        "text": request.text,
        "model_id": MODEL_ID,
        "voice_settings": {
            "stability": request.stability,
            "similarity_boost": request.similarity_boost,
        },
    }

    response = requests.post(url, json=payload, headers=headers)

    if response.status_code != 200:
        raise HTTPException(
            status_code=response.status_code,
            detail=f"ElevenLabs API error: {response.text}",
        )

    return Response(
      content = response.content, 
      media_type = "audio/mpeg",
      headers = {
            "X-Detected-Language": lang_code,
            "X-Detection-confidence": str(round(confidence,4)),
            "X-Voice-Id-Used": voice_id,
      }
    )