api/routes/transcription.py

"""Transcription routes for audio to text conversion."""
from fastapi import APIRouter, UploadFile, File, HTTPException, status, Depends, Query
from typing import Optional
from core.security import get_current_user
from domain.models import TranscriptionResponse, ErrorResponse
from services.transcription_service import transcription_service

router = APIRouter(prefix="/transcription", tags=["Transcription"])


@router.post(
    "",
    response_model=TranscriptionResponse,
    responses={
        400: {"model": ErrorResponse, "description": "Invalid file format"},
        500: {"model": ErrorResponse, "description": "Transcription failed"}
    }
)
async def transcribe_audio(
    current_user: dict = Depends(get_current_user),
    file: UploadFile = File(..., description="Audio file to transcribe"),
    language: Optional[str] = Query(None, description="ISO-639-1 language code (e.g., 'en', 'fr')"),
    prompt: Optional[str] = Query(None, description="Optional text to guide the model's style")
) -> TranscriptionResponse:
    """
    Transcribe an audio file to text using OpenAI Whisper.
    
    **Supported formats:** mp3, mp4, mpeg, mpga, m4a, wav, webm
    
    **Max file size:** 25 MB (OpenAI Whisper limit)
    
    Args:
        file: Audio file upload
        language: Optional language code to improve accuracy
        prompt: Optional prompt to guide transcription style
        current_user: Authenticated user (JWT required)
        
    Returns:
        Transcription with text, detected language, and duration
        
    Raises:
        HTTPException: If file format is unsupported or transcription fails
    """
    # Validate file format
    if not transcription_service.is_supported_format(file.filename):
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail=f"Unsupported file format. Supported: mp3, mp4, mpeg, mpga, m4a, wav, webm"
        )
    
    # Check file size (25 MB limit for Whisper API)
    file.file.seek(0, 2)  # Seek to end
    file_size = file.file.tell()  # Get position (file size)
    file.file.seek(0)  # Reset to beginning
    
    max_size = 25 * 1024 * 1024  # 25 MB
    if file_size > max_size:
        raise HTTPException(
            status_code=status.HTTP_400_BAD_REQUEST,
            detail=f"File too large. Maximum size is 25 MB, got {file_size / (1024 * 1024):.2f} MB"
        )
    
    try:
        # Transcribe audio
        result = await transcription_service.transcribe(
            audio_file=file,
            language=language,
            prompt=prompt
        )
        
        return TranscriptionResponse(**result)
        
    except Exception as e:
        raise HTTPException(
            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
            detail=f"Transcription failed: {str(e)}"
        )


@router.get("/supported-formats")
async def get_supported_formats(
    current_user: dict = Depends(get_current_user)
) -> dict:
    """
    Get list of supported audio formats.
    
    Returns:
        Dictionary with supported formats and info
    """
    return {
        "supported_formats": ["mp3", "mp4", "mpeg", "mpga", "m4a", "wav", "webm"],
        "max_file_size_mb": 25,
        "model": "whisper-1",
        "languages": "Auto-detection or specify ISO-639-1 code"
    }