|
|
from fastapi import APIRouter, HTTPException |
|
|
from fastapi.responses import FileResponse |
|
|
from models.tts import TTSRequest |
|
|
from services.tts_service import text_to_speech, text_to_speech_base64 |
|
|
from pathlib import Path |
|
|
|
|
|
router = APIRouter(prefix="/tts", tags=["Text To Speech"]) |
|
|
|
|
|
@router.post("/") |
|
|
async def generate_tts(request: TTSRequest): |
|
|
""" |
|
|
Convert text to speech using the free gTTS backend (MP3 only). |
|
|
Can return either Base64 or file based on return_base64 parameter. |
|
|
""" |
|
|
try: |
|
|
|
|
|
if getattr(request, "return_base64", False): |
|
|
result = text_to_speech_base64( |
|
|
text=request.text, |
|
|
voice=request.voice, |
|
|
fmt=request.format, |
|
|
) |
|
|
|
|
|
return { |
|
|
"success": True, |
|
|
"audio_base64": result["audio_base64"], |
|
|
"mime_type": result["mime_type"], |
|
|
"format": result["format"], |
|
|
"filename": result["filename"], |
|
|
"size_bytes": result["size_bytes"], |
|
|
"size_base64": result["size_base64"] |
|
|
} |
|
|
|
|
|
|
|
|
else: |
|
|
audio_path = text_to_speech( |
|
|
text=request.text, |
|
|
voice=request.voice, |
|
|
fmt=request.format, |
|
|
) |
|
|
|
|
|
if not Path(audio_path).exists(): |
|
|
raise HTTPException(status_code=500, detail="Audio file generation failed") |
|
|
|
|
|
media_type = "audio/mpeg" |
|
|
|
|
|
return FileResponse( |
|
|
path=audio_path, |
|
|
filename=f"speech.{request.format}", |
|
|
media_type=media_type, |
|
|
headers={ |
|
|
"Content-Disposition": f"attachment; filename=speech.{request.format}" |
|
|
}, |
|
|
) |
|
|
|
|
|
except ValueError as e: |
|
|
raise HTTPException(status_code=400, detail=str(e)) |
|
|
except Exception as e: |
|
|
raise HTTPException(status_code=500, detail=str(e)) |
|
|
except Exception as e: |
|
|
raise HTTPException(status_code=500, detail=str(e)) |
