appImage.py

@app.post("/imagecaption/")
async def caption_from_frontend(file: UploadFile):
    try:
        # Save temp image
        contents = await file.read()
        tmp_path = os.path.join(tempfile.gettempdir(), file.filename)
        with open(tmp_path, "wb") as f:
            f.write(contents)

        caption = generate_caption(tmp_path)

        # Generate audio
        audio_path = os.path.join(tempfile.gettempdir(), file.filename + ".mp3")
        tts = gTTS(text=caption)
        tts.save(audio_path)

        return JSONResponse({
            "answer": caption,
            "audio": f"/files/{os.path.basename(audio_path)}"
        })

    except Exception as e:
        return JSONResponse({"error": str(e)}, status_code=500)