eswar129/AI-VOICE-CLONE-DETECTOR ? reverse-engineered prompt

Build me a web app that can tell whether an uploaded voice clip is a real human voice or an AI cloned voice.

I want a simple frontend where someone can upload common audio files like wav, mp3, ogg, m4a, or flac, then see the result clearly with a confidence score and a short status message. The backend should handle the audio upload, preprocess the sound, extract useful features, and run a deep learning model to make the prediction. Please make it work as a React app on the front end and a FastAPI service on the back end, with a clean API for checking health and submitting files for detection. If it makes sense, include support for real time updates too.

Also set it up so the model can be trained from folders of real and fake voice samples, and saved for later use. Keep the UI simple and polished, and make the whole thing easy to run locally.