corentinj/real-time-voice-cloning ? reverse-engineered prompt

Build me a simple voice cloning app based on this project.

I want to be able to give it a short sample of someone’s voice, type in any text, and get back spoken audio that sounds like that person. Please make it easy to run on Windows or Linux, with both a quick command line way and a small visual demo if possible. If pretrained models are needed, set it up so they download automatically, and if not, make it clear how to use my own audio files.

Keep it practical and simple, since this repo is older, so don’t overcomplicate it. I mainly want the full flow working, from loading a voice sample to generating speech in real time. If you need to check current setup details or docs online, go ahead.