Voice cloning AI (deepfake for voice). Using cloned voice from only 5-10 seconds of targeted voice.
Implementation used an unofficial (but popular) Implementation of the famous paper "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis "
This demo is used only for educational perposes.
sample_0.mp4
-Hi people check this out this man Rida is doing something fun
out_0.mp4
-Morocco is a beautiful country that you should visit at least once in your life
out_1.mp4
obama_sample_1.mp4
-Hi people check this out this man Rida is doing something fun
obama_out.mp4
-Morocco is a beautiful country that you should visit at least once in your life
obama_out_1.mp4
Implementation using the model from: https://github.com/CorentinJ/Real-Time-Voice-Cloning
Based on the paper: https://arxiv.org/abs/1806.04558