Ed Jewett: AI Can Now Fake Your Voice in 5 Seconds

Advanced Cyber/IO

AI Clones Your Voice After Listening for 5 Seconds

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training.

Learn more and listen to examples.

Opt in for free daily update from this free blog. Separately The Steele Report ($11/mo) offers weekly text report and live webinar exclusive to paid subscribers, who can also ask questions of Robert. Or donate to ask questions directly of Robert.