

Oh I’m glad this tech went somewhere useful! I remember reading the paper and toying with the models they released as a proof of concept like… 8 years ago? It was really powerful back then. The ability to do TTS of someone’s voice given literally 3 seconds of training data?! (In fact I found that it worked best with short, nonsense audio clips than actually saying anything. Saying “test test test” worked way better than reading an actual sentence.) But now it looks like it can actually handle tone well. It’s also probably way better now, and less… Asthmatic sounding.
I saw one like this where a guy hired a hacker to get into his encrypted wallet device because he was sure it had like $100k in it. Guy broke in, pulled up the Bitcoin wallet and… It was empty. Dude had forgotten that he sold all his Bitcoin YEARS ago.