Hacker News new | ask | show | jobs
by Dowwie 3397 days ago
now? https://www.youtube.com/watch?v=XfcqBElF0ZI
1 comments
M4v3R 3397 days ago
Afaik VoCo isn't creating anything from thin air, instead it scans the available voice data (it reportedly needs a sample of about 20 mins of a person speaking) and copies fragments of it in specific order to create a sentence.
link