VALL-E: 5 things to know about Microsoft's AI model that can mimic any voice in 3 seconds

Microsoft calls VALL-E a "neural codec language model" that generates audio from text input and short samples from a target speaker. It can mimic any voice by listening to a voice sample as small as 3 seconds. VALL-E is not generally available yet.

from Gadgets News – Latest Technology News, Mobile News & Updates https://ift.tt/4QKuaHI
via