https://youtube.com/watch?v=17_xLsqny9E
Microsoft’s text-to-speech model VALL-E can mimic anyone’s voice with little training data. Now it can do so across languages while replicating emotion.
https://youtube.com/watch?v=17_xLsqny9E
Microsoft’s text-to-speech model VALL-E can mimic anyone’s voice with little training data. Now it can do so across languages while replicating emotion.
Comments are closed.