Tuesday, January 10, 2023

Microsoft’s new AI can simulate anyone’s voice with 3 seconds of audio Text-to-speech model can preserve speaker's emotional tone and acoustic environment.

https://ift.tt/NTbeE3s

Submitted January 10, 2023 at 04:21PM by x0y1 https://ift.tt/U7DE8Mr
Posted by at
Labels: ,

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)