Microsoft’s new AI can simulate anyone’s voice with 3 seconds of audio

Ars Technica 2023-01-09

Summary:

Text-to-speech model can preserve speaker's emotional tone and acoustic environment.

Link:

https://arstechnica.com/?p=1908618

From feeds:

Cyberlaw » Ars Technica
Music and Digital Media » Ars Technica

Tags:

&

Authors:

Benj Edwards

Date tagged:

01/09/2023, 18:42

Date published:

01/09/2023, 17:15