Microsoft Unveils VALL-E, Audio AI That Can Simulate Any Voice From 3-Second Prompts

Microsoft Unveils VALL-E, Audio AI That Can Simulate Any
Voice From 3-Second Prompts
VALL-E is a new text-to-speech AI model developed by Microsoft researchers that can precisely simulate a person's voice when offered a three-second audio prompt. VALL-E can reprocess audio of anyone saying anything once it has learned their voice while trying to retain the speaker's emotional tone. VALL-creators E's believe that when coupled with other generative AI m...

* This article was originally published here

Comments

-

*