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.

#Microsoft #AI #VoiceSimulation #VALLE
https://arstechnica.com/information-technology/2023/01/microsofts-new-ai-can-simulate-anyones-voice-with-3-seconds-of-audio/

A demonstration of Microsoft's neural codec language model VALL-E can be found at:

https://valle-demo.github.io/