Article · Wikipedia archive · Last revised Jun 18, 2026

VALL-E

VALL-E is a generative artificial intelligence system for speech synthesis developed by Microsoft Research and announced on January 5, 2023. It can "recreate any voice from a three-second sample clip". It has been trained on 60,000 hours of English language speech from Meta’s audio library LibriLight.

Last revised
Jun 18, 2026
Read time
≈ 1 min
Length
137 w
Citations
3
Source
Wikipedia ↗
VALL-E
DeveloperMicrosoft
PlatformCloud computing platforms
Websitehttps://www.microsoft.com/en-us/research/project/vall-e-x/

VALL-E is a generative artificial intelligence system for speech synthesis developed by Microsoft Research and announced on January 5, 2023.1 It can "recreate any voice from a three-second sample clip".2 It has been trained on 60,000 hours of English language speech from Meta’s audio library LibriLight.3

See also

See also

External links
References

References

  1. Dominguez, Daniel (January 27, 2023). "Microsoft Unveils VALL-E, a Game-Changing TTS Language Model". InfoQ. Retrieved September 19, 2023.
  2. Morrison, Ryan (January 10, 2023). "Microsoft's new VALL-E AI can clone your voice from a three-second audio clip". Tech Monitor. Retrieved September 19, 2023.
  3. Wodecki, Ben (January 11, 2023). "Microsoft's VALL-E Generates Speech From Just 3 Seconds of Audio". AI Business.