Microsoft VALL-E Clones Anyone's Voice From a 3-Second Sample

VALL-E can be used to synthesize high-quality personalized speech with only a three-second enrollment recording of a speaker as an acoustic prompt. The model of the voice can then be used for text-to-speech applications.

Related Keywords

New York ,United States ,Markn Vena ,Michaell Teich ,Giacomo Miceli ,Ross Rubin ,Werner Herzog ,Bob Odonnell ,Google ,Drexel University ,Smarttech Research ,Technalysis Research ,Reticle Research ,Microsoft ,New York City ,Ritu Jyoti ,San Jose ,Online Computer Science Degree ,Wiretap Act ,First Amendment ,Bobo Donnell ,Foster City ,