return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 5 months agoMicrosoft’s VASA-1 can deepfake a person with one photo and one audio trackarstechnica.comexternal-linkmessage-square43fedilinkarrow-up1112arrow-down13cross-posted to: technology@beehaw.orgtech@lemmit.onlineartificial_intel@lemmy.mltechnology@lemmy.ml
arrow-up1109arrow-down1external-linkMicrosoft’s VASA-1 can deepfake a person with one photo and one audio trackarstechnica.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 5 months agomessage-square43fedilinkcross-posted to: technology@beehaw.orgtech@lemmit.onlineartificial_intel@lemmy.mltechnology@lemmy.ml
minus-squarekromem@lemmy.worldlinkfedilinkEnglisharrow-up1·5 months agoThis project doesn’t recreate or simulate voices at all. It takes a still photograph and created a lip synched video of that person saying the paired full audio clip. There’s other projects that simulate voices.
This project doesn’t recreate or simulate voices at all.
It takes a still photograph and created a lip synched video of that person saying the paired full audio clip.
There’s other projects that simulate voices.