We will never again be able to trust video or audio. AI fed 3 seconds of speech can faithfully reproduce the voice under any circumstance including environmental sounds (such as background or phone/radio quality vocals) - Upgoat - "what's upgoat!"

×

Login Register an account

Top Submissions Explore Upgoat Search Random Subverse Random Post Colorize! Site Rules Donate

29

We will never again be able to trust video or audio. AI fed 3 seconds of speech can faithfully reproduce the voice under any circumstance including environmental sounds (such as background or phone/radio quality vocals)
submitted by totes_magotes to aII 2.3 yearsJan 11, 2023 18:52:34 ago (+30/-1) (valle-demo.github.io)
https://valle-demo.github.io/

22 comments block

retard 0 points 2.3 years ago

Sorry for my English. I'm using the dictionary sometimes.