And re: remixing:
How long until enough people put recordings of their voices out with a CC0 license that you can legally digitally remix any voice you want?
lloram239@feddit.de 1 year ago
Modern models need about 5sec of audio to replicate a voice. The days when you needed a large amount of audio for replication are gone.
And re: remixing:
How long until enough people put recordings of their voices out with a CC0 license that you can legally digitally remix any voice you want?
ryno364@lemmy.world 1 year ago
Do you have a reference for the 5secs of audio? And what would the quality of the ai be? I mean it would have to infer a lot of training just given 5 seconds of audio.
lloram239@feddit.de 1 year ago
PipedLinkBot@feddit.rocks [bot] 1 year ago
Here is an alternative Piped link(s):
Translation with HeyGen
Piped is a privacy-respecting open-source alternative frontend to YouTube.
I’m open-source, check me out at GitHub.