Your gilbert gottfried is better than mine - in that it's more obviously gilbert, however, when he's doing interviews and not "in character" the one i have sounds closer to his actual voice.[0][1]

I use(d) "Real time voice cloning" available on github. I have used your site before, i think that's actually the reason i wanted to find software to do it myself originally!

I ended up using mine to do the announcements on all of the ham repeaters in Central Louisiana. I'm not sure how many are still active, but i had a couple of podcasters and two presidents doing the announcements for a while.[2]

Nice work, wrapping it all in a website/service. I'll bookmark it!

[0] https://soundcloud.com/djoutcold/gottfried1-1

[1] https://soundcloud.com/djoutcold/gilbertopiatecookies

[2] https://soundcloud.com/djoutcold/trump-id-01

Good results! Where did you get the voice samples?

I love your use case for ham radio. That's brilliant!

I just cut up youtube videos' audio to only have the voice i wanted to use.

And thanks. I'm glad there's other people messing around with voice cloning, still.

I'm honestly surprised that virtual celebs haven't taken over more. They could replace people in a lot of roles like newscasters and such.

I'm seeing VTubers more and more on japanese (late night) TV green-screened in alongside regular people.

It's coming soon.

I'm so stoked for this, and I totally agree. This is the future of entertainment.

I'm working on mocap, photogrammetry, and compositing on Twitch, and I'm leveraging vocodes for subscriber interaction in the stream.

Are either of you working in this domain? Want to chat?

I'd love to hear more about how this is done, but I've never done a thing with any of this other than trying to predict the future and seeing this as something that will take over eventually. I'm Natsu#7152 on Discord.