Live data from Hacker News

Creates hyper-realistic voice clones from just 3 seconds of audio

anyvoice.net

1–10 of 48 posts

Re: Creates hyper-realistic voice clones from just 3 seconds of audio

#6
post #4

Sure, just let me submit my voice for cloning to a closed sourced, online service of unknown provenance. What could ever go wrong?

That's why you submit politician's voice instead

Yeah, but they have you read a specific text, so not as much of an option if you use the primary demo.

Seems like a heck of a nice way to gather a training set! :)

Re: Creates hyper-realistic voice clones from just 3 seconds of audio

#7
post #5

I submitted an 8 second clip of speech and the resulting synthesized speech did not sound like the same voice. Too bad.

I hope you have a nice voice, I'll be listening to it try to sell me an extended car warranty for the next 3 months.

Re: Creates hyper-realistic voice clones from just 3 seconds of audio

#10
post #2

3 seconds? That's crazy "Huuhhhhhhhhhhh" I wonder what their "fox jump" sentence is

Default for me was: “What a beautiful day it is today, with bright sunshine and gentle breeze. Let's talk about the future of artificial intelligence.”

That said, I'm not going to be submitting a sample because [reasons]

Post reply on HN