News for hackers. Stuff that matters.
Re:Show HN: Clone your voice and speak a foreign language by alonmln on Monday January 03, 2022 @03:47PM (#29786625)
Cool, it's impressive how much can it do with a short sample, although this seems like an easy way for end users to deep fake their friends / enemies saying something.
Re:Show HN: Clone your voice and speak a foreign language by kdavis on Monday January 03, 2022 @03:53PM (#29786713)
Currently we’re looking at possible solutions, see for example here[1]. If you have suggestions, feel free to chime in!

In the demo we specifically disallowed bulk uploads to hinder such abuses.

[1] https://github.com/coqui-ai/TTS/discussions/1036

Re:Show HN: Clone your voice and speak a foreign language by tiborsaas on Monday January 03, 2022 @05:49PM (#29788166)
I tested it with your comment: https://sndup.net/mghy/ :)

It's also a new possibility to somewhat personalize the text to speech engines. The above example is not really close to my voice.

Re:Show HN: Clone your voice and speak a foreign language by Philip-J-Fry on Monday January 03, 2022 @05:33PM (#29787955)
Maybe the solution is to have a randomly generated paragraph of text to read which expires in short amount of time. So you can't predict it and you don't have enough time to splice together a fake reading from something else.
Re:Show HN: Clone your voice and speak a foreign language by Gigachad on Monday January 03, 2022 @07:38PM (#29789307)
The problem with any anti abuse measure is someone can create another project which does not have any of this. There are a handful of projects which can do pretty good voice synthesis right now. It would be about as easy as getting a consensus for all photo editing tools to place a watermark on the image to prevent abuse.