Hacker News new | ask | show | jobs
by an_ko 1037 days ago
From a quick read of the code, it seems like all this does is shift pitch; it doesn't change resonance or anything else that affects how your voice sounds. So it's great for sounding like a chipmunk or a demon, but not that useful for sounding like a different person.

Looks like it uses libsox internally. You can also use command-line SoX utilities to get the same effect. For example, this plays your microphone back at you, pitch shifted and with a delay:

  play '|rec -p pitch +400 40 delay 5 5'
(To be clear, I don't mean to beat down anybody's pet project. Just spreading related information. There's very little accessible documentation of Linux audio stuff.)
2 comments

> So it's great for sounding like a chipmunk or a demon, but not that useful for sounding like a different person.

RVC is what you're looking for. There's lots of tooling around it.

edit: This is the repo you're looking for: https://github.com/RVC-Project/Retrieval-based-Voice-Convers...

I'm regularly struck by how much of technical Japanese is literal transliterations of loanwords. In the diagram at https://github.com/w-okada/voice-changer#vc-client-%E3%81%A8... , I see "user", "client (browser)", Docker "container", "server", "Host" PC, "speaker".

... I don't know what the label says on the link between the client and server, though, the katakana is "bo i che n" and I can't think of what that transliterates to. Maybe it's a loanword that's not from English?

Short for "voice (boi) changer (chen)"
At least that's what https://github.com/RVC-Project/Retrieval-based-Voice-Convers... links to

Realtime Voice Conversion Software using RVC : w-okada/voice-changer

Do you have a link? It appears impossible to Google something this common.
> There's very little accessible documentation of Linux audio stuff.

The classic information-through-IRC these days.