Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

waxy.org

Post reply on HN
Print view View original

201–207 of 207 posts

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#201

Post by modeless »

Bilal_io wrote: post #196
modeless wrote: post #193

Earlier quoted context omitted.

I spent a couple of hours debugging why jupyter's debugger wasn't working right, so not exactly related to the code. I did also find and fix that utils bug you mentioned. But my current issue is that phonemizer won't find espeak even though I set the environment variables that are supposed to work. I'll figure it out eventually... Thanks for writing up your experience! Good to know it works! And it's fast!

Are you on Windows? I've had the issue and was able to fix it by manually adding these system variables: PHONEMIZER_ESPEAK_LIBRARY = c:\Program Files\eSpeak NG\libespeak-ng.dll PHONEMIZER_ESPEAK_PATH = c:\Program Files\eSpeak NG

Yes I'm on Windows at the moment. I did try setting those yesterday but I must have made a typo or something. I'll try again, thanks!

Edit: Got it working, sounds really great and is super fast as advertised. Amazing! Just tried modifying the code to make it speak more quickly and it worked first try and still sounds good too! This is way better than using Coqui TTS. Just need a few more pretrained models and the voice cloning that was in the paper and this will become super popular very quickly.

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#202

Post by HappyDaoDude »

evilduck wrote: post #132
HappyDaoDude wrote: post #106

Earlier quoted context omitted.

I have said this will initially be sold as a feature on things like Audiobooks. Pick your book, pick your reader and away it goes. The Diary of Anne Frank read by Gilbert Gottfried.

I still like getting surprised when a new or unorthodox narrator knocks it out of the park but I’d really enjoy a “salvage this purchase” exit hatch with a AI voice alternative. I’d even pay a buck or two on top of an existing purchase to automatically fix a bad narration. Head over to Audible reviews, some books are widely considered to be great books as written but the audiobook is reviewed as one to be avoided bec…

These are some very fair points. There was one book 'Electron Fire' all about the creation of the transistor, I think. I say that because never have I heard a more unenthused narrator. Makes Henry Kissinger sound like a dramatic actor.

Any AI voice could save that one. Any of them! Heck the original voice on the 1984 Machintosh could do better.

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#203

Post by throwaway290 »

BeFlatXIII wrote: post #195
LordDragonfang wrote: post #89

Earlier quoted context omitted.

If the value your community provides is low enough that it can be effectively replaced by a general purpose LLM, then it should be. The value of a community should be pushing the boundaries of knowledge, not gatekeeping it. C'mon, this is hacker news, what happened to "information should be free"?

> C'mon, this is hacker news, what happened to "information should be free"? We've had an infestation of "pay me or I won't share" types.

More like an infestation of "open = I must be able to exploit and abuse for profit" entitled SV VC types.

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#204

Post by greenhearth »

RecycledEle wrote: post #175

Wow. I just realized any one of us could redo Weird Al's songs with his lyrics, but with the original singer's voice. We could be listening to Michael Jackson singing "Just Eat It" by lunchtime. I am constantly amazed at how the new AI tech can be used. Of course this would be illegal under most countries copyright laws.

How would this be amazing? It just sounds stupid and a waste of time.

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#205

Post by rockemsockem »

leni536 wrote: post #84
rockemsockem wrote: post #82

Earlier quoted context omitted.

No one owns a voice at the moment. There is no mechanism in the US to own a voice, even your own.

A person's voice is effectively owned by the corresponding person through right of publicity, which includes voice depending on jurisdiction. California, for example: "Any person who knowingly uses another’s name, voice , signature, photograph, or likeness, in any manner, on or in products, merchandise, or goods, or for purposes of advertising or selling, or soliciting purchases of, products, merchandise, goods or se…

Voices can sound very similar, they're far from unique. Clearly if you say or somehow strongly imply that a voice belongs to a specific person then that is protected. But what if you use someone's voice, someone not especially well known, and don't make any claims about where it comes from?

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#206

Post by leni536 »

rockemsockem wrote: post #205
leni536 wrote: post #84

Earlier quoted context omitted.

A person's voice is effectively owned by the corresponding person through right of publicity, which includes voice depending on jurisdiction. California, for example: "Any person who knowingly uses another’s name, voice , signature, photograph, or likeness, in any manner, on or in products, merchandise, or goods, or for purposes of advertising or selling, or soliciting purchases of, products, merchandise, goods or se…

Voices can sound very similar, they're far from unique. Clearly if you say or somehow strongly imply that a voice belongs to a specific person then that is protected. But what if you use someone's voice, someone not especially well known, and don't make any claims about where it comes from?

It's still not necessarily legal just because you can get away with it.

Re: Weird A.I. Yankovic: a cursed deep dive into the world of voice cloning

#207

Post by rockemsockem »

leni536 wrote: post #206
rockemsockem wrote: post #205

Earlier quoted context omitted.

Voices can sound very similar, they're far from unique. Clearly if you say or somehow strongly imply that a voice belongs to a specific person then that is protected. But what if you use someone's voice, someone not especially well known, and don't make any claims about where it comes from?

It's still not necessarily legal just because you can get away with it.

I don't think it's that clear at all. You own your "likeness", but the limits of what that means is highly untested. Of the similar examples that have been tested in court thus far, the Ford v Midler case is the closest, but the court specifically called out the fact that as a singer her voice is a distinctive part of their identity, and so it is protected.

https://en.wikipedia.org/wiki/Midler_v._Ford_Motor_Co.

Post reply on HN