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

151–160 of 207 posts

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

#151

Post by fomine3 »

vunderba wrote: post #123
minimaxir wrote: post #98

Earlier quoted context omitted.

Voice acting is more than just talking into a microphone. It's a skill not limited to the quality of voice.

You could have made that argument more effectively in the past when voice actors had to be able to mimic multiple voices (Dan Castlenetta, Mel Blanc, etc.). Nowadays, we're seeing more and more shows where the voices of the characters are just... the normal voice of the voice actor. Of course it's not totally devoid of skill, you need to be able to emote, inflect, and convey emotion, but the bar is far far lower.

I argue that emote is more important skill than switching multiple voice character, though latter contributes get more jobs

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

#152

Post by totetsu »

blagie wrote: post #100
hinkley wrote: post #73

> Artifacts aside, it sounds like Michael Jackson doing a Weird Al impression?! Every line has a distinctly “white and nerdy” vibe: it loses any seriousness and edge, exaggerating words for comic effect and enunciating lyrics really clearly so the punchlines can be heard. No, it sounds like someone doing doing an impression of Weird Al doing an impression of Michael Jackson. Someone whose mom told them they were spec…

... they're good enough. I have an accent. If not for that, I'd be a great presenter. If I could translate my voice into a poor Neil deGrasse Tyson, a poor Patrick Steward, a poor Carl Sagan, a poor Morgan Freeman, etc., my presentations would be... better.

Finally a way to not have to fix societies Prejudices just give everybody the tools to emulate the ideal of perfection no matter what color their skin or what their accent sounds like.

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

#153

Post by fragmede »

toddmorey wrote: post #145
mecredis wrote: post #3

It's kind of wild that these tools just transfer a copy of these models every time they're spun up (whether it's to a Google Colab notebook or a local machine.) This must mean Hugging Face's bandwidth bill must be crazy, or am I missing something (maybe they have a peering agreement? heavily caching things?)

Is hugging face just a model repository like GitHub is a code repository? Seems you can rent compute both cpu & gpu, but you are right that most models seem to be run elsewhere.

Yes, exactly.

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

#154

Post by lmm »

codetrotter wrote: post #34
simonw wrote: post #2

I did not know about this: "The center of the A.I. cover songs community is a massive 500,000+ member Discord called A.I. Hub, where members trade new tips, tools, techniques, and links to their original and cover songs."

Me neither. That’s what’s so weird about the internet. Imagine half a million people out in the streets together. You’d definitely notice that. Meanwhile, we can have these massive online communities and you’d never know unless you accidentally stumbled across it or someone told you about it.

> Imagine half a million people out in the streets together. You’d definitely notice that.

In the streets, sure. Meeting up at out of town conference centers a few times a year, probably not. Most real communities have always been "dark matter" to those outside them; Discord working the same way feels more authentic than most of the internet.

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

#156

Post by NoMoreNicksLeft »

squeaky-clean wrote: post #91
NoMoreNicksLeft wrote: post #80

Earlier quoted context omitted.

I like to read with my eyes, not listen. I honestly have no idea how long an audio book is, hours-wise. I've seen a few for download, and they're always like hundreds of meg, if not over a gig. And that's in mp3, where it should be compressed heavily.

In my audible library, the shortest is the first Hitchhiker's Guide to the Galaxy a 5h51m. The longest is The Power Broker at 66h9m. Most of the books I have are in the 15-25 hour range, but I also have a lot of fantasy stuff that gets near 50 hours (Game of Thrones, Brandon Sanderson...).

Well, then we're talking $300 to have ElevenLabs do a single GoT book, but maybe as many as 8 books for HHGTG-style stuff.

That's just not good value. Was sort of my point.

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

#157

Post by sublinear »

minimaxir wrote: post #10

This article only covers the musical aspects of AI voice cloning, but there's another dynamic to AI voice cloning that's more complicated: replacing general voice actors in movies/video games/anime (example: https://www.axios.com/2023/07/24/ai-voice-actors-victoria-at... ) Unlike musicians who can't be replaced without significant postprocessing, have enough money to not be impacted by competition, and have legal mus…

I have a different take on this.

AI voice is cheaper, but it's also a more boring and generic performance. There is zero progress made towards any sort of creative AI that produces good unique work.

The market for this then is small businesses who can't afford a professional voice actor. AI is opening up new markets, not killing the jobs of the truly talented.

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

#158

Post by modeless »

lhl wrote: post #23
satvikpendem wrote: post #9

What's the best open source text to speech? Eleven Labs and others are interesting but closed source. I want to use them mainly for audiobooks as I have a lot of ePubs and I'm just using the basic Google text to speech voices on my Android, via Moon+ Reader. It works fine but it's still more robotic than state of the art.

For neutral sounding very fast/efficient voices, I find Coqui TTS VITS models to be very good. For slower, more expressive voice or voice cloning I think the Coqui TTS XTTS is good (or you can look at the mrq/tortoise-tts). I'm still awaiting a StyleTTS2 implementation. The audio samples sound top notch: https://styletts2.github.io/

You're in luck, the code dropped 6 hours ago :) https://github.com/yl4579/StyleTTS2

Looks promising, I'm going to check it out too! MIT license, even! If it's fast enough for real time, it could be the new best option. The paper claims faster inference than VITS...

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

#159

Post by chefandy »

sublinear wrote: post #157
minimaxir wrote: post #10

This article only covers the musical aspects of AI voice cloning, but there's another dynamic to AI voice cloning that's more complicated: replacing general voice actors in movies/video games/anime (example: https://www.axios.com/2023/07/24/ai-voice-actors-victoria-at... ) Unlike musicians who can't be replaced without significant postprocessing, have enough money to not be impacted by competition, and have legal mus…

I have a different take on this. AI voice is cheaper, but it's also a more boring and generic performance. There is zero progress made towards any sort of creative AI that produces good unique work. The market for this then is small businesses who can't afford a professional voice actor. AI is opening up new markets, not killing the jobs of the truly talented.

This is the case for all generative "art." The people at the high end will still get paid well. The people who specialize in more utilitarian or low budget tasks in higher volume will take the biggest hit. Nobody who'd planned on hiring Morgan Freeman to do a voice over will be tempted to use AI Morgan Freeman instead.

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

#160

Post by mckirk »

darkerside wrote: post #69
mock-possum wrote: post #61

Earlier quoted context omitted.

Yeah that’s kind of the theme of the YouTube channel - I think it’s hilarious honestly, but maybe you have to go into it knowing what to expect.

Yeah, based on the parent, and the genius of the musicians involved, I was expecting something more than the sum of its parts. Hurt is an incredibly powerful song, and the Cash rendition imbues it with another beautiful layer. As a joke, I can see it being funny, but it was a jarring way to experience it.

I'm sorry, I probably should have advertised that better.
Post reply on HN