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

81–90 of 207 posts

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

#81

Post by hinkley »

Reventlov wrote: post #60
nemo44x wrote: post #35

Earlier quoted context omitted.

It sounds like Weird Al trying to be Michael Jackson trying to be Weird Al.

As a non native speaker, it does sound a bit like Michael Jackson imo…

Sometimes I’ll watch a movie with voiceover work, where some character has a very specific accent, and I’ll be watching along for twenty minutes and the VA will let slip just a couple syllables of their real voice and my ears will prick up and I’ll think, hey I know this guy. Isn’t that… oh the guy from the thing. From , no wait I mean ? Yes, it is.

That’s what this sounds like. Five syllables of Michael Jackson while he’s trying to be Action Hero or Big Villain, or Funny Sidekick (a problem Eddie Murphy has never had, all evidence from Coming to America notwithstanding).

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

#82

Post by rockemsockem »

dylan604 wrote: post #40
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…

> and their voicework is owned by their clients who may not be as incentivised in protecting the VO. The work product produced by their voice for fulfilling the contract is owned. No corp owns someone else's voice.

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

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

#83

Post by RajT88 »

callalex wrote: post #55
pdntspa wrote: post #25

Earlier quoted context omitted.

I really wish I could configure this crap to cache somewhere other than my C: drive Or better yet, how about asking me where I want to store my models?

I haven’t used windows in a while but I thought it supported some form of cross-volume symlink? Or at least mounting an image stored on another volume to an arbitrary path.

Links in windows are a thing, but not well known. I must have been using Windows for close to 20 years before I realized they were in there.

https://learn.microsoft.com/en-us/windows/win32/fileio/hard-...

https://learn.microsoft.com/en-us/windows-server/administrat...

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

#84

Post by leni536 »

rockemsockem wrote: post #82
dylan604 wrote: post #40

Earlier quoted context omitted.

> and their voicework is owned by their clients who may not be as incentivised in protecting the VO. The work product produced by their voice for fulfilling the contract is owned. No corp owns someone else's voice.

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 services, without such person’s prior consent, or, in the case of a minor, the prior consent of his parent or legal guardian, shall be liable for any damages sustained by the person or persons injured as a result thereof."

https://leginfo.legislature.ca.gov/faces/codes_displaySectio....

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

#86

Post by EGreg »

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…

Please do. Some of us critique capitalism

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

#87

Post by follower »

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.

> What's the best open source text to speech?

I haven't re-evaluated OSS TTS options for a few months but from my own experience earlier in the year I've been pleased with the results I've gotten from Piper:

* https://github.com/rhasspy/piper

I've primarily used it with the LibriTTS-based voices due to their license but if it's for personal local use you can probably use some of the other even higher quality voices.

The official samples are here: https://rhasspy.github.io/piper-samples/

Here's a small number of pre-rendered samples I've used that were generated from a WIP Piper port of my Dialogue Tool[0] project: https://rancidbacon.gitlab.io/piper-tts-demos/

While it's not perfect & output quality varies for a number of reasons, I've been using it because it's MIT licensed & there's multiple diverse voice options with licenses that suit my purposes.

(Piper and its predecessors Larynx & Mimic3 are significantly ahead of where other FLOSS options had been up until their existence in terms of quality.)

[0] https://rancidbacon.itch.io/dialogue-tool-for-larynx-text-to...

----

Edit to add links to some of my notes related to FLOSS TTS, in case they're of interest:

* https://gitlab.com/RancidBacon/notes_public/-/blob/main/note...

* https://gitlab.com/RancidBacon/notes_public/-/blob/main/note...

* https://gitlab.com/RancidBacon/notes_public/-/blob/main/note...

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

#88

Post by rcarr »

supriyo-biswas wrote: post #16
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…

HN isn't the only community to write for. While most people here seem to be unsympathetic to such job concerns, unconventional articles do hit the front page from time to time. I'd like to read it, in any case.

+1, I would also like to read it

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

#89

Post by LordDragonfang »

throwaway290 wrote: post #68
LordDragonfang wrote: post #41

Earlier quoted context omitted.

Yeah, one of the "worst" (good for metrics, bad for legibility) parts of the trend of moving to discord for any sort of online community is that you have to "join" the community to even view any of the resources ensconced within. Meaning it's poorly indexed (discord search is okay, but not great) and not available at all to external crawlers.

If this community was available for crawling then LLM would crawl it and there would be no value in participating in the community because you can just ask the LLM about all that, no?

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"?

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

#90

Post by rcarr »

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…

It's sad if the only way voice actors are going to be able to make a living is by doing stuff like Critical Role on Youtube. I love Critical Role but it likely wouldn't be the same if those guys hadn't spent years honing their craft. Watching people play RPGs online has replaced a lot of my streaming viewing now, but the market is much smaller and I imagine it can only sustain a much smaller pool of creatives than the current voice over market can.
Post reply on HN