Elevenlabs.io - AI Generate anyone's voice with a minute of audio saying how much they hate trannies

  • 🐕 I am attempting to get the site runnning as fast as possible. If you are experiencing slow page load times, please report it.
Spruce Supremacist said:
It seems they recently censored the AI dubbing part of the website. Before this you'd get some hilarious translations, with some ENG to RUS ones becoming memes of their own, like Chester Stone vids for example:
View attachment 6418082

...but now, whenever it detects a naughty word like "nigger" it doesn't even try and substitute it with something similarly vulgar yet inoffensive, but literally says "censored".
It truly feels like an unwritten rule at this point, that any and all new public web AI solutions will progressively get more and more neutered the longer they're up and running.
Click to expand...
Stuff like RVC, while not perfect, seems to work still on giving you complete freedom of what you want characters to say provided you have the data for it.
 
  • Feels
Reactions: Cowboy Kim and anustart76
IamnottheNSA said:
Just plain old RTX 3060 12GB. Took me a whole day to train up my model.
I can share it by the way, along with the voice clips that I used.
Click to expand...
Gotcha, I have a 2060 12gb so I would expect my own attempt to go even more slowly. If you could share your model that would be cool!
 
Necro'ing the thread for something, somewhat related. When Eleven Labs originally came out, 4chan found it used it for all kinds of shit until it was nerfed to death, I remember downloading almost all of it from a .zip file.

I have an archive of almost everything they did with it (mainly stuff from /tv/ & a few things from /co/ & /v/). I don't even know what most of these say (There's a surprising lot to listen to), apart from whose voice it is & what the basic context of some of these might be. I'm cleaning some storage & I'm putting it here as an archive.

Edit: I've tried twice but it keeps making a duplicate upload on it's own.
 

Attachments

Last edited:
  • Winner
  • Informative
Reactions: IamnottheNSA, ZMOT, Cowboy Kim and 5 others

il_1140xN.5665100509_egbz.png
 
  • Thunk-Provoking
  • Like
Reactions: jray4559, IamnottheNSA, ZMOT and 1 other person
NSJAP said:
https://x.com/fifteenai/status/1865439846744871044

View attachment 6856704
Click to expand...
Jesus fucking words batman...
So TL;DR he gives a bit of background as to how the site came to be, some retrospection, and how ultimately it was Copyright notices that got his website shut down (which is odd because non of his previous tweets ever alluded to law takedown notices and that "it was just technical problems, I'll get it back up eventually trust me bro"). And that he still plans on bringing it back someday "his way". Like Rembrant above says, I don’t know how he's going to upstage tools like ElevanLabs or RVC, and while the former is paywalled to a degree, the latter lets you clone and generate voicelines for free if you know what you're doing.
I guess ultimately it comes down to him providing a free, convenient AI TTS voice cloning service to people, no strings attached, so whatever plans he has for it he's definitely gonna be in it for the long haul.

EDIT: Archive of link above: https://ghostarchive.org/archive/MDbtv
As for keeping people in the dark on Patreon, he says he "never wanted to make money off his project" and that this was just a way of giving him handouts because people felt they had to pay him, so he got someone else to make it for him. He also didn't want to outright say to his paypigs what was going on in fear of opening up to other lawsuit fuckery I guess?
CqmVXHs9KS.png
632RtNyZoT.png
 
Last edited:
  • Feels
Reactions: Xenomorphs Are Cute and NSJAP
He's been collecting a cool $200 a month for doing literally nothing for 4 years, never shut the thing down despite knowing he can't continue the project and now he's saying he "never wanted to make one anyway"? This doesn't add up.
 
  • Like
Reactions: Cowboy Kim
IamnottheNSA said:
Book 9 done:
View attachment 5948137
And that's it. Gotta say, having another video card really helped speed things up - while I was editing one chapter, I had a separate machine generating the others. This is why it only took me 4 months to complete this, as opposed to initially expected 9 months.

Also, here's the entire thing, all 39-and-a-half hours of it (uploaded to google drive, because it is impossible to upload 850 MB of audio here):
Click to expand...
Google Drive took down your link for "violating Terms of Service", cowards.
 
Ars Technica: Eerily realistic AI voice demo sparks amazement and discomfort online (archive)
In late February, Sesame released a demo for the company's new Conversational Speech Model (CSM) that appears to cross over what many consider the "uncanny valley" of AI-generated speech, with some testers reporting emotional connections to the male or female voice assistant ("Miles" and "Maya").
Click to expand...
1. Microphone permission is required. 2. Calls are recorded for quality review but not used for ML training and are deleted within 30 days. 3. By using this demo, you are agreeing to our Terms of Use and Privacy Policy. 4. We recommend using Chrome (Audio quality may be degraded in iOS/Safari 17.5).
Click to expand...
 
  • Informative
Reactions: Cowboy Kim
mentally retarded user said:
Wasted everyones time award.

I'm calling this the brony curse and it will be a real thing when this happens to the pony diffusion guy and he never ships v7.
Click to expand...
15's a fucking nigger I personally know a guy who worked for him for a long time, and I interacted with him indirectly for around a year. (and I think I saw him in a hall last harmonycon) I believe v7 will come out.
 
  • Informative
  • Thunk-Provoking
Reactions: Cowboy Kim, Verpa Teutonica Ingens and NSJAP
You must log in or register to reply here.
Back