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

[Puff]

What character's voice is that supposed to be?

I'm not CERTAIN, but the clips from the generic places to grab them for Dumbledore sound nothing like him because there's music and background noise that hasn't even been attempted to be removed.

 

[Serbian Peacekeepers]

Interesting to note is he seems to believe that Eleven Labs is using a further trained version of Tortoise to run their service. Not sure whether he's onto something or if he's just sneeding.

That's been a working theory for awhile, i saw someone on /g/ say 11labs was trained with 50k hours of audio book content, which is why its so good at what it does.

 

[purpleflurp]

Posted this in his thread, but here's a deepfake of Dream reading the OP about him.

In total, it took about 40 minutes from start to finish, with most of that time coming from needing to track down his music playlist. Total sample was 14 seconds of him reading out a TommyInnit tweet.

At the current rates, it'll cost me around $2 to render the audio for a 30-40 minute video essay, with some variance for retakes. Brb, gonna go make an LS Mark ripoff.

 

[$80 Nude Haircut]

 

[NSJAP]

 

[Toolbox]

In the span of, what? Two years? In the span of two years, we've seen AIvoice, drawing, and writing come fully into their own. You could literally make a cartoon show of professional quality for nothing. It reminded me of the heady days back in 99 2000 where the internet put culture and knowledge at man kinds fingertips. Art, philosophy and science where once you had to go to a university or major urban library, costing a fortune could be enjoyed by the entire human race via modem.

Then boof. the DMCA

Now we're back here again. This tech is all censored to hell.

And why? Because they can't have you make your own Simpsons or South Park. Because that is one of the foremost levers of power in society. Media. I'm dreading the new DMCA, and what other draconian, abusive powers it will give figures. Just look at the damage to fair use DMCA strikes has caused.

It'll be harder for this to make any more impact when there are text gens and audio gens you can easily run on consumer hardware like with stable diffusion. Text gen will take longer to get there but the push is there.

 

[Iron Jaguar]

I just do it in my own voice

 

[Michael Wade]

Question. Can you take a voice in another language and make it speak clear English?

 

[Puff]

Question. Can you take a voice in another language and make it speak clear English?

I've not tried, but you get generic voices when the input audio is bad so I'd assume that. Who should I try

 

[AnOminous]

I've not tried, but you get generic voices when the input audio is bad so I'd assume that. Who should I try

Hitler would probably have interesting results.

 

[Puff]

Hitler would probably have interesting results.

This set is likely effected more by audio input quality than language. I used a 1/30/1940 speech as the sample and the only preprocessing I put in was deleting crowd noises and cheering. Here are three different attempts using a random.txt (switched putinbots for stalinbots since it seemed topical) as text with different settings. The middle one is a woman for some reason.

 

[Puff]

Shinzo Abe using a Japanese language speech as an input. Much cleaner starting audio. The long pauses are consistent with the input data btw. He's probably waiting for a live translation or something that isn't in my audio. This one was much more consistent across different attempts, so I'm only posting one file.

I couldn't make the audio upload by editing previous, sorry for double post.

 

[Michael Wade]

Fascinating. It's not perfect but I would love to do some stuff with hammy japanese voice actors.

 

[Muu]

 

[Mysterious Autist XX]

Fascinating. It's not perfect but I would love to do some stuff with hammy japanese voice actors.

We talking Norio Wakamoto ham, Nobuyuki Hiyama hot bloodedness or what?

 

[Michael Wade]

We talking Norio Wakamoto ham, Nobuyuki Hiyama hot bloodedness or what?

It's a start. I hesitate to pay them money but I may have to if they have the best quality and least amount of hassle to set up

 

[Colon capital V]

Shinzo Abe using a Japanese language speech as an input. Much cleaner starting audio. The long pauses are consistent with the input data btw. He's probably waiting for a live translation or something that isn't in my audio. This one was much more consistent across different attempts, so I'm only posting one file.
View attachment 4761324
I couldn't make the audio upload by editing previous, sorry for double post.

this will be realllllly interesting in the near future, to know that shit like anime dubs or hell even foreign shows being dubbed over with AI voices using the VAs' country of origin will be really fascinating to witness.

Now Cory in the House Anime will be within our grasp in no time.

 

[Slur Generator]

this will be realllllly interesting in the near future, to know that shit like anime dubs or hell even foreign shows being dubbed over with AI voices using the VAs' country of origin will be really fascinating to witness.

Now Cory in the House Anime will be within our grasp in no time.

Its kind of impossible to separate someones speech paters from the language. People talking in different languages can sound totally different. I know for sure I do. People have mentioned that my voice is deeper when I speak english.

Anime where they speak like the advisor from shogun 2 total war would be the funniest shit though.

 

[purpleflurp]

This set is likely effected more by audio input quality than language. I used a 1/30/1940 speech as the sample and the only preprocessing I put in was deleting crowd noises and cheering. Here are three different attempts using a random.txt (switched putinbots for stalinbots since it seemed topical) as text with different settings. The middle one is a woman for some reason.
View attachment 4760938
View attachment 4760944
View attachment 4760964

This mimics the issue I had with Reagan’s voice. I’m looking into possible fixes, but for now try the Hitler actor from Downfall’s voice

 

[Puff]

I caught a 'tism and made a thing. It's not done yet, but I have all of the audio generated. Just need to do editing and regenerate the shit parts. I started getting lazy after 5 days after work of playing with this, but here's the first hour. I'll probably not finish it or just throw up the unfinished parts as a file.

Spoiler: Jordan Peterson Reads INDUSTRIAL SOCIETY AND ITS FUTURE paragraphs 1-92

Intro
View attachment 4742377
2 - THE PSYCHOLOGY OF MODERN LEFTISM
View attachment 4742396
3 - FEELINGS OF INFERIORITY
View attachment 4742416
4 - OVERSOCIALIZATION
View attachment 4742466
5 - THE POWER PROCESS
View attachment 4742493
6 - SURROGATE ACTIVITIES
View attachment 4742516
7 - AUTONOMY
View attachment 4742572
8 - SOURCES OF SOCIAL PROBLEMS
View attachment 4742592
9 - DISRUPTION OF THE POWER PROCESS IN MODERN SOCIETY
View attachment 4742630
10 - HOW SOME PEOPLE ADJUST
View attachment 4742668
11 - THE MOTIVES OF SCIENTISTS
View attachment 4742684

It's not perfect, but I'd say fair for a first go. Learned a lot about how this stuff likes to be handled. I left in some misspelling because they were used multiple times and might have been intentional. There was a shitton of editing and certain words will get cut off at the end of a generation no matter what you do.

Moar Parts

Spoiler: audio

12 - THE NATURE OF FREEDOM

13 - SOME PRINCIPLES OF HISTORY

14 - INDUSTRIAL-TECHNOLOGICAL SOCIETY CANNOT BE REFORMED

15 - RESTRICTION OF FREEDOM IS UNAVOIDABLE IN INDUSTRIAL SOCIETY

16 - THE ‘BAD’ PARTS OF TECHNOLOGY CANNOT BE SEPARATED FROM THE ‘GOOD’ PARTS

Edit: I might have made a major duplication, or the schizo writing repeats itself.