I need an AI that controls my body and takes me to war, killing innocent people, while I am completely oblivious in a simulated reality enjoying ice-cream.
The depressed Aussie voice is spot on - all of us Aussies sound depressed right now - high inflation, crazy house prices. I’d be shocked if the Aussie voice sounded optimistic- that’d be unrealistic.
Why not use a language model in order to calculate the emotions of a paragraph or separate certain people in the book and use that to prompt the engine to get the caricatures necessary and consistency needed
Ma man, it's so cool to see you having so much fun doing this stuff. AI has just been an awesome and always improving ride for those who jumped on the wagon.
❤🔥FREAKIN' ROCKTASTIC!!! YESSSSSSSSSSSSSSSSSSSSSSSSSS! This is gonna be an awesome tool! Thanks for sharing and making the video!!! I am so pysched about this! 🤘😎
It would be cool if the voices that are generated could be further edited. Let’s say I like one of the voices, but it’s not perfect. In this case, I want to use that voice as a template, and give the AI prompts on how to further edit it.
Great in principal but it's clearly nowhere near ready for everyday use. You'd quickly eat through your credits just in previews to finally get one that works for you.
Cool and funny, i just wanna ask to bring more real world content generation examples, you know? "How you can use this to... lets test this voice". Etc
Best ai voice for me is OpenAI’s advanced GPT-4o Voice. It’s picky about what you ask it to say, and iPhone won’t let me screen record it unfortunately. Often loses the direction I ask it to do, like ask to to do an accent emotionally and it will do it well, but then it can lose it randomly. I asked for a story and asked it to act out the parts it made some amazing voices and sounds!
I'm curious, are data labelers working for EL using other people's pro voice prints to train their text to voice AI? I have a voice on EL also, and I'm pretty sure the TOS stated that they wouldn't use it inappropriately. I guess they are training THIS thing with all our pro voice prints.
About time. All of these AI tools are just shitty or good, but overhyped MVPs built to farm money through hype but some of them do reinvest into themselves and produce updates and new features like this
kinda sad that lots of the training data probably got poisoned causing the quality of some of them to really drop.. as this is superb for indie animators and game developers.
Haha, that second Australian accent is an almost exact replica of an Australian crime podcaster (don’t know his name). Also that’s the first time I’ve heard an AI get the Australian accent right.
The trouble with this is you’re stuck with whatever emotion you promoted. GPT-4o can modify one voice in so many different ways, so we know it’s possible
And thanks to Eleven Labs, my mini series titles became possible like this one. I'd say it's the best demonstration of what Eleven Labs can do. th-cam.com/video/83zY1doT6Ok/w-d-xo.html
I really appreciate your efforts! I need some advice: My OKX wallet holds some USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How can I transfer them to Binance?
The trouble is, they all sound American... I haven't watched the entire vid yet so I'm hoping that accent is a parameter. 🙂 Wow, I wish I had 6,000,000 credits! Morty Voice 2 sounds like Bishop, the synthetic human in Aliens, "I may be synthetic, but I'm not stupid". Hurrah! Accents - the Australian accents are excellent.
I have an crazy insanity idea with no shame in it. How about combined all the complex algorithm models into a huge AI Sentient form, and put an rick sanchez characteristic personality into the humanoid robot, AI rick will get the idea from Google library Wikipedia inputs towards the algorithm bot and output the idea to create his own garage of science stuffs of his genius plans. WOW I JUST CREATED AN REAL LIFE RICK SANCHEZ? OOOOOPS! Welcome to science fiction to real life science
Can it do other languages better now? I remember it was a bit off with pronunciation in Japanese before. And had some foreigner accents. Unless I uploaded a JP Seiyuu for it to train from.
The acting is still horribly unconvincing, but here's what you do: describe the voice you want, prompt till you get one that sounds right, generate several sample clips of that same voice, now use it to train RVC (free open source). Now YOU speak the lines in that voice and it sounds like a human speaking it, provided you can act decently enough to get the inflection right. AI might be able to make good voices, but the delivery is awful and needs a human driver behind the wheel. With RVC you can do that, and for free without limits.
Man, AI voice changers are lagging behind hard. I’d like to have this kind of quality in real time. I just don’t have any use for text to speech like this.
This new feature will be crazy for animation / content creators. 11labs is about to make a whole ton of more money
I wonder when this technology will be use on movies industry, for example on Netflix, Chinese movies, or japanese tv shows for example.
i am a character animator who could speak in 20 different accents since i was a kid
This is exactly what I have been waiting for so long.
I wanted to be able to generate brand new random voices instead of just cloning existing ones.
I need an AI that can sleep for me so I can stay awake...
Genius
I’d rather have it stay awake so I can sleep 😂
@@IronicleseAndSardoniclese Right?! 😂
Go to sleep
I need an AI that controls my body and takes me to war, killing innocent people, while I am completely oblivious in a simulated reality enjoying ice-cream.
THIS IS ACTUALLY SO GOOD 19:52 LIKE IT BELONGS IN SOME OLD TH-cam VIDEO FROM 2011-2015. IT JUST SOUNDS WAY TOO HUMAN
The depressed Aussie voice is spot on - all of us Aussies sound depressed right now - high inflation, crazy house prices. I’d be shocked if the Aussie voice sounded optimistic- that’d be unrealistic.
The entire Western world right now is awful, sad.
It sounds like the guy that does crime podcasts for news corp. don’t remember his name.
This is fantastic, well done ElevnLabs. Will be perfect for my content and short stories :D:D
Why not use a language model in order to calculate the emotions of a paragraph or separate certain people in the book and use that to prompt the engine to get the caricatures necessary and consistency needed
Insane for solo indie devs :O so i have to check their Rights ect but this is a real game changer
Time to make an audiobook
Shut up don't talk about it
make a book first
@@marcusk.6223Already on that
@@marcusk.6223😂
th-cam.com/video/BrxAoPcOmgs/w-d-xo.html
Goodbye anime voice actors and voice overs for movies 😎😎😎
Ma man, it's so cool to see you having so much fun doing this stuff. AI has just been an awesome and always improving ride for those who jumped on the wagon.
its too much. I am getting excitement overload. It feels like Christmas has come early!
Awesome can't wait for the open source version
What a time to be alive
I see what you did there in 2 minutes.
This is seriously next-level tech. Elevate Labs is killing it with these custom AI voices! I am blown away! wow! insane!
❤🔥FREAKIN' ROCKTASTIC!!! YESSSSSSSSSSSSSSSSSSSSSSSSSS! This is gonna be an awesome tool! Thanks for sharing and making the video!!! I am so pysched about this! 🤘😎
8:11 that one was actually dang good
*8:11** was the best one in the whole video*
It would be cool if the voices that are generated could be further edited. Let’s say I like one of the voices, but it’s not perfect. In this case, I want to use that voice as a template, and give the AI prompts on how to further edit it.
I just listened to this video at the gym. I laughed out loud several times. Now I can’t go back to the gym. Thx Matt
Great in principal but it's clearly nowhere near ready for everyday use. You'd quickly eat through your credits just in previews to finally get one that works for you.
Bro!! the stereotypical youtubers really got me🤣🤣
8:59 This Voice 2 sounds pretty close to Rick's voice. Impressive!
Using the text-to-voice with the voice changing/voice-to-voice feature works best, I've found.
Never knew about this, thanks for bringing it to my attention.
Been waiting for this
It literally doesn't matter how powerful this technology is when it's all censored to hell.
Exactly
That's why once I see a video is about eleven labs I just turn it off.
Cool and funny, i just wanna ask to bring more real world content generation examples, you know? "How you can use this to... lets test this voice". Etc
This paired with runways Act-one will be the new landslide of viral videos.
clonemyvoice AI fixes this. Generate SCARY Real AI Voices
It’s about time!
Best ai voice for me is OpenAI’s advanced GPT-4o Voice. It’s picky about what you ask it to say, and iPhone won’t let me screen record it unfortunately. Often loses the direction I ask it to do, like ask to to do an accent emotionally and it will do it well, but then it can lose it randomly.
I asked for a story and asked it to act out the parts it made some amazing voices and sounds!
Morty: "...Why are you looking at me like that, Rick. It is making me uncomfortable..."
*adding a filter removing all screaming and yelling*
I'm curious, are data labelers working for EL using other people's pro voice prints to train their text to voice AI? I have a voice on EL also, and I'm pretty sure the TOS stated that they wouldn't use it inappropriately. I guess they are training THIS thing with all our pro voice prints.
About time. All of these AI tools are just shitty or good, but overhyped MVPs built to farm money through hype but some of them do reinvest into themselves and produce updates and new features like this
Voice 1 when you tried reverb, was really close to Andy Serkis 🤩
Can you apply these voices to a sung track to replace the vocal tone with that of the newly designed model? That's what I'm looking for...
Great video!
Regular voice cloning is sooooooo much better imo. I feel like this would funnel what I want into underwhelming results until the 50th try.
Love Screaming Volcano Voice 2. Haha!
Really need some competition here! How else will this become cheaper?
The third Aussie accent sounded like a current affairs show host - awesome.
Its not as good as they make out in their polished deno at the start.
It's not good at all. Just sounds like normal people no matter the prompt and the voice acting is not there
It's going so fast!!
kinda sad that lots of the training data probably got poisoned causing the quality of some of them to really drop.. as this is superb for indie animators and game developers.
5:22 DUDE! this is straight outta Red Dead Redemption 2
WOW, this is great
The TH-cam channel “Audioviser” appears to be using your elevenlabs voice, or one that sounds strikingly similar to yours
10:20 voice 1 and voice 3 reminded me on kamala
Emotions have been out for over a year on PlayHT and revoicer? Frustrating they not gone down this path :(
You can use the "burp" as a stand in spacer, in an audio editor just add a burp
Haha, that second Australian accent is an almost exact replica of an Australian crime podcaster (don’t know his name). Also that’s the first time I’ve heard an AI get the Australian accent right.
Stoked!
I wish they had a screen reader like speechify for reading documents and web pages etc
10:11 You don't actually know whether this prompt worked or not, because you made the first sentence so long that you never got to the end of it.
true
I don't think it would have worked anyways, but it is definitely frustrating that he didn't even check if it did
But I prefer to use Speech to Voice, so I can animate the vocals how I want. Can we do that? Or only text
Sounds like either Ahsoka or Padmé (Clone Wars) at 5:42!
I saw someone using your voice on TikTok recently. haha
18:00 thats Trevor from GTA V!! LMAO
I see using this with KLING's lip-syncing feature
In case u didnt know - this is Judd Nelson's nephew
We should be able to use this to generate vocaloid voice banks oh my god..
Lmao that's Rick from different universes for sure!!
Can you tell me the best AI for lip sync in non human characters? Thanks
The trouble with this is you’re stuck with whatever emotion you promoted. GPT-4o can modify one voice in so many different ways, so we know it’s possible
That Rick voice sounded like Joe Rogan trying to imitate Rick Sanchez.
And thanks to Eleven Labs, my mini series titles became possible like this one. I'd say it's the best demonstration of what Eleven Labs can do. th-cam.com/video/83zY1doT6Ok/w-d-xo.html
I really appreciate your efforts! I need some advice: My OKX wallet holds some USDT, and I have the seed phrase. (alarm fetch churn bridge exercise tape speak race clerk couch crater letter). How can I transfer them to Binance?
Another Ai banger!
Wanted to check how it performed in different languages but it seems there's no trial, it requires a subscription to try it, bummed.
This new 11 labs AI voice designer, is it free or do you have to pay for it?
Does hallo 2
The trouble is, they all sound American... I haven't watched the entire vid yet so I'm hoping that accent is a parameter. 🙂 Wow, I wish I had 6,000,000 credits! Morty Voice 2 sounds like Bishop, the synthetic human in Aliens, "I may be synthetic, but I'm not stupid". Hurrah! Accents - the Australian accents are excellent.
lol i think you got reverb, but you wanted to hear an echo
That second voice is literally elfo from, enchantment lol
8:31 Voice 3 sounds like Rick when he was middle aged.
I was underwhelmed. Couldn't even do a southern twang.
I have an crazy insanity idea with no shame in it. How about combined all the complex algorithm models into a huge AI Sentient form, and put an rick sanchez characteristic personality into the humanoid robot, AI rick will get the idea from Google library Wikipedia inputs towards the algorithm bot and output the idea to create his own garage of science stuffs of his genius plans. WOW I JUST CREATED AN REAL LIFE RICK SANCHEZ? OOOOOPS! Welcome to science fiction to real life science
12:38 that sounds like Duke Nukem
that second try at the goblin sounded like Trump near the end of voice 1
14:30 that sounds like Andy Serkis!!
Totally!
This clearly still needs a lot of work. Some examples are great, not definitely not all of them.
Can it do other languages better now? I remember it was a bit off with pronunciation in Japanese before. And had some foreigner accents. Unless I uploaded a JP Seiyuu for it to train from.
17:20 something about that voice destroyed my tinnitus.
Very good
These were not the droid voice generators I was looking for...
The acting is still horribly unconvincing, but here's what you do: describe the voice you want, prompt till you get one that sounds right, generate several sample clips of that same voice, now use it to train RVC (free open source). Now YOU speak the lines in that voice and it sounds like a human speaking it, provided you can act decently enough to get the inflection right. AI might be able to make good voices, but the delivery is awful and needs a human driver behind the wheel. With RVC you can do that, and for free without limits.
I really hope Voice Design can use Speech to Voice
Even if it won't be, and I don't know: record the one you drew and then add it to your voices
Man, AI voice changers are lagging behind hard. I’d like to have this kind of quality in real time. I just don’t have any use for text to speech like this.
woah, Nicholas cage at 4:59... very interesting.
8:58 sounds like a blend of Joe Rogan and Rick Sanchez
Eleven Labs needs to drop the price & create a middle between pro how do we go from $22 to $99, give us a middle 49.999
no sound effects?
The copyright censorship ruins everything but I get it, they don’t want to get sued by Nintendo or some other scummy corporation.
sad, i thought it was local gen
Thats the end for the voice acting industry. The 1st industry completely ended
Ill try to find it - there IS a TH-cam channel who uses your voice. I was sure it is just another one of yours.....😮
Hahahah, Temu SpongeBob 😆🧽
8:56 - Rick, voiced by Joe Rogan.
How TF does one get 6 million tokens?