Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Eleven v3

elevenlabs.io

Post reply on HN
Print view View original

101–110 of 168 posts

Re: Eleven v3

#101

Post by vlovich123 »

SoftTalker wrote: post #51
ricketycricket wrote: post #28

From the example: "Oh no, I'm really sorry to hear you're having trouble with your new device. That sounds frustrating." Being patronized by a machine when you just want help is going to feel absolutely terrible. Not looking forward to this future.

Yeah it's irritating enough when humans do it, it's so transparently insincere. Just help me with my problem. I guess I am just old now but I hate talking to computers, I never use Siri or any other voice interfaces, and I don't want computers talking to me as if they are human. Maybe if it were like Star Trek and the computer just said "Working..." and then gave me the answer it would be tolerable. Just please cut o…

I agree it seems transparently insincere yes, but the reason it’s done is because it works on some people who either don’t detect it or need it as politeness norms and the ones who see it as insincere just ignore it and move on. Thus net, you win by doing this because it rarely if ever costs you and thus you only have upside.

Re: Eleven v3

#102

Post by throwup238 »

steve_adams_86 wrote: post #100
mrkstu wrote: post #69

Earlier quoted context omitted.

Better by a mile than most anime voice work, but lacks the detail that a good voice narrator has on an audio book.

Yes, I couldn't bear this for an entire audio book.

Wait until you hear Burt Reynolds and Richard Feynman narrate the Fifty Shades of Gray.

Re: Eleven v3

#105

Post by vessenes »

lharries wrote: post #17
ianbicking wrote: post #12

I've been using OpenAI's new models a lot lately ( https://www.openai.fm/ )... separating instructions from the spoken word is an interesting choice, and I'm assuming also has a lot to do with OpenAI/GPT using "instructions" across their products, and maybe they are just more comfortable and familiar generating the data and do the training for that style. Separate instructions is a bit awkward, but does allow mixing…

> The result with OpenAI feels much less predictable and of lower production quality than ElevenLabs Thank you Ian! Credit to our research team for making this possible For the prosidy, if you choose an expressive voice the prosidy should be larger

Ninjaing in to ask: is v3 on the roadmap for your voice agents? The quality increase is huge.

Re: Eleven v3

#106

Post by vessenes »

delgaudm wrote: post #22
artninja1988 wrote: post #2

Sounds absolutely amazing, like 99% indistinguishable from real professional voice actors to me. I couldn't find any pricing though. Anyone know what they charge for it?

Ouch. Professional Voice Actor here.

Time to license your voice to Elevenlabs and sit back and enjoy the good life!

Re: Eleven v3

#107

Post by ipsum2 »

palisade wrote: post #61

For reference in case anyone is wondering, it is based on: https://github.com/152334H/tortoise-tts-fast The developer of tortoise tts fast was hired by Eleven labs.

The former does not imply the latter.

Re: Eleven v3

#108

Post by pu_pe »

drag0s wrote: post #10

English sounds really great, congrats! other languages I've tried doesn't sound that good, you can hear a strong english accent

For Portuguese, interestingly enough one of the voices (Liam) has a Spanish accent. Also, the language flag is from Portugal, but the style is clearly Brazilian Portuguese.

Re: Eleven v3

#109

Post by stavros »

riebschlager wrote: post #31

I didn't see anything about this in the documentation or prompting guide, but... is it supposed to be able to sing? Since I am a fundamentally unserious person, I copied in the Friends theme song lyrics into the demo and what came out was a singing voice with guitar. In another test, I added [verse] and [chorus] labels and it's singing acappella. [1] and [2] were prompted with just the lyrics. [3] was with the verse/…

Oh wow, it's interesting that it sings, but the singing itself is terrible! That's maybe more interesting, it sings exactly like a human who can't sing.

Re: Eleven v3

#110

Post by stavros »

ianbicking wrote: post #12

I've been using OpenAI's new models a lot lately ( https://www.openai.fm/ )... separating instructions from the spoken word is an interesting choice, and I'm assuming also has a lot to do with OpenAI/GPT using "instructions" across their products, and maybe they are just more comfortable and familiar generating the data and do the training for that style. Separate instructions is a bit awkward, but does allow mixing…

That's the reason I don't use Elevenlabs and go with worse solutions, I don't want to feel like I'm paying for a whole chunk of compute, whether I use it or not, every single month, with only the option to pay for a yet larger chunk of compute if I run out.

Terrible pricing model, in my opinion.

Post reply on HN