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

11–20 of 168 posts

Re: Eleven v3

#11

Post by dustincoates »

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

The French one sounded like an Alabaman who took a semester of college French.

But the English sounds really good.

Re: Eleven v3

#12

Post by ianbicking »

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 general instructions with specific instructions. Like I can concatenate output-specific instructions like "voice lowers to a whisper after 'but actually', and a touch of fear" with a general instruction like "a deep voice with a hint of an English accent" and it mostly figures it out.

The result with OpenAI feels much less predictable and of lower production quality than Eleven Labs. But the range of prosidy is much larger, almost overengaged. The range of _voices_ is much smaller with OpenAI... you can instruct the voices to sound different, but it feels a little like the same person doing different voices.

But in the end OpenAI's biggest feature is that it's 10x cheaper and completely pay-as-you-go. (Why are all these TTS services doing subscriptions on top of limits and credits? Blech!)

Re: Eleven v3

#13

Post by lharries »

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

Can you try with a voice that was trained on that language? This research preview is more variable based on the voice chosen

Re: Eleven v3

#14

Post by k__ »

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

German sounds okay.

Re: Eleven v3

#15

Post by lharries »

wewewedxfgdf wrote: post #9

I did not see an British accent example. Generally it appears the TTS systems all do US accents and the British accent tends to sound like Frasier - an American faking an British accent.

We have lots of great British voices in our voice library! Or if you want to hear an american trying to do a british accent add "[British accent]" at the start of the generation

Re: Eleven v3

#16

Post by zamadatix »

The (American English) voices are absolutely amazing but the tags for laughs still feel more like an "inserted dedicated laugh section" than a "laugh at this point in speaking" type thing. I.e. it can't seem to reliably know when to giggle while saying a word, "just" giggle leading up to a word.

Re: Eleven v3

#17

Post by lharries »

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

Re: Eleven v3

#19

Post by lharries »

dustincoates wrote: post #11
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

The French one sounded like an Alabaman who took a semester of college French. But the English sounds really good.

If you're trying to make an audiobook about an Alabaman visiting Paris this might be quite useful... But in seriousness try it with this voice: https://elevenlabs.io/app/voice-library?voiceId=rbFGGoDXFHtV...
Post reply on HN