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

This Voice Doesn't Exist – Generative Voice AI

blog.elevenlabs.io

Post reply on HN
Print view View original

111–120 of 279 posts

Re: This Voice Doesn't Exist – Generative Voice AI

#111

Post by feoren »

Okay can I ask a question that has been bothering me for a long time?

Why do seemingly all these text-to-speech programs attempt to produce spoken voice based solely on raw text? Why don't they consume a MIDI-like text-markup language where you can write phonetic pronunciations along with markup about the emotion, volume, speed, etc.? I feel like this is a huge unnecessary roadblock holding back this kind of technology. It'd be like if every music composition program rendered a wave file not by MIDI or VST, but by trying to visually read sheet music. I totally understand why TTS solutions that have to consume arbitrary content, like screen-readers, need to read purely raw text. But content creators don't need to be limited to raw text! Why is everyone doing it that way? Where is the TTS markup language for content creators?

Re: This Voice Doesn't Exist – Generative Voice AI

#112

Post by gmadsen »

vouaobrasil wrote: post #70
didericis wrote: post #56

I can't tell if I'm starting to get that old person "new things are scary" instinct or if my gut level of fear about the implications of these things is warranted. As impressive as a lot of these models are, I can't help but feel like they're going to end up making an incredible amount of sterile soulless content that makes everyone's lives worse . We're already drowning in ad dominated cynical soulless computer gene…

I agree with this completely. Technology has always made us trade quality for low-quality quantity in exchange for convenience. People now interact more through technology which removes a lot of body language and other enriching experiences. The most dangerous aspect of this is that each step seems relatively harmless: right now, ChatGPT and DALL-E are amusements, but each small step is building a monstrous and as yo…

I think what gets lost in these doom and gloom predictions is that there is a large healthy portion of young adults that do not engage in internet forums or social media.

It is perfectly viable in the modern day, to work a job, have passionate hobbies, regularly meet for social events, volunteer, etc and spend minimal to zero time engaging on the internet, besides pragmatic things like map directions

Re: This Voice Doesn't Exist – Generative Voice AI

#113

Post by vixen99 »

Sightline wrote: post #106
djmips wrote: post #99

Earlier quoted context omitted.

> Technology has always made us trade quality for low-quality quantity in exchange for convenience. People now interact more through technology which removes a lot of body language and other enriching experiences. I went to the mall today and you can tell malls are dying. I lived in a small town where the mall died and it had a zombie like existence a long time before it finally cratered. The mall here in this larger…

I never went to malls to socialize.

Sometimes circumstances mean that going to a mall is the only way some folk can get to meet their fellow human beings. And that doesn't mean it doesn't have other advantages such as conversing with people one might not normally come across.

Re: This Voice Doesn't Exist – Generative Voice AI

#114

Post by intelVISA »

cheeseface wrote: post #102
coverband wrote: post #24

This is cooler than ChatGPT and image generation as far as I'm concerned. If they're able to bring out the emotional connectivity and purposefulness of the human voice, it will be revolutionary...

There are so many uses cases for this, even with the current quality. Many game developers dream of having something like this.

Awesome, I think a few years we'll hit levels of AI generative media tech where you can produce, as a lone greybeard, a Cyberpunk 2077 tier title. Same # of bugs too ;)

Re: This Voice Doesn't Exist – Generative Voice AI

#115

Post by intelVISA »

holler wrote: post #37
bsenftner wrote: post #34

Earlier quoted context omitted.

Not only voice actors, include radio hosts, documentary/news content, any voice over for anything, as well as imitation of familiar voices.

This will really open pandoras box for scammers and other bad actors. Grandma won't know she's speaking with an AI.

Blade Runner: 2024

spotting open (closed) AI models by doing the Voight-KAPTCHA test

Re: This Voice Doesn't Exist – Generative Voice AI

#116

Post by bredren »

feoren wrote: post #111

Okay can I ask a question that has been bothering me for a long time? Why do seemingly all these text-to-speech programs attempt to produce spoken voice based solely on raw text ? Why don't they consume a MIDI-like text-markup language where you can write phonetic pronunciations along with markup about the emotion, volume, speed, etc.? I feel like this is a huge unnecessary roadblock holding back this kind of technol…

I don’t know how many of the solutions offer this, but there is a markup language for TTS:

https://en.wikipedia.org/wiki/Speech_Synthesis_Markup_Langua...

Amazon Polly, (which seems kind of ancient with all these new solutions showing up) has supported SSML for some time.

AWS Polly SSML docs: https://docs.aws.amazon.com/polly/latest/dg/ssml.html

Re: This Voice Doesn't Exist – Generative Voice AI

#117

Post by kreddor »

ThePyCoder wrote: post #101
wand3r wrote: post #73

Earlier quoted context omitted.

I work in TTS and i just dont believe this. If these really are random text and not trained on literally the copy they are reading, with no correction I would be surprised. Also, our competitors have good voices but they also take ages to produce. Maybe these really are legit but take like 1 minute to produce or something. So while this is impressive, i doubt that in practice this would be this high quality and could…

I want to agree, but I searched on their website and found their narration service with 2 full book examples. I listened to the first one for a while and it's the first time an Ai narrator was good enough to keep me listening: https://www.audiostory.ai/2065785/11707800-alice-s-adventure...

It's noticable worse than the examples in the blog post. I mean, it's good enough for listening, but no better than the competition.

Re: This Voice Doesn't Exist – Generative Voice AI

#118

Post by tomcam »

didericis wrote: post #56

I can't tell if I'm starting to get that old person "new things are scary" instinct or if my gut level of fear about the implications of these things is warranted. As impressive as a lot of these models are, I can't help but feel like they're going to end up making an incredible amount of sterile soulless content that makes everyone's lives worse . We're already drowning in ad dominated cynical soulless computer gene…

I want to agree with you, but I have to admit I hate most human narrators of audiobooks. I would actually much prefer this company‘s voices to most of the humans reading books that I have encountered.

Re: This Voice Doesn't Exist – Generative Voice AI

#120

Post by pmichaud »

feoren wrote: post #111

Okay can I ask a question that has been bothering me for a long time? Why do seemingly all these text-to-speech programs attempt to produce spoken voice based solely on raw text ? Why don't they consume a MIDI-like text-markup language where you can write phonetic pronunciations along with markup about the emotion, volume, speed, etc.? I feel like this is a huge unnecessary roadblock holding back this kind of technol…

As the sibling comment notes, there is in fact markup for this, and the results are actually pretty great.
Post reply on HN