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

271–279 of 279 posts

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

#271

Post by PeterisP »

yieldcrv wrote: post #72
didericis wrote: post #63

Earlier quoted context omitted.

A galaxy scale exploration game on the scale of Elite Dangerous where you could have more complex and varied interaction would be pretty amazing. The way you could apply these new AI models to video games has some wild potential. I think video games are one of the areas where I see the most potential for positive impact rather than negative impact.

The file sizes would drop by 50 gigabytes again Most of it is high definition audio these days, and then that just gets replaced by a 10gb training set, or maybe the training set becomes a shared resource on the console

Generating quality voice is sufficiently compute-intensive that it would increase the file size, as they would still ship all the audio (instead of computing locally) but there would just be so much more of it.

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

#272

Post by QuantumGood »

anigbrowl wrote: post #25

Less than a week ago, I said AI would upend the market for voice actors within the next couple of years: https://news.ycombinator.com/item?id=34271948

The "budget advantage" doesn't matter in the top half of the industry; directing a human voice talent is not going away anytime soon.

Budget clients are suspicious of AI voices and feel "cheated" if they think someone they hired are using one. This will change fastest.

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

#273

Post by hiisukun »

piotr11 wrote: post #166

Hey - developers behind ElevenLabs here. Thank you so much for the constructive and positive feedback - we’re taking it onboard! We’re currently focused on researching and deploying a different way for speech synthesis that can generate nuanced intonation and emotions by understanding text and taking context into account. Additionally, we provide creators with a way to clone their own voice based on very short sample…

Maybe I'm late to the party -- but this [1] graphic is great in the linked article.

Could the designer share a little about how it was made? Does it represent one of the generated voices, or is it just 'artistic'? (both are cool, I think).

[1] https://blog.elevenlabs.io/content/images/2023/01/Sequence-0...

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

#274

Post by havnagiggle »

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 used to work in automotive navigation. Other colleagues handled our voice systems, but I do remember all our prompts were written in SSML[1] with varrying amounts of specificity. We would use Lua to configure and customize the SSML, including some custom extensions for different voice renderers.

Even with the prompts marked up, there were huge differences between products. Some car OEMs would pay higher fees for better voice and some wouldn't. It's fairly tedious work and difficult to scale as the amount of sentences grows. We basically built up a catalog over many years and they were always explicitly stated as part of our requirements docs. Of course the renderers could say anything you wanted but letting it free form was so a big risk from a product point of view.

[1] https://en.m.wikipedia.org/wiki/Speech_Synthesis_Markup_Lang...

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

#276

Post by fireant »

piotr11 wrote: post #166

Hey - developers behind ElevenLabs here. Thank you so much for the constructive and positive feedback - we’re taking it onboard! We’re currently focused on researching and deploying a different way for speech synthesis that can generate nuanced intonation and emotions by understanding text and taking context into account. Additionally, we provide creators with a way to clone their own voice based on very short sample…

The voices are really amazing, I couldn't really tell that they are synthetic and I was looking for it.

The only issue is that the actual recordings sound like they have been overcompressed, or poorly recorded - is there any way to improve this? Something like superresolution, but for voice?

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

#277

Post by Roark66 »

jsjohnst wrote: post #230
Roark66 wrote: post #149

Earlier quoted context omitted.

I remember in the 80s of last century there was a speech synthesis software I had on an 8 bit computer that accepted either normal text, or phonetic notation that had extra modifiers for basic things like "make this a question" etc.

Do you remember what that was? Dectalk was around in the 80s and so might’ve been that, but it wasn’t a generally available thing. Dr Sbaitso was common, but that wasn’t until 91/92.

Yes I do, it was a Commodore 64 cartridge called "Black Box 8". And it spoke Polish with the right accent with all the sounds not present in English etc.

I read back then that it was domestic Polish make, but back then there was no such thing as IP protection so it is very likely it was based on work of Denic Klatt(same as DECtalk). When I heard some DECtalk recordings in a youtube video not long ago it immediately reminded me nded me of Commodore 64 Black Box 8. Although DECtalk spoke in English and black box 8 spoke in Polish there is some similarity that can be heard in their voices(not pitch - this was a user setting, but more of a rhythm if it makes sense)

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

#278

Post by LarsDu88 »

didericis wrote: post #63
yieldcrv wrote: post #21

Earlier quoted context omitted.

I’m looking forward to NPCs having dynamic responses with real voices Doesn't have to be prerecorded, just trained

A galaxy scale exploration game on the scale of Elite Dangerous where you could have more complex and varied interaction would be pretty amazing. The way you could apply these new AI models to video games has some wild potential. I think video games are one of the areas where I see the most potential for positive impact rather than negative impact.

I'm working on a VR space game that actually uses Ssml azure cloud generated voices for dialog, but I've ditched the rogue-like procedural elements which are wickedly hard to implement

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

#279

Post by selfhoster11 »

PaulBGD_ wrote: post #100
93po wrote: post #91

Earlier quoted context omitted.

I feel like if Bethesda really wants another industry defining game, this is the path they should be taking. AI generated conversation with AI generated voice acting with voice-to-text recognition. You can literally have microphone-voice conversations with NPCs that have rich, AI generated backgrounds and personalities.

Even bigger than that (I think at least) is the potential for fully voiced mods. There’s nothing stopping modders at that point from adding content indistinguishable from the base game.

I'd love to see that. Voice acting for mods where you want to include new NPCs requires either someone to donate some voice lines, or paying for it to be recorded. If you want to patch existing NPCs, that's even harder because getting the original voice actor to do the new lines would require both persuading them to do it, and complying with any agreements they might have with the publisher that could prevent that.
Post reply on HN