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

161–170 of 279 posts

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

#161

Post by hackernewds »

pronlover723 wrote: post #84

What are the odds of this kind of thing being open source so I can use it at home. So far, most of the "good" text-to-speech systems are all commercial services https://aws.amazon.com/polly/ https://cloud.google.com/text-to-speech https://azure.microsoft.com/en-us/products/cognitive-service... And now one is also a service. I tried using tortoise-tts on my M1. Generating a 7 minute speech took 3 days and, while bette…

What kind of personal adult content do you generate? We are curious for details

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

#162

Post by TaylorAlexander »

KRAKRISMOTT wrote: post #126
bredren wrote: post #116

Earlier quoted context omitted.

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

In practice they are next to useless, the expressions are not very... expressive (just try it in the AWS editor). I suspect a LLM would be able to infer the context or we can use prompt engineering to generate the appropriate tokens encoding emotions for the intermediate neural codecs directly (Mel spectrograms are so passé now post Vall-E).

Something I always noticed is that they get Morgan Freeman to do voiceovers for science shows, but he’s not a scientist so he has a sort of generic inflection when he talks about the various ideas in the script. And then you watch Carl Sagan’s COSMOS, where he co-wrote the material, and there is so much depth and expression to his delivery. There’s a lifetime of public speaking, specifically delivering complex scientific topics to a general audience, that Sagan drew from when recording his show.

Sagan would have learned this through conversation with people, and careful updates to his expression and delivery as he matured.

I guess an LLM could improve upon previous methods but I would also say there is a gap that even humans struggle with, which requires really complex knowledge both of public speaking and of the material. It may be a long time before we can really master that with AI systems.

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

#163

Post by sanroot98 »

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 ,it's not technology that's real problem ,it's that loss of ethics in domain of knowledge ,since industrial and scientific revolution ,we put more emphasis on reductionism and objectification ,even human are being objectified ,this disease of over rationalism plaguing to every domains of knowledge ,I think it's always been constant battle of rationalism vs romantics .

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

#164

Post by sanroot98 »

WheelsAtLarge wrote: post #57

I'm listening to an audiobook whose reader is not as good as some of these voices. At one level, I'm impressed but at an another I'm sadden since we are heading towards uncharted territory. We are looking at a future where we'll have content, video,audio, and text by the truckload. More does not mean better. It just means more blah stuff. I don't think that's the future I'm looking forward to live in.

I think you are overestimating the capabilities of ai to create novel content ,high genuine quality content will be always there ,but amount of bs content will increase

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

#166

Post by piotr11 »

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 samples. With the published blog post, we are now deploying a way to help them design entirely new ones!

Anyone will be able to generate that level of quality just with a copy-paste. We are planning to open up Beta later this month. Our goal is to let you convert any written content into high-quality, compelling audio.

To address a few questions that frequently came up:

- Latency for our streaming TTS is - We can clone voices instantly, based just on 5s of speech, without training required

- We are working on adding SSML-like support for better control; speed controls will be coming as part of that too

- API is directly available as part of Beta; we are preparing the infrastructure to scale easily for the release!

We are hiring researchers, frontend and full-stack developers! If you are interested, send over your GitHub account and short message to founders[at]elevenlabs.io.

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

#167

Post by piotr11 »

wand3r wrote: post #73
dj_mc_merlin wrote: post #66

The examples are insanely good. Insanely good. I can barely believe we really live in a world where this is possible. I don't have anything constructive to add.. just wow.

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…

Thanks! ElevenLabs dev here - these are generated 6x faster than real-time, with latency of We are working on long-form speech synthesis too, needless to say, the audio reading the article has been also synthesized by a voice that does not exist.

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

#168

Post by diminikolaou »

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…

Hey Piotr - just wanted to say congratz for the awesome work so far man. The quality is genuinely unbelievable. I don't know if you guys are ready to take clients at scale, but I don't see any reason why all newsletter creators wouldn't use your tech right now to address whole new markets. I'll be following the journey, excited for what's to come.

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

#169

Post by piotr11 »

dalmo3 wrote: post #7

I found the samples incredibly good. But the samples in their other post about conveying emotions[0] are still far from acceptable. In any case, I'm hoping this can be expanded to other languages as it would be an amazing tool for language learning. [0] https://blog.elevenlabs.io/the_first_ai_that_can_laugh/

Thanks (ElevenLabs dev here), we are constantly working on improving our model, we do out own research and train it completely from scratch.

We do support Polish already and the quality is actually better IMO than English as we use a newer generation model: https://www.youtube.com/watch?v=ra8xFG3keSs Some people think it is fake and we hired a real voice actor to read.

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

#170

Post by moffkalast »

spaceman_2020 wrote: post #151
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…

My YouTube feed is currently filled with videos of whitehats hacking into Indian scam call centers. Most of the time, the giveaway is the callers' Indian accent. If you could simply type into a box and speak with an American accent, it would be really hard to get caught. We're opening a pandora's box here if I'm honest. I'm hardly one for pro-regulation, but good God, we're playing with things here that can really hu…

And here I thought the giveaway was just them trying to blatantly scam you.
Post reply on HN