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

Show HN: Dia, an open-weights TTS model for generating realistic dialogue

github.com

Post reply on HN
Print view View original

51–60 of 202 posts

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#51

Post by gapan »

teddyh wrote: post #31
Magma7404 wrote: post #27

Earlier quoted context omitted.

I know it's a bit ridiculous to see that as some kind of conspiracy, but I have seen a very long list of AI-related projects that got the same name as a famous open-source project, as if they wanted to hijack the popularity of those projects, and Dia is yet another example. It was relatively famous a few years ago and you cannot have forgotten it if you used Linux for more than a few weeks. It's almost done on purpos…

The generous interpretation is that the AI hype people just didn’t know about those other projects, i.e. that they are neither open source developers, nor users.

Of course, how could they have known? Doing a basic web search before deciding on a name is so last year.

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#53

Post by codingmoh »

Hey, this is really cool! Curious how good the multi-language support is. Also - pretty wild that you trained the whole thing yourselves, especially without prior experience in speech models.

Might actually be helpful for others if you ever feel like documenting how you got started and what the process looked like. I’ve never worked with TTS models myself, and honestly wouldn’t know where to begin. Either way, awesome work. Big respect.

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#55

Post by mrandish »

jinay wrote: post #48
tyrauber wrote: post #28

Hey, do yourself a favor and listen to the fun example: > [S1] Oh fire! Oh my goodness! What's the procedure? What to we do people? The smoke could be coming through an air duct! Seriously impressive. Wish I could direct link the audio. Kudos to the Dia team.

For anyone who wants to listen, it's on this page: https://yummy-fir-7a4.notion.site/dia

Wow. Thanks for posting the direct link to examples. Those sound incredibly good and would be impressive for a frontier lab. For two people over a few months, it's spectacular.

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#56

Post by mrandish »

aclark wrote: post #25
toebee wrote: post #5

Earlier quoted context omitted.

Thanks for the heads-up! We weren’t aware of the GNOME Dia project. Since we focus on speech AI, we’ll make sure to clarify that distinction.

Ditto this! Dia diagram tool user here just noticing the name clash. Good luck with your Dia!! Assuming both can exist in harmony. :-)

> Assuming both can exist in harmony.

I'm sure they can... talk it over.

I'll show myself out.

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#57

Post by heystefan »

toebee wrote: post #2

Hey HN! We’re Toby and Jay, creators of Dia. Dia is 1.6B parameter open-weights model that generates dialogue directly from a transcript. Unlike TTS models that generate each speaker turn and stitch them together, Dia generates the entire conversation in a single pass. This makes it faster, more natural, and easier to use for dialogue generation. It also supports audio prompts — you can condition the output on a spec…

Could one usecase be generating an audiobook with this from existing books? I wonder if I could fine-tune the "characters" that speak these lines since you said it's a single pass whole the whole convo. Wonder if that's a limitation for this kind of a usecase (where speed is not imperative).

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#58

Post by bzuker »

toebee wrote: post #2

Hey HN! We’re Toby and Jay, creators of Dia. Dia is 1.6B parameter open-weights model that generates dialogue directly from a transcript. Unlike TTS models that generate each speaker turn and stitch them together, Dia generates the entire conversation in a single pass. This makes it faster, more natural, and easier to use for dialogue generation. It also supports audio prompts — you can condition the output on a spec…

hey, this looks (or rather, sounds) amazing! Does it work with different languages or is it English only?

Re: Show HN: Dia, an open-weights TTS model for generating realistic dialogue

#60

Post by nojs »

tyrauber wrote: post #28

Hey, do yourself a favor and listen to the fun example: > [S1] Oh fire! Oh my goodness! What's the procedure? What to we do people? The smoke could be coming through an air duct! Seriously impressive. Wish I could direct link the audio. Kudos to the Dia team.

This is so good. Reminds me of The Office. I love how bad the other examples are.
Post reply on HN