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

101–110 of 202 posts

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

#101

Post by dragonwriter »

Havoc wrote: post #66

Sounds really good & human! Got a fair bit of unexpected artifacts though. e.g. 3 seconds hissing noise before dialogue. And music in background when I added (happy) in an attempt to control tone. Also don't understand how to control the S1 and S2 speakers...is it just random based on temp? > TODO Docker support Got this adapted pretty easily. Just latest nvidia cuda container, throw python and modules on it and chan…

> Also don't understand how to control the S1 and S2 speakers...

Do a clip with the speakers you want as the audio prompt, add the text of that clip (with speaker tags) of the clip at the beginning of your text prompt, and it clones the voices from your audio prompt for the output.

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

#103

Post by toebee »

nickthegreek wrote: post #44
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…

Are there any examples of the audio differences between the this and the larger model?

We're still experimenting, so do not have samples yet from the larger model. All we have is Dia-1.6B at the moment.

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

#105

Post by toebee »

enodios wrote: post #86

The audio quality is seriously impressive. Any plans to add word-level timing maps? For my usecase that is a requirement, so unfortunately I cannot use this yet, but I would very much like to.

Thank you for the kind words! We don't have plans for that yet, but you can always open an issue or RP on Github.

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

#107

Post by toebee »

eob wrote: post #54

Bravo -- this is fantastic. I've been waiting for this ever since reading some interview with Orson Scott Card ages ago. It turns out he thinks of his novels as radio theater, not books. Which is a very different way to experience the audio.

Thanks for the kind words :)))

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

#108

Post by toebee »

ivape wrote: post #16
toebee wrote: post #13

Earlier quoted context omitted.

We will work on a quantized version of the model, so hopefully you will be able to run it soon! We've seen Bark from Suno go from 16GB requirement -> 4GB requirement + running on CPUs. Won't be too hard, just need some time to work on it.

No doubt, these TTS models locally are what I'm looking for because I'm so done typing and reading :)

You can try it now on https://huggingface.co/spaces/nari-labs/Dia-1.6B !!!

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

#110

Post by toebee »

lostmsu wrote: post #42

Does this only work for two voices? Can I generate an entire conversation between multiple people? Like this HN thread.

Only two voices at the moment... We will need to upgrade the dataset to make that happen, and are considering that as one of the next steps.
Post reply on HN