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

71–80 of 202 posts

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

#71

Post by yjftsjthsd-h »

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…

> Does mean it pulls the model every time on startup though which isn't ideal

Surely it just downloads to a directory that can be volume mapped?

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

#72

Post by 3abiton »

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 oddly reminiscent of the office. I wonder if tv shows were part of its training data!

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

#73

Post by Havoc »

yjftsjthsd-h wrote: post #71
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…

> Does mean it pulls the model every time on startup though which isn't ideal Surely it just downloads to a directory that can be volume mapped?

Yep. I just didn't spend the time to track down the location tbh. Plus huggingface usually does links to a cache folder that I don't recall the location of

Literally got cuda containers working earlier today so haven't spent a huge amount of time figuring things out

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

#76

Post by llm_nerd »

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…

This is a pretty incredible three month creation for a couple of people who had no experience with speech models.

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

#77

Post by jelling »

dindindin wrote: post #75

Was this trained on Planet Money / NPR podcasts? The last audio (continuation of prompt) sounds eerily like Planet Money, I had to double check if my Spotify had accidentally started playing.

NPR voice is a thing.

It started with Ira Glass voice and now the default voice is someone that sounds like they're not certain they should be saying the very banal thing they are about to say, followed by a hand-shake protocol of nervous laughter.

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

#79

Post by smusamashah »

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…

Hi! This is awesome for size and quality. I want to see a book reading example or try it myself.

This is a tangent point but it would have been nicer if it wasn't a notion site. You could put the same page on github pages and it will be much lighter to open, navigate and link (like people trying to link some audio)

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

#80

Post by toebee »

hemloc_io wrote: post #41

Very cool! Insane how much low hanging fruit there is for Audio models right now. A team of two picking things up over a few months can build something that still competes with large players with tons of funding

Thank you for the kind words <3
Post reply on HN