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

VibeVoice: Open-source frontier voice AI

github.com

Post reply on HN
Print view View original

151–160 of 191 posts

Re: VibeVoice: Open-source frontier voice AI

#151

Post by freedomben »

clickety_clack wrote: post #119
freedomben wrote: post #114

Earlier quoted context omitted.

I don't disagree, but it is perfectly acceptable per the MIT license, which is an OSI approved license. MIT doesn't require source distribution with the binary (which is why from the developer perspective, it's a more "permissive" license)

The license describes what users are allowed to do with the source code, it doesn’t (and shouldn’t) define what a creator has to do to make the source code open.

Then it sounds like you're philosophically opposed to copyleft license like GPL. That's ok, we can agree to (in my case vehemently) disagree, but your philosophy is inconsistent with the commonly accepted definition of "open source" such as OSI's OSD[1][2]

[1]: https://opensource.org/licenses [2]: https://opensource.org/osd

Re: VibeVoice: Open-source frontier voice AI

#152

Post by keeda »

engeljohnb wrote: post #124
JumpCrisscross wrote: post #19

Earlier quoted context omitted.

> we should stop calling this type of model open source. They are indeed "open weight” This ship has sailed. It’s now in the same category as hacker/cracker and the pronunciation of GIF.

The inventor of GIF didn't begin with a document* clearly laying out what is and isn't to be called a "GIF." I think it's right to push back whenever a huge tech corporation tries to build goodwill by falsely using terms like "open source." * https://opensource.org/osd

To be fair, the initiators of the "Open Source" movement also co-opted a term that previously had a much more flexible meaning (and had been around for more than a decade at that point.) Just writing a document attributing specific criteria to a term does not grant one authority over the use of that term.

Ironically, the roots of the Open Source movement are a direct reponse to the Free Software movement largely because it was considered too ideological and unfriendly to corporate interests (i.e. monetization.)

Re: VibeVoice: Open-source frontier voice AI

#154

Post by tombert »

logicchains wrote: post #142
tombert wrote: post #135

Earlier quoted context omitted.

I'm shocked, shocked to find that Microsoft takes credit for a slow, unoriginal product that doesn't actually do what it advertises.

Imagine the balls it took to willingly attach the Microsoft label to the front of the product that is Teams.

I mean the same can be said about most versions of Windows as well. People act like Windows 11 is where it all went sour, but I've personally kind of hated it since Windows XP.

I feel like a recurring pattern with Microsoft is to create something quickly, market it aggressively and push for everyone to use it immediately, and only once it is installed everywhere do people suddenly realize how terrible it is, but it's too late to change.

Re: VibeVoice: Open-source frontier voice AI

#155

Post by clickety_clack »

freedomben wrote: post #151
clickety_clack wrote: post #119

Earlier quoted context omitted.

The license describes what users are allowed to do with the source code, it doesn’t (and shouldn’t) define what a creator has to do to make the source code open.

Then it sounds like you're philosophically opposed to copyleft license like GPL. That's ok, we can agree to (in my case vehemently) disagree, but your philosophy is inconsistent with the commonly accepted definition of "open source" such as OSI's OSD[1][2] [1]: https://opensource.org/licenses [2]: https://opensource.org/osd

I think you completely misunderstand me. I don’t have any opinion on GPL, but in the links you shared, even OSI considers the license to be separate from the definition of open source “Open source licenses are licenses that comply with the Open Source Definition”. You can use a license that open source projects use (ie MIT), and still keep the source closed, or you can write one that puts obligations on you if you want. In fact, you can use or write pretty much any license you want if you own the copyright.

Re: VibeVoice: Open-source frontier voice AI

#156

Post by soperj »

realty_geek wrote: post #106
xnx wrote: post #77

Earlier quoted context omitted.

Simonw (who has a bit of a Midas touch for posts here) just posted about it https://simonwillison.net/2026/Apr/27/vibevoice/

To be fair, his Midas touch is a result of consistency and a lot of hard work. It's like the gardener at one of the Oxford colleges said - it's really easy to create these perfect lawns, just turn up every day and trim and water it - for a couple hundred years.

I thought they rolled it as well?

Re: VibeVoice: Open-source frontier voice AI

#157

Post by Stagnant »

gagan2020 wrote: post #93
steinvakt2 wrote: post #10

This is not a new model. Also, it hallucinates a lot. Also, it's very heavy and slow in inference. It's also bad in multilingual. Edit: I'm talking purely about speech to text (STT). Not sure about the other things this can do.

It is not good for text to speech (TTS) as well. I am trying it for few days. First of all 1.5B model documentation is not there. 0.5B realtime is shit model. I was converting text, line by line and it was randomly adding music and couldn't handle special characters like "…". I really disappointed with this model to say the least.

The 7B parameter Vibevoice TTS model is still the most impressive local TTS model i've tried. It was pulled by Microsoft a few days after its release due to "abuse potential" but it can be found in various community maintained huggingface repos.

Re: VibeVoice: Open-source frontier voice AI

#158

Post by tempodox »

lvncelot wrote: post #122
aqme28 wrote: post #28

Interesting to see "vibe" enshrined by the likes of Microsoft as an AI product word.

I'm honestly more surprised that they could resist the temptation to call it Copilot

Microslop Copilot for Voice! After they renamed Office, they surely will rename this one, too.

Re: VibeVoice: Open-source frontier voice AI

#159

Post by woodson »

frangonf wrote: post #46

I took a look into local options for ASR and diarization some months ago, I missed that VibeVoice now has this feature. My conclusions back then (which only came from a shallow research on the topic and 0 real experience mind you) was that Whisper + Pyannote was the "stable" approach. Have the VibeVoice, Voxtral, Qwen or the Nemo solutions caught up in segmentation and speaker recognition?

It highly depends on the sort of data you’re processing (phone calls, podcasts, meetings of more people recorded using single channel?). For NVIDIA/NeMo, check out their softformer diarization models (also streaming).
Post reply on HN