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

101–110 of 191 posts

Re: VibeVoice: Open-source frontier voice AI

#101

Post by rogerrogerr »

yjftsjthsd-h wrote: post #90
simonw wrote: post #84

Earlier quoted context omitted.

I'm reserving that complaint for "open source" models which are released under non-open-source licenses. I care that I know what I can DO with the project when I see it described as "open source".

> I care that I know what I can DO with the project when I see it described as "open source". Yes, the first of which is that you should be able to build it from source. Which requires the source code, and in this case data.

They’ll never reveal the data, because that would reveal this is all built on stolen work.

Re: VibeVoice: Open-source frontier voice AI

#102

Post by WorldMaker »

giancarlostoro wrote: post #81
pardon_me wrote: post #51

Earlier quoted context omitted.

How do you pronounce giraffe?

Same way I pronounce my first name btw ;) but I think of "gif" as "gift" and this is probably the subconscious association people make without realizing it.

Which is why I find it fun to bring up that in Old English "gift" hadn't yet picked up the "t" and was spelled "gif", but in Old English "g" was most commonly "HY". I like the Old English pronunciation of "gif" as "HYEEF", which is a "compromise" position that often makes some of both soft-g and hard-g "gif" pronunciation fans angry.

Re: VibeVoice: Open-source frontier voice AI

#103

Post by mberg »

I've been using VibeVoice's ASR (speech to text) model quite intensively for the past month and have found it to be a lot more reliable and out-of-the box functional then Whisper, parakeet and other models. The fact that is has diarization built into to the model is a huge win in my book. Without that you have to run a different model just for that which adds significantly to the overall processing time vs VibeVoice which gives you reliably great results. Big fan.

Re: VibeVoice: Open-source frontier voice AI

#105

Post by WhyNotHugo »

maxloh wrote: post #14

I think we should stop calling this type of models open source. They are indeed "open weight." The training code is proprietary and never revealed. https://github.com/microsoft/VibeVoice/issues/102

Devils advocate here: I can give you a binary of my open source MIT code and never phone you the code. The code is still MIT licensed, and open source. You just have no access to it.

That said, I entirely agree that MS is misrepresenting their openness here, which isn’t in the least surprising.

Re: VibeVoice: Open-source frontier voice AI

#106

Post by realty_geek »

xnx wrote: post #77
lblock wrote: post #15

Earlier quoted context omitted.

Yeah, I don't get why it is suddenly getting so much attention today, it is all over twitter too

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.

Re: VibeVoice: Open-source frontier voice AI

#107

Post by simonw »

rogerrogerr wrote: post #101
yjftsjthsd-h wrote: post #90

Earlier quoted context omitted.

> I care that I know what I can DO with the project when I see it described as "open source". Yes, the first of which is that you should be able to build it from source. Which requires the source code, and in this case data.

They’ll never reveal the data, because that would reveal this is all built on stolen work.

Some of the models DO reveal the data, and it's still built on "stolen work" in that it's unlicensed scrapes of the Web. Here's an example:

https://huggingface.co/allenai/OLMo-2-0325-32B

Here's one of their training mixes: https://huggingface.co/datasets/allenai/dolma3_pool - which includes 8 trillion tokens from Common Crawl.

Re: VibeVoice: Open-source frontier voice AI

#108

Post by riedel »

simonw wrote: post #100
yjftsjthsd-h wrote: post #90

Earlier quoted context omitted.

> I care that I know what I can DO with the project when I see it described as "open source". Yes, the first of which is that you should be able to build it from source. Which requires the source code, and in this case data.

The OSI's take on this is that an open source model can be modified through fine-tuning etc, even if you can't rebuild it from scratch. The problem with requiring "build from scratch" for open source models is that the number of interesting models with training data that can be openly licensed is close to zero. If you trained your model on an unlicensed scrape of the web you can't release the data under an open sourc…

I would personally disagree slightly with this take. Freely being able to use means IMHO, that this can be done for all applications in a legal (and ideally ethical) fashion. Regulation often requires to prove the quality or provenance of data. Open source has IMHO often a very libertarian view on things focusing on the rights of the user an not society in general.

Re: VibeVoice: Open-source frontier voice AI

#109

Post by bronson »

s20n wrote: post #88
ziml77 wrote: post #72

Earlier quoted context omitted.

I hadn't thought about how to pronounce GIS, but do you have a problem with the pronunciation of the Japanese Industrial Standards: JIS?

I've been pronouncing both of them as /dʒis/ like hiss and not /dʒɪz/. I however am not a native english speaker of English. I wonder if native speakers gravitate towards the z more?

I think it depends on region. Related, many speakers pronounce chips and salza, Tezla, Wezley.

Re: VibeVoice: Open-source frontier voice AI

#110

Post by cute_boi »

btown wrote: post #64
maxloh wrote: post #14

I think we should stop calling this type of models open source. They are indeed "open weight." The training code is proprietary and never revealed. https://github.com/microsoft/VibeVoice/issues/102

At least it's MIT licensed! As much as non-open training data irks me, restrictive licensing irks me more!

what is problem with restrictive licensing? Most of them starts if you have 1M users etc?
Post reply on HN