HN

Need help?
<- Back
Microsoft VibeVoice: Open-Source Frontier Voice AI

Microsoft VibeVoice: Open-Source Frontier Voice AI

tosh

Comments (139)

  • steinvakt2
    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.
  • maxloh
    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
  • isodev
    I think in this category, Voxtral by Mistral is a lot better. It also happens to be small enough to run on webGPU https://huggingface.co/spaces/mistralai/Voxtral-Realtime-Web...
  • triage8004
    Surprised it wasn't called Copilot Voice
  • pluc
    Interesting story about this repo/product/author by cybersecurity researcher Kevin Beaumont: https://cyberplace.social/@GossiTheDog/116454846703138243
  • aqme28
    Interesting to see "vibe" enshrined by the likes of Microsoft as an AI product word.
  • yayadarsh
    Someone tell me if this is better or worse than Parakeet
  • embedding-shape
    Isn't this project the one Microsoft published but then soon after pulled it for security/safety reasons? What has changed since then?
  • xnx
    Still waiting for the open weights model that conclusively beats the multi-year old Whisper in accuracy, features, and performance.
  • dragonfax
    Shouldn't it be called something like "Copilot Voice"?
  • 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.
  • CubsFan1060
    Great post last night from Simon: https://simonwillison.net/2026/Apr/27/vibevoice/
  • podgietaru
    So we've really just settled on Vibe as the verb for AI then?
  • chaosprint
    Microsoft Store App Vibing.exe Accused of Harvesting Screens, Audio, and Clipboard Data:https://cyberpress.org/microsoft-store-app-vibing-exe-accuse...
  • ryukoposting
    Holy moly, a Microsoft AI product that isn't named Copilot!
  • Anonyneko
    You have selected Microsoft Sam as the computer's default voice.
  • anon
    undefined
  • nickandbro
    This is a very good model, but can it be run on the web?
  • frangonf
    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?
  • Mobius01
    Microsoft has historically made poor choices in product naming, but this has to be a new low.
  • solomatov
    It would have been better if they provided not just weights, but also some frontend where it is usable as is.
  • Void_
    I the past month or so, I added 2 models to my app Whisper Memos (https://whispermemos.com):- Cohere Transcribe (self hosted)- Grok Speech To Text (they provide an API, only $0.10/hr!)They are both excellent. I'm not sure about this one. Would you like to see it in a consumer speech to text app?
  • JumpCrisscross
    What’s the current state of the art, for each of training locally and in the cloud, for learning my voice?
  • BlastBash192
    Maybe Microsoft’s real strength was never making the best model, it was knowing you don’t need to, as long as you own the platform everyone builds on.
  • khimaros
    looks like this offers ASR support in GGUF https://github.com/CrispStrobe/CrispASR -- haven't tested
  • mistic92
    For me its giving me very poor results
  • Zopieux
    English only?
  • walthamstow
    Seems quite heavy for a STT model, Parakeet and Whisper are much smaller and perform great for quick dictation and transcription of longer files. I guess that's due to additional accuracy and speaker diarisation?The TTS example clip in the repo of 'spontaneous singing' is creepy as fuck
  • ChrisArchitect
  • starkeeper
    Microsoft is famous for choosing terrible names but how could they be this terrible.
  • villgax
    lol they rug-pulled the 7B for our own safety some months ago