by steinvakt2
9 subcomments
- 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.
- 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
- 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...
- Interesting story about this repo/product/author by cybersecurity researcher Kevin Beaumont: https://cyberplace.social/@GossiTheDog/116454846703138243
by d4rkp4ttern
1 subcomments
- This was on HN 7 months ago:
https://news.ycombinator.com/item?id=45114245
Every time a STT/TTS model is posted I wonder if it will change my current workflow on MacOS, which is:
STT with Parakeet-V3 via Hex [1] app for near-instant good-enough transcription for talking to AI agents.
TTS using KyutAI’s Pocket-TTS, an amazing 100M-param model. I used this to make a "voice" plugin [2] for Claude Code
So far I haven’t seen anything that replaces these for me, or haven't been persuaded enough to spend time testing an alternative (explore/exploit and all that).
[1] Hex STT app - https://github.com/kitlangton/Hex, which is macOS-only.
(also good free/OSS alternatives: Handy, VoiceInk. No need for Wispr, Superwhisper etc)
[2] Claude Code Voice Plugin - https://pchalasani.github.io/claude-code-tools/plugins-detai...
by embedding-shape
2 subcomments
- Isn't this project the one Microsoft published but then soon after pulled it for security/safety reasons? What has changed since then?
- Interesting to see "vibe" enshrined by the likes of Microsoft as an AI product word.
by CubsFan1060
2 subcomments
- Great post last night from Simon: https://simonwillison.net/2026/Apr/27/vibevoice/
by Anonyneko
1 subcomments
- You have selected Microsoft Sam as the computer's default voice.
by podgietaru
2 subcomments
- So we've really just settled on Vibe as the verb for AI then?
by ryukoposting
1 subcomments
- Holy moly, a Microsoft AI product that isn't named Copilot!
- Still waiting for the open weights model that conclusively beats the multi-year old Whisper in accuracy, features, and performance.
- The 60-minute single-pass transcription is the part that actually matters. Most ASR models chunk audio and you lose speaker continuity across boundaries. If the diarization actually holds up on hour-long recordings without drifting, thats a real solve for podcast and meeting transcription workflows.
by chaosprint
0 subcomment
- Microsoft Store App Vibing.exe Accused of Harvesting Screens, Audio, and Clipboard Data:
https://cyberpress.org/microsoft-store-app-vibing-exe-accuse...
by triage8004
0 subcomment
- Surprised it wasn't called Copilot Voice
- I built speech-swift, which focuses on on-device speech processing like VibeVoice, but specifically leverages Apple Silicon's capabilities for ASR, TTS, and VAD without cloud dependency. Our ASR supports 52 languages with a real-time factor of 0.06. https://soniqo.audio/benchmarks
- 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.
- 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?
- 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?
by JumpCrisscross
3 subcomments
- What’s the current state of the art, for each of training locally and in the cloud, for learning my voice?
by leadgenman
0 subcomment
- This is really great. I know it's not a new model, and it does often hallucinate, but it's really great frontier open-source voice AI models.
- Microsoft has historically made poor choices in product naming, but this has to be a new low.
by dragonfax
1 subcomments
- Shouldn't it be called something like "Copilot Voice"?
- Someone tell me if this is better or worse than Parakeet
by BlastBash192
1 subcomments
- 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.
by ChrisArchitect
1 subcomments
- Previously:
Sept 2025 https://news.ycombinator.com/item?id=45114245
by low_tech_punk
0 subcomment
- When mixing languages, why does the English have Chinese accent and Chinese have English accent? Is it a feature or bug?
by lizardking
0 subcomment
- Microsoft continues to be completely incapable of coming up with good names for their products and services
- Explains most of the shit they have pushing with Windows 11. Perhaps all that bloatware was VibeVoiced too.
- It would have been better if they provided not just weights, but also some frontend where it is usable as is.
- For me its giving me very poor results
- Sounds like Msft wanted to coast on the “vibecode” vibe popularity?
- Seriously, VibeVoice? Microslop really has a penchant for the worst names.
- looks like this offers ASR support in GGUF https://github.com/CrispStrobe/CrispASR -- haven't tested
by nickandbro
0 subcomment
- This is a very good model, but can it be run on the web?
- What the do they mean by frontier voice
- any idea on how does this STT compare to whisper large or turbo?
by decide1000
0 subcomment
- Isn't voxtral much better?
by walthamstow
0 subcomment
- 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
- English only?
by starkeeper
0 subcomment
- Microsoft is famous for choosing terrible names but how could they be this terrible.
- lol they rug-pulled the 7B for our own safety some months ago
- What a terrible name
- [flagged]
- [dead]
Hacker News