Model reference · open weights
VibeVoice-ASR is an open-weight audio or speech model from microsoft, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
VibeVoice-ASR [](https://github.com/microsoft/VibeVoice) [](https://aka.ms/vibevoice-asr) [](https://arxiv.org/pdf/2601.18184) VibeVoice-ASR is a unified speech-to-text model designed to handle 60-minute long-form audio in a single pass, generating structured transcriptions containing Who (Speaker), When (Timestamps), and What (Content), with support for Customized Hotwords and over 50 languages. ➡️ Code: microsoft/VibeVoice<br ➡️ Demo: VibeVoice-ASR-Demo<br ➡️ Report: VibeVoice-ASR Technical Report<br ➡️ Finetuning: Finetuning<br ➡️ vLLM: vLLM-VibeVoice-ASR<br 🔥 Key Features - 🕒 60-minute Single-Pass Processing: Unlike conventional ASR models that slice audio into short chunks (often losing global context), VibeVoice ASR accepts up to 60 minutes of continuous audio input within 64K token length. This ensures consistent speaker tracking and semantic coherence across the entire hour. - 👤 Customized Hotwords: Users can provide customized hotwords (e.g., specific names, technical terms, or background info) to guide the recognition process, significantly improving accuracy on domain-specific content. - 📝 Rich Transcription (Who, When, What): The model jointly performs ASR, diarization, and timestamping, producing a structured output that indicates who said what and when. - 🌍 Multilingual & Code-Switching Support: It supports over 50 languages, requires no explicit language setting, and natively handles code-switching within and across utterances. Language distribution can be found here. Evaluation Installation and Usage Please refer to GitHub README. Language Distribution License This project is licensed under the MIT License. Contact This project was conducted by members of Microsoft Research. We welcome feedback and collaboration from our audience. If you have suggestions, questions, or observe unexpected/offensive behavior in our technology, please contact us at VibeVoice@microsoft.com. If the team receives reports of undesired behavior or identifies issues independently, we will update this repository with appropriate mitigations.
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | microsoft |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 8.7B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-01-21 |
| Popularity | 700k downloads / month |
| Likes | 1,278 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| VibeVoice-ASR | 8.7B | BF16 | ~20 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys vibevoice-asr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vibevoice-asr below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="vibevoice-asr" -F file=@audio.mp3
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗