Skip to content

VibeVoice-ASR

Hugging Face (open weights) Open weights

The catch: Large for an ASR model (about 9B parameters in the repo), and setup goes through Microsoft's VibeVoice GitHub code.

AccessOpen weights
Free limitsFree to download and self-host; you pay only for your own compute. Speech-to-text that takes up to 60 minutes of audio in one pass and returns who spoke, when and what (speaker labels and timestamps); 50+ languages. MIT licence.
Modalityaudio
Credit cardNot required
Commercial useAllowed
Trains on your data–
Licence or termsMIT
Context window–
Model idmicrosoft/VibeVoice-ASR
Base URL–
Last checked8 Oct 2026

How to use VibeVoice-ASR

Download the weights and serve them yourself; the quickstart below shows one way. Licence: MIT.

Quickstart
git clone https://github.com/microsoft/VibeVoice  # then follow its ASR instructions for microsoft/VibeVoice-ASR
Paste into Claude Code
I want to run the open-weight model "VibeVoice-ASR" (microsoft/VibeVoice-ASR) for my project.
Please:
1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint).
2. Give me a minimal working setup and a test request.
3. Tell me the licence terms for commercial use.
4. If a cheaper or smaller variant would do the job, mention it.

Before you ship on it

  • Large for an ASR model (about 9B parameters in the repo), and setup goes through Microsoft's VibeVoice GitHub code.
  • MIT (licence tag on the HF repo): use, modify and sell freely; keep the copyright notice.
  • Free to run means you pay for the GPUs, the serving stack and the on-call.

Questions

Is VibeVoice-ASR free?

Yes. Open weights offers it as open weights, with these limits: Self-host free · MIT. No credit card is needed.

Can I use VibeVoice-ASR commercially?

Yes, under MIT. Check the current terms before you ship.

How do I start with VibeVoice-ASR?

Download the weights and serve them yourself; the quickstart below shows one way. Licence: MIT.

Source: huggingface.co/microsoft/VibeVoice-ASR, checked 8 Oct 2026.