Model reference · open weights
VibeVoice-ASR-Streaming is an open-weight audio or speech model from microsoft. VibeVoice-ASR-Streaming-7B (BF16) weighs 17.3 GB; the smallest configuration that runs it is RTX 4090 24 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the microsoft/VibeVoice-ASR-Streaming-1.5B model card, 2026-10-01. The estimate below is for another build of the family.
What it is
| Released by | microsoft |
|---|---|
| Released | 2026-09-02 |
| Parameters | 2.8B |
| VRAM | 17.3 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB … RTX 4060 Ti 16 GB | does not fit | |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
Builds
| Build | Params | Precision | Weights | Smallest setup |
|---|---|---|---|---|
| VibeVoice-ASR-Streaming-1.5B ↗ | 2.8B | BF16 | 5.6 GB | RTX 3060 12 GB |
| VibeVoice-ASR-Streaming-7B (above) ↗ | 8.7B | BF16 | 17.3 GB | RTX 4090 24 GB |
From the model card
VibeVoice-ASR-Streaming is a unified streaming ASR model that transcribes Who (Speaker) said What (Content), with support for Customized Hotwords and 10 languages.
➡️ Code: microsoft/VibeVoice ➡️ Demo: VibeVoice-ASR-Streaming
📝 Streaming Speaker-Attributed Transcription: Continuously transcribes who said what as speech arrives.
👤 Customized Hotwords: Users can provide customized hotwords, such as names and technical terms, to improve recognition of domain-specific content.
🌍 Multilingual Support: It supports Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian, and Spanish.
Please refer to the GitHub repository.
This project is licensed under the MIT License.
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.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.