VibeVoice-ASR-Streaming-7B
VibeVoice-ASR-Streaming-7B is a speech-to-text model (9B total) from Microsoft, released under the MIT license. The reviewed source lists 10 languages (10 explicitly enumerated in our record), and the model is designed for native streaming. It produces speaker-attributed transcripts natively. Among the common setups we test, it ranks highest for Japanese live transcription (#5 of 26 in the matcher).
Larger sibling of VibeVoice-ASR Streaming 1.5B: native streaming who-said-what transcription in the same ten languages, with customized hotwords. The model card lists 9B parameters and advertises Who/What output rather than timestamped When output. Ratings are provisional until independent benchmarks are available.
Key facts
| Provider | Microsoft |
|---|---|
| Model family | VibeVoice-ASR |
| Parameters | 9B total |
| License | MIT · Permissive — license text ↗ |
| Language coverage | 10 listed languages · 10 enumerated in our record |
| Streaming | Native streaming architecture |
| Timestamps | Limited or runtime-dependent |
| Speaker diarization | Yes — native speaker-attributed output |
| Speech translation | No |
| Documented runtimes | Hugging Face Transformers, microsoft/VibeVoice — how to run it |
| Primary source | huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B ↗ |
| Rating status | Provisional (added November 3, 2026) |
| Last reviewed |
Hardware and workload fit
These are Speech Model Match's conservative 1–5 editorial ratings, relative to the other 19 reviewed models. They come from model size, official memory guidance and documented runtimes — not from a universal benchmark. How the ratings work.
| Dimension | Rating | Scale |
|---|---|---|
| CPU-only fit | 1/5 | |
| Apple Silicon fit | 1/5 | |
| NVIDIA GPU fit | 4/5 | |
| Speed | 3/5 | |
| Accuracy (relative) | 3/5 | |
| Low memory use | 1/5 | |
| Long recordings | 4/5 | |
| Live / low latency | 4/5 | |
| Subtitle work | 2/5 | |
| Edge / low-power devices | 1/5 |
Where it is strong
- Native speaker-attributed transcription (diarization)
- Native streaming architecture for live, low-latency transcription
- NVIDIA GPU fit: rated 4/5
- Long recordings: rated 4/5
- Live / low latency: rated 4/5
What to check first
- CPU-only fit: rated 1/5
- Apple Silicon fit: rated 1/5
- Low memory use: rated 1/5
- Subtitle work: rated 2/5
- Edge / low-power devices: rated 1/5
- Timestamp support is limited or runtime-dependent — test it if you need subtitles
How it ranks in common setups
Ranks come from the same deterministic matcher that runs on the homepage, applied to all 26 reviewed models. They are decision guidance, not accuracy claims.
| Setup | Rank | Fit score | Top match |
|---|---|---|---|
| Long recordings on an 8–12 GB NVIDIA GPU, balanced | #24 of 26 | 65/100 · Possible fit | Whisper turbo |
| Live captions or voice input (native streaming + timestamps, speed first) | #14 of 26 | 77/100 · Strong fit | Nemotron 3.5 ASR Streaming 0.6B |
| Subtitles with timing, accuracy first | #23 of 26 | 61/100 · Possible fit | Whisper medium |
| Meetings with speaker labels (diarization + timestamps) | #13 of 26 | 74/100 · Strong fit | VibeVoice-ASR 7B |
| CPU-only machine, low memory use | #24 of 26 | 48/100 · Weak fit | VibeVoice-ASR-BitNet |
| Apple Silicon with 8–16 GB unified memory, long recordings | #26 of 26 | 50/100 · Weak fit | Whisper small |
| Japanese live transcription (native streaming, speed first) | #5 of 26 | 77/100 · Strong fit | Nemotron 3.5 ASR Streaming 0.6B |
Supported languages
- English
en - French
fr - German
de - Italian
it - Japanese
ja - Korean
ko - Mandarin Chinese
zh - Portuguese
pt - Russian
ru - Spanish
es
Compare coverage across every reviewed model in the language support matrix.
Community activity on Hugging Face
- Downloads, last 30 days
- 7,826
- Likes
- 268
- Repository last updated
- 3 Sept 2026
- Published on the Hub
- 2 Sept 2026
Figures from the Hugging Face Hub API, 11 Nov 2026. Source: huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B ↗. Downloads count file downloads, not active users, and do not affect the matcher's scores. Compare all models.
How to run VibeVoice-ASR-Streaming-7B locally
The 7B streaming model loads through Transformers; Microsoft's VibeVoice repository holds the full instructions. Runtimes below are the ones the official model card or repository documents for this model (checked November 2, 2026).
- Hugging Face Transformers ↗Framework · usage shown on the model card
- microsoft/VibeVoice ↗Official package · full installation and usage
Install command shown in the official huggingface.co page ↗:
pip install -U transformers accelerate
Audio input: Continuously transcribes who said what as speech arrives; customized hotwords are supported.
Official hardware guidance: No memory figure is published; the card lists 9B parameters. Source ↗
Whatever runtime you choose, measure speed and accuracy on your own audio with the benchmark tool; results differ a lot between runtimes, precision and hardware.
Before you deploy VibeVoice-ASR-Streaming-7B
A printable checklist built from the facts on this page. Tick it off before putting the model into production.
- Language. Confirm your language is in the 10-language list on this page, and test any accents or code-switching you expect.
- License. MIT: Include the copyright notice and the permission notice in all copies or substantial portions. Provided as is, without warranty. License guide.
- Install. Start from the official command:
pip install -U transformers accelerate(full run notes). - Audio input. Continuously transcribes who said what as speech arrives; customized hotwords are supported.
- Hardware. No memory figure is published; the card lists 9B parameters.
- Features you rely on. For VibeVoice-ASR-Streaming-7B, native streaming is documented; timestamps are limited or runtime-dependent; speaker attribution is native. Test each one you need with real audio.
- Measure. Run 10–20 representative clips, score them with the WER calculator and record speed in the benchmark workspace before you commit.
- Provisional ratings. This model was added on November 3, 2026; treat its hardware and workload ratings as estimates and weight your own measurements higher.
Alternatives and related models
Same family: VibeVoice-ASR 7B, VibeVoice-ASR Streaming 1.5B, VibeVoice-ASR-BitNet.
Similar fit profile: Jais-ASR (IFM, 5.7B total), Cohere Transcribe 03-2026 (Cohere Labs, 2B), Fun-ASR-MLT-Nano-2512 (FunAudioLLM, 800M). Similarity is computed from the ten fit ratings plus streaming and diarization support.
| Fact | VibeVoice-ASR-Streaming-7B | VibeVoice-ASR 7B | VibeVoice-ASR Streaming 1.5B |
|---|---|---|---|
| Provider · size | Microsoft · 9B total | Microsoft · 9B total | Microsoft · 3B total |
| License | MIT Permissive | MIT Permissive | MIT Permissive |
| Languages | 10 listed languages | 51 listed languages | 10 listed languages |
| Streaming | Native | Batch-first | Native |
| Timestamps | Limited | Yes | Limited |
| Speaker diarization | Native | Native | Native |
| CPU · Apple · NVIDIA fit | 1/5 · 1/5 · 4/5 | 1/5 · 2/5 · 4/5 | 1/5 · 2/5 · 4/5 |
| Live · long recordings | 4/5 · 4/5 | 1/5 · 5/5 | 5/5 · 4/5 |
| Main runtime | Hugging Face Transformers | microsoft/VibeVoice | microsoft/VibeVoice |
Head-to-head pages: VibeVoice-ASR Streaming 1.5B vs VibeVoice-ASR-Streaming-7B
Compare VibeVoice-ASR-Streaming-7B side by side
Check VibeVoice-ASR-Streaming-7B for your setup
Pick your language, hardware and workload to see this model's fit score, the reasons behind it and where it ranks against all reviewed models. Everything runs in your browser.
Common questions
Can I use VibeVoice-ASR-Streaming-7B commercially?
Permissive license; commercial use is allowed under the listed terms. The listed license is MIT; read the current license text ↗ before shipping a product, because terms can change. The license guide compares the obligations of all 26 reviewed models.
Does VibeVoice-ASR-Streaming-7B support real-time streaming?
Yes. The reviewed source describes a native streaming architecture, so it is a candidate for live captions, dictation or voice agents. Measure end-to-end latency on your own hardware.
Which languages does VibeVoice-ASR-Streaming-7B transcribe?
10 listed languages. The full list of 10 explicitly enumerated languages is shown above.
Can VibeVoice-ASR-Streaming-7B tell speakers apart?
Yes. The reviewed source documents native speaker-attributed transcription. Still check accuracy on overlapping speech in your own recordings.
Primary sources
Reviewed against primary sources on November 3, 2026. Model behavior, runtime support, language coverage and licenses can change; re-check the linked primary source before production use. See the full source directory.