# VibeVoice-ASR-Streaming model notes: Voice Benchmark Profile

> Microsoft’s model card documents streaming speaker-attributed transcription, hotword support, and ten-language coverage; evaluation results are published as an image.

- Scope: Capabilities and language coverage from the model card
- Measurement lanes: Conversation dynamics
- Primary metric: Documented capabilities (no scored benchmark)
- Available evidence: Evaluation table published only as an image
- Owner: Microsoft Research
- Source snapshots refreshed: 2026-09-11

## Interpretation limit

No numeric results are transcribed because the card publishes them as an image.

## Primary sources

- [Owner page](https://huggingface.co/microsoft/VibeVoice-ASR-Streaming-7B)

Canonical page: https://benchlm.ai/voice-benchmarks/vibevoice-asr-streaming-7b-launch-evaluation