Speech-to-text
VibeVoice-ASR requirements, license & speed
By Microsoft · released 2026-01-21 · 8.67B parameters
Commercial useYes
Min memoryNot stated
Runs on CPUUnknown
StreamingNo
Key facts
- License
- mit source
- Commercial use
- Yes sourceMIT; Microsoft's repo advises further testing before commercial/real-world use
- Parameters
- 8.67B sourcesafetensors parameter count
- Minimum memory
- Not stated by source
- Runs on CPU
- Unknown
- Streaming
- No sourceThis checkpoint is offline; a separate VibeVoice-ASR-Streaming model exists
- Voice cloning
- n/a (speech-to-text)
- Languages
- 50+ languages source
- Released
- 2026-01-21 sourceHugging Face repo creation date (proxy for release date)
- Gated on HF
- No
Measured speed & memory
Benchmark pending. We haven't measured VibeVoice-ASR yet. Planned targets: CPU (8 vCPU), Apple Silicon Mac, RTX-class consumer GPU and a rented cloud GPU. Get notified.
Similar STT models
Spotted an error? Report it. Every fact links to the model card or repo it came from.