libregistry
Registry
Models
Docker
IAM
MCP
Docs
Sign in with Google
Models
/
microsoft
/ VibeVoice ASR
VibeVoice ASR
JSON →
audio
A Microsoft speech recognition model optimized for real-time transcription with low latency.
audio
streaming
homepage ↗
Specs
Context & limits
—
context window
—
max output
Lifecycle
Dates
released
2024-03-01
Resources
homepage
https://huggingface.co/microsoft/VibeVoice-ASR ↗