Vibevoice ASR HF
Microsoft's Vibevoice ASR HF is a speech-to-text model capable of handling long-form audio, generating structured transcriptions with speaker identification, timestamps, and content. It is particularly adept at processing audio up to 60 minutes in length in a single pass, thanks to its large context window of 131,072 tokens.
Input
Output
Context
131K
Max Output
-
Parameters
8.3B
Technical Specifications
Model TypeAudio
Context Window131,072 tokens
Max Output TokensNot available
Parameters8.3B
Release DateMar 2, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
AudioText
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Vibevoice ASR HF
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Microsoft
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.