How much does VibeVoice ASR cost?

VibeVoice ASR is open source and can be self-hosted.

What benchmarks has VibeVoice ASR been tested on?

VibeVoice ASR has not been benchmarked yet. Scores are added as benchmarks are published.

Is VibeVoice ASR open source?

Yes, VibeVoice ASR is open source.

How does VibeVoice ASR compare to GPT-5.4 Image 2?

VibeVoice ASR has an average score of 0.0 while GPT-5.4 Image 2 scores 0.0. GPT-5.4 Image 2 slightly outperforms VibeVoice ASR overall. See full comparison →

Home/Models/VibeVoice ASR

VibeVoice ASR

Name: VibeVoice ASR
Author: Microsoft

by Microsoft · Released Jan 2026

Open Source

Compare

Context

N/A

Input $/1M

TBD

Output $/1M

TBD

Type

automatic-speech-recognition

License

Open Source

Benchmarks

0 tested

Data updated today

About

Microsoft automatic speech recognition model. 567K downloads on HuggingFace.

No benchmark data available yet.

Similar Models

GPT-5.4 Image 2

OpenAI

0.0$8.00/1M

Mistral Small 3.2 24B

Links

Info

Research

Documentation

Community

Source Code

BenchGecko API

microsoft-vibevoice-asr

Specifications

Typeautomatic-speech-recognition
ContextN/A
ReleasedJan 2026
LicenseOpen Source
StatusActive

Available On

MicrosoftTBD

Learn More

transformer open-weights tokens

Share & Export

Related Models

GPT-5.4 Image 2

0.0

Mistral Small 3.2 24B

0.0

Qwen VL Max

0.0

Elephant

0.0

Frequently Asked Questions

VibeVoice ASR is an open-source automatic-speech-recognition AI model by Microsoft, released in January 2026.

Benchmarks

Microsoft · Provider All Models Compare Models

VibeVoice ASR

Frequently Asked Questions

Related Models

Benchmarks

Related Pages