Overview
An audio-native reasoning model using Modality-Grounded Reasoning Distillation so test-time compute scaling operates on acoustic information.
Step-Audio-R1
An audio-native reasoning model using Modality-Grounded Reasoning Distillation so test-time compute scaling operates on acoustic information.
MODEL NUMBER344
- First public date
- 2025-11-27
- Organization
- StepFun
- Family
- StepAudio
01
Specifications
Only published specifications are shown.
- Input modalities
- Text · Audio
- Output modalities
- Text
- Open weights
- Yes
- License
- Apache-2.0
- Status
- Current
02
Overview
Why it mattered
Step-Audio-R1 extends StepFun’s reasoning line from text and vision to audio understanding.
03
Architecture & capabilities
Model capabilities
Native audioReasoning
04
Release history
Step-Audio-R1 inference code and weights were released.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.