StepFunStep ASR
Step ASR
Step ASR supports Chinese and English speech recognition. Its identifier remains in the billing catalog.
Keep the earlier recognizer distinct
The guide covers real-time and offline recognition.StepFun audio model overview
Use current endpoint documentation
Practical guidance. If maintaining an existing integration, check the endpoint as well as the model name. New file and live-stream guides prefer StepAudio 2.5 ASR, which makes it the clearer starting point for a new transcription workflow.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | step-asr |
| Access | Listed in the current hosted billing catalog.StepFun billing catalog and 9 November 2026 audio change |
Related models
- Step ASR 1.1
StepFun · Step ASR
A speech-recognition model with separate file-transcription and live-streaming variants.
Launch date not confirmedDeprecated API; check access detailsAPI - StepAudio 2.5 ASR
StepFun · StepAudio 2.5
StepAudio 2.5 ASR is a 4B speech recognition model that uses multi-token prediction.
Launch date not confirmedAPI