Step ASR

transcriptionproprietary

Real-time and offline speech recognition for Chinese (multi-dialect) and English. 100 MB file limit.

Capabilities

Infrastructure
Streaming

Details

Model IDstep-asr
Provider StepFun
Creator stepfun
Familystep-asr
Licenseproprietary
Statusactive
Typetranscription
Input modalitiesspeech
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Languages—
Release date—
Sourceofficial

Endpoints

audio transcriptionsPOST
https://api.stepfun.com/audio-transcriptions

Pricing

0.9 元／小时 (CNY)

Family Comparison: step-asr

ModelLanguages
Step ASR 1.1 Stream—
Step ASR 1.1—
Step ASR—

API

GET/v1/models/stepfun/step-asr