StepAudio 2.5 ASR
by StepFun AI · family step · listed Apr 2026
Speech transcription model for accurate audio-to-text and captioning workflows
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
stepaudio-2.5-asr- Context window
- — tokens
- Max output
- —
- Input modalities
- audio
- Output modalities
- text
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-04-24
- Last updated
- 2026-07-02
Also listed at
- StepFun— in · — out