All tasks / Models
StepAudio 3 ASR
StepFun's closed speech recognition model served through the StepFun API platform.
- StepFun
- Closed
- Released 14 Sep 2026
Where it ranks
- STranscriptionModels · Cloud · 2.5% on Artificial Analysis Speech to Text: AA-WER v2 (non-streaming)
Facts
- Vendor
- StepFun
- Family
- StepAudio ASR
- Released
- 14 Sep 2026
- Weights
- Closed: API and apps only
- License
- proprietary
- API price
- $0.0067 per minute of audio (Artificial Analysis lists $6.67 per 1,000 minutes (StepAudio 3 ASR); divided by 1,000.)
- Last verified
- 19 Oct 2026
Price from artificialanalysis.ai, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Speech to Text: AA-WER v2 (non-streaming) | 2.5% | StepAudio 3 ASR, StepFunAA-WER v2 (non-streaming), provider StepFun; embedded value 0.025 converted to percent and rounded; page shows no last-updated date. | 19 Oct 2026 | artificialanalysis.ai |
Where you can use it
No tracked tool lists this model yet.
Earlier versions
- StepAudio 2.5 ASR · 22 Apr 2026