StepAudio 2.5 ASR
by StepFunTranscription
Speech transcription model for accurate audio-to-text and captioning workflows
- 00
- Released
- 2026-04-24
- Weights
- Closed
stepfun/stepaudio-2-5-asr
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2026-04-24
- Weights
- Closed
- Input
- Audio
- Output
- Text
- Context window
- max across endpoints
- Max output
- Providers
- 2
- Epoch Capabilities Index
- not evaluated
- Direct price range
- no comparable direct price
More details
- Last updated
- 2026-07-02
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured outputunknown
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Cost calculator
Loading endpoints…
More from StepFun
Newest StepFun models in the catalogue. All StepFun models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Step 5 Preview | 2026-09-16 | 1M | from $0.959 /1M tok |
| Step 3.7 Flash | 2026-05-29 | 256K | from $0.185 /1M tok |
| StepAudio 2.5 TTS | 2026-04-16 | — | unpriced |
| Step 3.5 Flash 2603 | 2026-04-02 | 256K | from $0.10 /1M tok |
| Step TTS 2 | 2026-03-01 | — | unpriced |
| Step 3.5 Flash | 2026-01-29 | 256K | from $0.09 /1M tok |
| Gelab Zero 4b Preview | 2025-12-23 | 8.2K | unpriced |
| Step-3 | 2025-07-31 | 65.5K | unpriced |
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model