StepFunWeights not listed·Not published context·— params
StepAudio 3 ASR Maxstepfun/stepaudio-3-asr-max
StepAudio 3 ASR Max transcribes audio into text, with contextual recognition of domain terms and mixed Chinese-English speech. The HTTP interface returns incremental and final text over SSE.
Availability and billing notes
Reviewed September 21, 2026 · check the linked provider documentation for later changes.
Model ID stepaudio-3-asr-max; POST /v1/audio/asr/sse. Official USD prices conflict: the model guide quotes $0.24/hour, while the central pricing page quotes $0.40/hour. Confirm the account billing rate before use; neither is presented as a settled price.
Capabilities
- speech_recognition
Technical specs
- Context
- Not published
- Max output
- —
- Parameters
- —
- Release
- —
- Training cutoff
- —
- License
- —
Similar models
- Qwen3.8 LiveTranslate Flash RealtimeAlibaba Cloud·— params·Context not published
- StepAudio 3 Chat PreviewStepFun·— params·Context not published
- StepAudio 3 Gen PreviewStepFun·— params·Context not published
- StepAudio 3 Music PreviewStepFun·— params·Context not published
- StepAudio 3 Realtime PreviewStepFun·— params·Context not published
Compare with
- StepAudio 3 ASR Max vs Qwen3.8 LiveTranslate Flash RealtimeComparison planned — not yet published
- StepAudio 3 ASR Max vs StepAudio 3 Chat PreviewComparison planned — not yet published
- StepAudio 3 ASR Max vs StepAudio 3 Gen PreviewComparison planned — not yet published
Fast Pivot — Access hundreds of AI models from a single API — competitive pricing, reliable uptime, enterprise-grade infrastructure.