stepaudio-3-asr-max
StepFun's largest LLM-based ASR model, with context-aware recognition of names, domain terms, dialects, code-switching, whispers and singing.
01 Price
$0.60per hour
Cheaper than 54% of 236 priced speech-to-text and realtime models.
Speech-to-text and realtime $ per hour of audio, log scale 236 priced
other models this modelAll models by price
Price effective 2026-11-17 12:00 UTC+8 per StepFun pricing notice (recorded 2026-11-16). Billed by input audio duration. Model page still shows the pre-change $0.24/hour.
Pricing source, checked 2026-11-16
02 Languages 6
03 Features 0 of 11 listed
- Word timestampsnot listed
- Speaker diarizationnot listed
- Punctuationnot listed
- Profanity filternot listed
- Custom vocabularynot listed
- Language detectionnot listed
- Translationnot listed
- Sentimentnot listed
- PII redactionnot listed
- Summarizationnot listed
- Topic detectionnot listed
"Not listed" means the provider's data doesn't mention it, not that the model lacks it.
04 Get this record
curl https://voicedex.dev/v1/providers/stepfun/models/stepaudio-3-asr-max
Free, no key needed. Use model id stepaudio-3-asr-max with StepFun's own API. API reference.