domains / families / media / stepfun-asr

stepfun-asr

separate

Transcribes Chinese/English audio with StepFun's stepaudio-3-asr-max via its SSE endpoint (not /v1/audio/transcriptions) — one call handles long-form audio with no chunking. Use when migrating from step-asr/stepaudio-2.5-asr, or hitting the misleading "model not supported" error (actually wrong endpoint). Triggers on 阶跃 ASR, 语音识别. Not for TTS with the sibling model (use stepfun-tts).

When to use

• Transcribing Chinese audio
• Transcribing English audio
• Handling long-form audio without chunking
• Migrating from step-asr or stepaudio-2.5-asr
• Resolving 'model not supported' endpoint errors
• Generating per-word timestamps
• Speaker labeling via async file endpoint

When not to use

• Text-to-Speech (TTS) generation
• Using stepfun-tts skill
• Processing audio longer than 30 minutes without splitting
• Using Plan subscription keys for audio endpoints

Skill page

Source