Turn Chinese or English audio into a transcript.
What it does
Transcribes Chinese and English audio into text through StepFun's long-form speech recognition endpoint.
When to use it
Use for Chinese or English transcription, migration from older StepFun ASR models, or diagnosis of a misleading model-not-supported error.
How to use it
Give it an audio file; it returns a plain-text transcript, with JSON output available for timestamps and usage.
What you provide
- Your files
Uses
Good to know
- cannot be undone: StepFun; ${CLAUDE_PLUGIN_DATA}/config.json
Latest review
What you need · 2
Requires Python 3 to run the bundled transcription script.
Requires a StepFun account with access to a Normal API key; Plan subscription keys cannot call audio endpoints.
Access · 3
This skill
StepFun
Write
Sends audio to paid transcription (irreversible)
${CLAUDE_PLUGIN_DATA}/config.json
Write
Saves your API key (irreversible)