AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

StepFun ASR (stepaudio-2.5-asr) Transcription

A skill that transcribes Chinese/English audio up to ~30 minutes in a single call via StepFun's stepaudio-2.5-asr SSE endpoint.

UtilitiesIntermediate★ 1,393⑂ 219AI score 8/10Last updated: Sep 15, 2026

What it does

  • Calls StepFun's stepaudio-2.5-asr model on the correct endpoint (/v1/audio/asr/sse) to turn speech into text.
  • The bundled scripts/asr_transcribe.py handles base64 encoding, the nested JSON body, and SSE event parsing for you.
  • Uses the 32K context window to transcribe 5–30 minute recordings in one request — no client-side chunking.
  • Ships lookup tables for the classic traps: the misleading model stepaudio-2.5-asr not supported error (really a wrong-endpoint problem), Plan vs Normal API keys, mid-stream error events, and repetition hallucination.
  • Suggests sensible follow-ups after transcription (transcript cleanup or structured meeting minutes).

Who it's for

  • Developers using the StepFun API for Chinese/English speech-to-text.
  • Teams evaluating migration from step-asr / step-asr-1.1.
  • Anyone processing long-form audio (podcasts, interviews, meetings) without splitting files.
  • People who have burned hours on opaque 4xx errors or "model not supported" messages.

Examples

  1. python3 scripts/asr_transcribe.py interview.mp3 — transcribe a 17-minute interview in roughly 10 seconds of wall clock.
  2. python3 scripts/asr_transcribe.py talk.wav --language en --json — transcribe an English talk and capture token usage and timing as JSON.
  3. For recordings over 30 minutes, split with ffmpeg, transcribe each part, then hand the text to a meeting-minutes skill to extract decisions and action items.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/daymade/claude-code-skills/HEAD/daymade-audio/stepfun-asr/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the daymade-audio/stepfun-asr folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/stepfun-asr/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git && mkdir -p ~/.claude/skills && cp -r claude-code-skills/daymade-audio/stepfun-asr ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/daymade/claude-code-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy just this skill: cp -r claude-code-skills/daymade-audio/stepfun-asr ~/.claude/skills/
  4. Get an API key at https://platform.stepfun.com/ → API Keys. You must use a Normal key; "Plan" keys cannot call audio endpoints.
  5. Export the key: export STEPFUN_API_KEY="your_key" (add it to your shell profile to persist it).
  6. Make sure Python 3 is installed, plus ffmpeg if you need to transcode mp4/m4a/webm to mp3/wav/ogg.
  7. Restart Claude Code and try: "Transcribe this mp3 with StepFun ASR."
View source on GitHub ↗License: MIT