Skills Explorer Add Skills

stepfun-asr

An agent skill by daymade, from daymade/claude-code-skills. Tags: api, audio, ml, stepfun, transcription.

What it does

Transcribe audio with StepFun's stepaudio-3-asr-max — an SSE endpoint (NOT /v1/audio/transcriptions), single call handles long audio with no client-side chunking. Use when transcribing Chinese / English audio with StepFun, when long-form recordings (5-30 min) need to land in one request, when migrating from step-asr / step-asr-1.1 / stepaudio-2.5-asr, or when hitting the misleading `model stepaudio-3-asr-max not supported` error (which actually means wrong endpoint). Triggers on 阶跃 ASR, StepFun ASR, stepaudio-3-asr-max, stepaudio-2.5-asr, 转录, 语音识别, 长音频转写, 语音转文字. For TTS with the sibling stepaudio-3-tts model, use the stepfun-tts skill instead.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add daymade/claude-code-skills --skill stepfun-asr

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/daymade/claude-code-skills
cp -r claude-code-skills/daymade-audio/stepfun-asr ~/.claude/skills/stepfun-asr

Safety box score

Grade C, moderate risk: 28 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill transcribes audio by sending it to StepFun's ASR API, and it also has a diarization path that sends a public audio URL to a separate StepFun endpoint. The main risks are external data egress, plain-text API-key handling, and a couple of helper scripts that read/write files outside the repo.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution1 (low)The skill ships runnable Python entry points (`python3 scripts/asr_transcribe.py`, `scripts/asr_file.py`, `scripts/check_params.py`) that execute live HTTP logic, but there is no shell eval or downloaded code.
Network access2 (moderate)The core behavior sends audio or audio URLs to StepFun (`https://api.stepfun.com/v1/audio/asr/sse`, `https://api.stepfun.com/v1/audio/asr/file`) and `check_params.py` also fetches live docs from `stepfun.mintlify.app`.
Filesystem reach2 (moderate)It reads arbitrary local audio paths via `audio_path.read_bytes()` and the setup instructions write `${CLAUDE_PLUGIN_DATA}/config.json`, which is outside the project tree.
Secrets & credentials2 (moderate)API keys are read from `STEPFUN_API_KEY` or `${CLAUDE_PLUGIN_DATA}/config.json`, and the skill explicitly tells the user to paste a "Normal key" into that file.
Privilege & persistence0 (none)No sudo, global installs, services, scheduled tasks, shell startup edits, or OS-level configuration changes are present.
Instruction hijack surface0 (none)There are no hidden prompts, remote instruction fetches, or directions to ignore safety/confirmation rules; the "do not" wording is ordinary usage guidance.
Irreversible actions0 (none)The skill only returns transcripts or JSON; it does not push, post, pay, deploy, delete, or otherwise take external actions on its own.
Transparency0 (none)All shipped content is plain-text Markdown/Python; there are no binaries, base64 blobs, minified bundles, or unreviewable installers.

Before installing

Rated 2026-10-19 by an automated review of 6 files from the skill's repository.

Source

Repository
daymade/claude-code-skills (all skills from this repository)
Path
daymade-audio/stepfun-asr/SKILL.md
Branch
main
Updated
2026-09-20