Transcription Skill

Transcribe speech in audio or video files (mp4, mov, mkv, wav, m4a, mp3) into a structured, timestamped Transcript with a local ASR engine (faster-whisper), Japanese and English first-class; export plain SRT/VTT; derive speech intervals. Use this skill whenever the user asks what is said in a recording, wants a transcript, timestamps of speech, word timings, or timed text to hand to a subtitle or editing tool. It does not edit video, style subtitles, detect speakers, or decide anything about a production.

6 starsImages, Video & Audio

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add kajisho5/transcription-skill --skill transcription-skill
Manual install
git clone --depth 1 https://github.com/kajisho5/transcription-skill.git /tmp/transcription-skill
mkdir -p ~/.claude/skills
cp -r /tmp/transcription-skill/. ~/.claude/skills/transcription-skill

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# transcription-skill

Run `transcription <command>` (installed by `pip install ".[faster-whisper]"`), or
`python3 -m transcription_skill.cli <command>`. Every command accepts `--json` (one JSON document on
stdout) and `transcribe` accepts `--dry-run` (plan only, no ASR).

## Workflow

1. **Doctor first** on a new machine: `transcription doctor`. It reports ffmpeg/ffprobe, the engine,
   which Whisper models are already cached, the workspace and the cache. Rows are `AVAILABLE`,
   `MISSING`, `DEGRADED` or `UNKNOWN`. Do not transcribe when the engine row is MISSING; tell the
   user the install line the row shows.
2. **Dry-run before long media**: `transcription transcribe input.mp4 --dry-run --json` shows the
   input's duration, the engine and model, the language mode, the budget and whether the cache already
   has this exact result (`cache.status: hit` means no ASR will run).
3. **Transcribe**: `transcription transcribe input.mp4 --language ja --json -o input.transcript.json`.
   Pass `--language` when the user names it; otherwise the language is auto-detected and recorded as
   `unknown` when detection is not confident. Add `--word-timestamps` only when words are needed
   (karaoke-style captions, precise cut points); it is slower.
4. **Check**: `transcription check input.transcript.json` validates the document. A transcript that
   fails validation is never produced by `transcribe`; run `check` on files that came from elsewhere.
Read the full skill on GitHub

Details

Skill name
transcription-skill
Repository
kajisho5/transcription-skill
License
MIT
Repo updated
31 October 2026

FAQ

What does the Transcription Skill skill do?

Transcribe speech in audio or video files (mp4, mov, mkv, wav, m4a, mp3) into a structured, timestamped Transcript with a local ASR engine (faster-whisper), Japanese and English first-class; export plain SRT/VTT; derive speech intervals. Use this skill whenever the user asks what is said in a recording, wants a transcript, timestamps of speech, word timings, or timed text to hand to a subtitle or editing tool. It does not edit video, style subtitles, detect speakers, or decide anything about a production.

How do I install the Transcription Skill skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add kajisho5/transcription-skill --skill transcription-skill. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Transcription Skill popular?

It lives in kajisho5/transcription-skill, which has 6 GitHub stars and 0 forks.

Related skills

Xhs Studio

6

waynefu2020/xhs-studio

Publishes image-text notes to Xiaohongshu (小红书) via a local MCP server. Supports text, images, tags, visibility settings, and scheduled publishing. Also supports searching trending content. Use when user asks to "post to XHS", "发小红书", "publish to Xiaohongshu", or "搜索小红书热点".

Images, Video & Audio

Pixel Snap

6

DreamC0der-AI/pixel-snap

Convert upscaled pixel art images back to clean, sharp pixel art. Detects grid size, extracts true pixel colors, and outputs crisp results. Supports icon mode (remove background, crop, center) and scene mode (preserve full image).

Images, Video & Audio

Bilibili Audio

5

shuolsure/bilibili-audio-skill

下载B站视频音频。支持单个视频下载和批量下载UP主所有视频。当用户提供B站视频链接（bilibili.com、b23.tv）、要求下载B站音频、下载B站视频、提取B站音频、或批量下载某个UP主的视频时使用。触发词：B站下载、bilibili下载、下载B站音频、B站音频、哔站下载。

Images, Video & Audio

Interior Vibing

6

zyliu0/interior-vibing

Generate professional, purposeful interior design renderings that solve specific user problems. Use this skill when a user uploads a room photo and wants design recommendations, staging plans, or visual concepts for any interior space. This skill ensures every rendering is specific to the room's architecture, the user's goal (sell, rent, host, refresh), and real purchasable items — never generic "modern living room" output. Trigger on: room photos, interior design requests, staging advice, rental optimization, Airbnb improvement, home sale prep, or any "how should I design this room" question.

Images, Video & Audio

Blender

5

LevyBytes/AI-SKILL-blender

Use when working with Blender workflows or Python APIs: .blend files, bpy scripting, operators, add-ons, extensions, animation, rigging, modeling, geometry and shader nodes, materials, UVs, sculpting, painting, cameras, lighting, rendering, compositing, video editing, linked libraries or user-interface controls. Not for other DCC applications or general Python unrelated to Blender.

Images, Video & Audio

Image Upload

6

iamzifei/image-upload-skill

Upload images to hosting providers and get shareable URLs 新手引导：输入 `/图床 新手`、「这个怎么用」「第一次用」「能干嘛」时，走 SKILL.md 的〈新手上路〉，不要直接开始干活。

Images, Video & Audio

Browse the most popular Claude skills, all images, video & audio skills, or write your own with the skills generator.