Use when the user wants to transcribe a video or audio file to text with word-level timestamps — spins up a self-contained local Whisper (whisper.cpp) Docker service bundled in this skill and returns transcript.txt, transcript.srt, and word-level transcript.words.json. Also used as a building block by /produce-video. Triggers on "transcribe this video", "get a transcript", "transcribe-video".
安装
npx skills add AlemTuzlak/skills --skill transcribe-videonpx skills add AlemTuzlak/skills --skill transcribe-video -a claude-code -gnpx skills add AlemTuzlak/skills --skill transcribe-video -a codex -ggemini skills install https://github.com/AlemTuzlak/skills.git --path skills/transcribe-videogh skill install AlemTuzlak/skills transcribe-videogit clone --depth 1 https://github.com/AlemTuzlak/skills /tmp/AlemTuzlak__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/AlemTuzlak__skills/skills/transcribe-video ~/.claude/skills/transcribe-video # Claude Code
cp -R /tmp/AlemTuzlak__skills/skills/transcribe-video ~/.agents/skills/transcribe-video # Codex, Cursor, Gemini CLI, Copilot, OpenCode