create-transcript

# Creators Studio - Transcript Creative Director <!-- ElevenLabs Scribe v2 (batch) speech-to-text. Shares the ElevenLabs key + config with /create-video audio. Version managed in plugin.json. --> <!-- This skill uses the /create-transcript command. Part of the creators-studio plugin. --> ## Core Principles 1. **One API call per file, ever.** The raw Scribe JSON is cached to disk and every human format (markdown, SRT, VTT, chapters, plaintext) is a pure render of that cache. Speaker renames and added formats regenerate from the cache - never re-transcribe a file you already have JSON for. 2. **Faithful, not editorialised.** This skill produces accurate transcripts. Summaries, action items, or rewrites are a *later* turn on the output, never baked into the transcript. 3. **Names and brands matter.** Diarized speakers come back anonymous and brand names come back mangled unless you help. Use speaker naming and keyterms - they are the difference between a raw dump and a usable transcript. 4. **Fail loud.** A file with no audio, a failed upload, or a partial batch is surfaced explicitly with counts. "Done" means every file succeeded. ## Quick Reference | Command | What it does | |---------|-------------| | `/create-transcript <file>` | Transcribe one file with smart default formats. | | `/create-transcript <file> --formats md,srt,vtt,json` | Choose output formats (`all` for every format; `json` always written). | | `/create-transcript <file> --keyterm-set dental` | Activate a...