elevenlabs-transcribe — Claude Code skill: transcription
elevenlabs-transcribe is a Claude Code skill that sends audio and video files to ElevenLabs Scribe v2 and returns a transcript. Set the language, output file, or speaker count.
no license ★ 1,357 updated 2026-03-01
npx skills add qdhenry/Claude-Command-Suite --skill elevenlabs-transcribe -a claude-codeWhat elevenlabs-transcribe does
This skill turns speech in audio and video into text through ElevenLabs Scribe v2. It can label speakers and mark sounds such as laughter or applause. Provide an ISO-639 language code, or let the service detect the language.
You need ELEVENLABS_API_KEY in the project’s .env file and uv installed. The script stops when the key is missing, and it needs uv to run. Script dependencies are handled through uv; the transcript can go to the terminal or a file.
Options let you set the speaker count, supply terms to guide recognition, and choose timestamp detail. You can turn off speaker labels or sound tagging, or request JSON output. The maximum file size is 3GB.
What it helps with
- transcribe a meeting or interview recording
- write a transcript to a chosen file
- separate spoken text by speaker
- add word- or character-level timestamps
- mark laughter, music, and other sounds
Example prompts for the agent
- Transcribe
meeting.mp3and label each speaker. - Save a transcript of
interview.wavtotranscript.txtineng. - Process
demo.mp4and return the full JSON response.
How to install elevenlabs-transcribe
1Skills CLI (Vercel)
npx skills add qdhenry/Claude-Command-Suite --skill elevenlabs-transcribe -a claude-code2Manually: put the files in place
~/.claude/skills/elevenlabs-transcribe/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/elevenlabs-transcribe/
1Skills CLI (Vercel)
npx skills add qdhenry/Claude-Command-Suite --skill elevenlabs-transcribe -a codex2Manually: put the files in place
.agents/skills/elevenlabs-transcribe/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add qdhenry/Claude-Command-Suite --skill elevenlabs-transcribe -a cursor2Manually: put the files in place
.cursor/skills/elevenlabs-transcribe/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install qdhenry/Claude-Command-Suite .claude/skills/elevenlabs-transcribe2Manually: put the files in place
.github/skills/elevenlabs-transcribe/SKILL.md1Skills CLI (Vercel)
npx skills add qdhenry/Claude-Command-Suite --skill elevenlabs-transcribe -a gemini-cli2Platform CLI
gemini skills install https://github.com/qdhenry/Claude-Command-Suite --path .claude/skills/elevenlabs-transcribeManually: put the files in place
.devin/skills/elevenlabs-transcribe/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about elevenlabs-transcribe
How do I install elevenlabs-transcribe in Claude Code?
Run npx skills add qdhenry/Claude-Command-Suite --skill elevenlabs-transcribe -a claude-code, then use ~/.claude/skills/elevenlabs-transcribe/SKILL.md.
What does elevenlabs-transcribe do?
It sends an audio or video file to ElevenLabs Scribe v2 and returns the recognized speech. With the relevant options enabled, it also labels speakers and detected sounds.
What does elevenlabs-transcribe require?
Set ELEVENLABS_API_KEY in the project’s .env file and have uv installed. Processing stops if the key is missing.