elevenlabs-stt — Claude Code skill: what it does, how to install
elevenlabs-stt runs ElevenLabs Scribe speech-to-text models and forced text alignment via the belt command-line tool.
no license 236 installs ★ 31 updated 2026-08-31
npx skills add 101-skills/superpowers --skill elevenlabs-stt -a claude-codeWhat elevenlabs-stt does
This skill drives ElevenLabs Scribe speech recognition pipelines using the belt CLI tool from inference.sh. It supports both scribe_v2 and scribe_v1, covering over 90 languages with reported 98%+ accuracy. You can instruct the agent to run speaker diarization or flag non-speech audio events such as laughter and music.
For projects with an existing transcript, the skill runs forced alignment through elevenlabs/forced-alignment. That produces character and word timestamps suitable for subtitle generation, lyric display, or animation lip-sync.
Workflows fail immediately if the machine lacks the belt CLI or an active session via belt login. The skill configuration restricts execution strictly to Bash(belt *) commands.
What it helps with
- transcribe meeting recordings with speaker identification
- generate word-level timestamps to sync subtitles or captions
- tag non-speech audio events like laughter or applause
- align existing narration scripts against voice recordings
Example prompts for the agent
- Transcribe the recording at
https://meeting.mp3with diarization enabled - Align this script text against
https://narration.mp3and get word timestamps - Generate a transcript for
https://podcast.mp3and flag audio events
How to install elevenlabs-stt
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill elevenlabs-stt -a claude-code2Manually: put the files in place
~/.claude/skills/elevenlabs-stt/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/elevenlabs-stt/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill elevenlabs-stt -a codex2Manually: put the files in place
.agents/skills/elevenlabs-stt/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill elevenlabs-stt -a cursor2Manually: put the files in place
.cursor/skills/elevenlabs-stt/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install 101-skills/superpowers tools/audio/elevenlabs-stt2Manually: put the files in place
.github/skills/elevenlabs-stt/SKILL.md1Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill elevenlabs-stt -a gemini-cli2Platform CLI
gemini skills install https://github.com/101-skills/superpowers --path tools/audio/elevenlabs-sttManually: put the files in place
.devin/skills/elevenlabs-stt/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add 101-skills/superpowers --skill elevenlabs-stt -a opencodeClaude.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-stt
How do I install elevenlabs-stt in Claude Code?
Run npx skills add 101-skills/superpowers --skill elevenlabs-stt -a claude-code. You also need the belt CLI installed and authenticated with belt login.
What does elevenlabs-stt do?
It runs speech-to-text on audio files using ElevenLabs Scribe models, identifies different speakers, and tags background sounds. It also aligns provided scripts to audio tracks to produce exact word timestamps.
Which models does elevenlabs-stt support?
The skill works with scribe_v2 as the default model and supports scribe_v1 as an alternative.