Agent skill · ElevenLabs
ElevenLabs Speech to Text skill for Claude Code, Codex and Cursor
Officialname: speech-to-text★ 508 (repo)pushed 2026-10-24MITSKILL.md on GitHubchecked 2026-11-07
What it does, in the publisher's words
Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.
The description field of the SKILL.md. The agent reads only this at startup and decides from it when to load the full skill.
Install ElevenLabs Speech to Text
The skills CLI copies the skill into the folder of each agent you pick (Claude Code, Codex, Cursor, Copilot, Gemini CLI, OpenCode, Windsurf...). Add -g for all projects. Needs Node.js 22.20+. docs
npx skills add elevenlabs/skills --skill speech-to-text
Copy the skill folder into ~/.claude/skills (all projects) or .claude/skills (this repo). Claude Code picks it up without a restart. docs
npx skills add elevenlabs/skills --skill speech-to-text -a claude-code # or by hand: git clone --depth 1 https://github.com/elevenlabs/skills.git /tmp/speech-to-text-src cp -r /tmp/speech-to-text-src/speech-to-text ~/.claude/skills/speech-to-text
Download the skill folder, zip it, then Customize > Skills > + > Create skill > Upload a skill. Code execution must be on (Settings > Capabilities). docs
git clone --depth 1 https://github.com/elevenlabs/skills.git /tmp/speech-to-text-src cp -r /tmp/speech-to-text-src/speech-to-text ./speech-to-text zip -r speech-to-text.zip speech-to-text
Codex reads skills from .agents/skills in the repo or ~/.agents/skills. Type $ in Codex to use one. docs
npx skills add elevenlabs/skills --skill speech-to-text -a codex
gh skill (GitHub CLI 2.90+, preview) installs it for Copilot in VS Code, the CLI and the cloud agent. Copilot also reads .github/skills and ~/.copilot/skills. docs
gh skill install elevenlabs/skills speech-to-text
Cursor reads .cursor/skills, .agents/skills and ~/.cursor/skills (and .claude/skills). It does not install loose skills from a GitHub URL, so copy it in. docs
npx skills add elevenlabs/skills --skill speech-to-text -a cursor
Installs from the GitHub repo; --path picks this skill out of the repo. Default scope is user (all projects). docs
gemini skills install https://github.com/elevenlabs/skills.git --path speech-to-text
OpenCode reads .opencode/skills, ~/.config/opencode/skills and the Claude and .agents folders. docs
npx skills add elevenlabs/skills --skill speech-to-text -a opencode
Windsurf (now Devin Desktop) reads .devin/skills, .windsurf/skills and ~/.codeium/windsurf/skills. docs
npx skills add elevenlabs/skills --skill speech-to-text -a windsurf
Works with
Claude Code, Claude.ai and Claude Desktop, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and other agents that read the open Agent Skills format.
- The SKILL.md says: "Requires internet access and an ElevenLabs API key (ELEVENLABS_API_KEY)."
What's in the SKILL.md
- Quick Start
- Python
- JavaScript
- CLI
- Models
- Transcription with Timestamps
- Speaker Diarization
- Multichannel Audio
- Keyterm Prompting
- Language Detection
- Supported Formats
- Response Format
- Error Handling
- Tracking Costs
- Real-Time Streaming
- Python (Server-Side)
- JavaScript (Client-Side with React)
- Commit Strategies
- Event Types
- References
Bundled files
- references/installation.md
- references/realtime-client-side.md
- references/realtime-commit-strategies.md
- references/realtime-events.md
- references/realtime-server-side.md
- references/transcription-options.md
Loaded only when the instructions point to them.
Facts
- Skill name
- speech-to-text
- Publisher
- ElevenLabs (official)
- Repo
- elevenlabs/skills
- License
- MIT
- SKILL.md size
- 711 words, 322 lines
- Bundled files
- 6, 6 docs
- Repo stars
- 508 (as of 2026-10-24)
- SKILL.md checked
- 2026-11-07
Pairs with the ElevenLabs MCP server: the server gives the agent the tools, the skill teaches it how to use them.
More skills from elevenlabs/skills
- ElevenLabs Voice Agents: Builds real-time voice assistants with ElevenLabs, including their tools and workflows.
- ElevenLabs Text to Speech: Generates spoken audio from text with ElevenLabs voices in many languages.
Related media skills
- Canvas Design · Anthropic
- Slack GIF Creator · Anthropic
- Image Generation · OpenAI
- Remotion Best Practices · Remotion
- Remotion Render · Remotion
FAQ
What does the speech-to-text skill do?+
Transcribes audio or video to text and subtitles with ElevenLabs Scribe. In its own SKILL.md, ElevenLabs describes it as: "Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content."
How do I install the speech-to-text skill?+
Run npx skills add elevenlabs/skills --skill speech-to-text and pick your agents, or use the tab for your agent above. In Claude Code the skill ends up in ~/.claude/skills/speech-to-text/SKILL.md; in Codex and Cursor in .agents/skills/speech-to-text/.
Does ElevenLabs Speech to Text work in Codex, Cursor and Copilot, or only Claude?+
It's a standard SKILL.md, so any agent that reads the Agent Skills format can use it: Claude Code, the Claude apps, Codex, GitHub Copilot, Cursor, Gemini CLI, OpenCode, Windsurf and more. The SKILL.md notes: Requires internet access and an ElevenLabs API key (ELEVENLABS_API_KEY).
Who maintains ElevenLabs Speech to Text?+
ElevenLabs, the company or project behind it, in the elevenlabs/skills repo on GitHub, last pushed 2026-10-24. License: MIT.
Read a skill's SKILL.md and scripts before you install it: skills aren't verified by any agent vendor. Claude skills marketplace · How to install skills · MCP servers