Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Starts an ElevenLabs MCP server that exposes 24 audio tools to an agent platform. Tools cover text-to-speech, sound effects, music composition, voice cloning, and speech transcription. Designed to be loaded at agent startup so other skills can call its tools directly.
Exposes 24 ElevenLabs audio capabilities as MCP tools so agents can call them natively without custom API integration code.
When to use it
- Adding spoken narration to a generated document
- Creating background music for a video project
- Transcribing recorded meeting audio to text
- Cloning a speaker's voice for consistent automated narration
- Generating sound effects for a game or interactive app
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a thunderstorm sound effect
- 1Agent identifies the request as a sound effects task
- 2Calls the text_to_sound_effects MCP tool with the description 'thunderstorm'
- 3ElevenLabs API processes the request and generates audio
- 4Server returns the audio file to the agent
- 5Agent delivers the file path or playback URL to the user
A thunderstorm sound effect audio file ready for download or playback
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.