Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Command-line interface for the ElevenLabs AI audio platform with full SDK coverage. Handles text-to-speech, speech-to-text, voice cloning, sound effect generation, audio isolation, dubbing, and conversational agent management. Community-built, not officially released by ElevenLabs.
Full SDK coverage in a single CLI means you can access every ElevenLabs feature without switching between SDKs or writing custom API calls.
When to use it
- Convert a script file to an MP3 audiobook
- Transcribe a recorded meeting with speaker identification
- Clone a custom voice from audio samples
- Dub a video into another language
- Generate a sound effect from a text description
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: transcribe meeting.mp3 and identify the speakers
- 1Run `elevenlabs stt meeting.mp3 --diarize --num-speakers 3`
- 2CLI sends the audio file to the ElevenLabs API with diarization enabled
- 3API returns transcript with speaker labels and timestamps
- 4CLI outputs the result to stdout or a specified file
Transcript with labeled speaker turns and optional word-level timestamps
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.