Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Provides text-to-speech, sound effects, music generation, voice cloning, and quota tracking through the ElevenLabs API. Outputs audio in multiple formats including MP3, PCM, and telephony-grade μ-law. Supports voice management and instant cloning from audio samples.
Covers the full ElevenLabs workflow from generation to quota monitoring in one skill, without switching between the API docs and separate scripts.
When to use it
- Generate a voiceover for a video using a specific ElevenLabs voice
- Create a custom sound effect like a cinematic boom or whoosh
- Produce a background music bed for a podcast intro
- Clone a voice from audio samples for consistent narration
- Check remaining character quota before a large TTS job
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Clone my voice from sample files and generate a voiceover saying 'Welcome to the show'
- 1Run voiceclone.py with provided audio sample files to create an instant voice clone
- 2Capture the new voice ID from the clone output
- 3Run speech.py with the cloned voice ID and the target text
- 4Save the output as an MP3 file
- 5Run quota.py to confirm remaining character balance after generation
output.mp3 containing the cloned voice saying 'Welcome to the show', with quota summary printed to console
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.