Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates a sound effect audio file from a text description using the ElevenLabs SFX API. Accepts optional duration and prompt influence parameters for finer control. Validates the output for quality and retries up to twice on failure.
Built-in quality validation and automatic retry logic reduces manual iteration compared to calling the ElevenLabs API directly.
When to use it
- Generating laser or explosion sounds for a game prototype
- Adding ambient sound effects to a podcast or video edit
- Producing custom UI feedback sounds for an app
- Creating foley audio for a short film or animation
- Quickly testing how a described sound translates to audio
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a 3-second sound of a spaceship door opening with a pneumatic hiss
- 1Parse prompt text and duration_seconds: 3.5 from the request
- 2Prepare API payload with text, duration_seconds, and prompt_influence: 0.3
- 3Call ElevenLabs /v1/sound-generation endpoint
- 4Validate returned audio for silence or clipping artifacts
- 5Return sfx.mp3 with duration_ms and model metadata
spaceship_door_hiss.mp3, duration_ms: 3489, model: eleven_text_to_sound_v2
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.