Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates audio visualization videos using the each::sense AI API. Accepts an audio file URL and a text description of the desired visual style, then returns a rendered video. Supports waveforms, spectrum analyzers, particle systems, 3D landscapes, and beat-synced animations.
Describing the visual style in plain text and iterating with session_id removes the need for video editing software or manual keyframing.
When to use it
- Adding a waveform video to a podcast episode upload
- Creating a YouTube visualizer for a music track release
- Generating a looping Spotify Canvas from a song
- Making beat-synced visuals for a TikTok or Instagram Reel
- Producing branded circular visualizers for a record label's social media
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Create a neon spectrum analyzer for my EDM track at https://example.com/track.mp3
- 1Accepts the audio URL and style description from the user
- 2Sends a POST request to https://sense.eachlabs.run/chat with the audio URL, style prompt, and mode set to max
- 3Streams the response and waits for the rendered video URL
- 4Returns the video URL to the user
- 5Optionally continues the session with a session_id to refine colors or add effects
A 1920x1080 MP4 video of a neon spectrum analyzer reacting to the track
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.