A transparent desktop overlay featuring a pixel art lobster that provides real-time lip-syncing for AI agent speech output.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pixel-lobster
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pixel-lobster using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Pixel Lobster?
Pixel Lobster is a lightweight, Electron-based desktop overlay designed to give your AI agent a visual presence. By integrating with local Text-to-Speech (TTS) servers, this skill enables a charming pixel art lobster to animate its mouth in perfect synchronization with your agent's voice output. Unlike simple audio visualizers, it uses specific envelope data to ensure the lobster only speaks when the agent does, ignoring background music or system sounds.
As part of the expanding library of Openclaw Skills, Pixel Lobster offers a more immersive interaction model. It runs as a transparent window on your Windows or Linux desktop, allowing you to maintain a visual connection with your AI assistant without obstructing your primary workspace. The app is fully bundled within the skill, requiring no complex external cloning or repository management.
Pixel Lobster Use Cases
- Adding a visual persona to local AI agents during interactions
- Creating engaging desktop environments for developers using Openclaw Skills
- Providing visual feedback for AI voice responses in loud environments
- Livestreaming with an interactive AI-driven avatar overlay
How Pixel Lobster Works
- The skill launches a bundled Electron application that creates a transparent, stay-on-top desktop overlay.
- The app establishes a connection to a local TTS server (like XTTS) or an OpenClaw TTS proxy.
- It polls the audio envelope endpoint at 45ms intervals during active speech.
- Mathematical spring physics and viseme mapping convert the audio envelope data into six distinct mouth shapes.
- The lobster animations are rendered in real-time, providing low-latency lip-syncing synchronized with the agent's audio playback.
Pixel Lobster Setup
To get started with this entry in Openclaw Skills, follow these steps to install the bundled application:
# Navigate to the skill's app directory
cd <skill_dir>/app
# Install the necessary Electron dependencies
npm install
# Launch the lobster overlay via npx or the helper script
npx electron .
# OR
bash <skill_dir>/scripts/launch.sh
Pixel Lobster Data Schema & Taxonomy
The skill manages its behavior through a config.json file and processes animation via a viseme taxonomy:
| Configuration Key | Default | Description |
|---|---|---|
audioMode |
"tts" | Switch between reacting only to TTS or all system audio. |
ttsUrl |
"http://127.0.0.1:8787" | The endpoint for your local XTTS or TTS server. |
lobsterScale |
4 | The sprite scaling factor for the desktop display. |
clickThrough |
false | Determines if the window ignores mouse clicks. |
Animation Visemes:
- A-F: Six distinct mouth shapes (wide open, grin, round, pucker, etc.) driven by audio intensity.
- X: Default closed state for silence.
Pixel Lobster Advanced Features
- Multi-Monitor Cycling: Use the F8 keyboard shortcut to instantly move the avatar across different displays.
- Interactive Toggle: Use F9 to enable or disable click-through mode, allowing you to interact with windows behind the lobster.
- Sync Tuning: Adjustable
ttsPlayStartOffsetMsparameter to perfectly align mouth movement with specific audio drivers. - Performance Optimization: Dynamic polling intervals ensure the app uses minimal CPU resources when the agent is idle.
SKILL.md
Loading
Related Openclaw Skills
Local-First LLM Router
A smart routing agent that prioritizes local LLMs over cloud APIs to reduce costs and enhance data privacy.
Adaptive Routing
A local-first routing engine that prioritizes privacy and cost-efficiency by intelligently escalating LLM requests to the cloud only when necessary.
Supabase
A powerful integration for querying Supabase projects and generating user analytics directly from your chat interface.
Polymarket Prediction Market Tool
A comprehensive CLI tool for tracking Polymarket prediction markets, monitoring price momentum, and simulating trades via a local paper trading system.
Immich Photo Library (claw2immich)
Seamlessly interact with your Immich photo library through an AI agent using natural language and advanced metadata filtering.
Policy Engine
A deterministic governance layer for controlling AI agent tool execution and enforcing security policies.
METADATA
Featured*
