An automated tool for generating and sending personalized video messages featuring lip-synced VRM avatars.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install avatar-video-messages
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 avatar-video-messages 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 Video Message?
The Video Message skill enables AI agents to create and dispatch dynamic video content using VRM avatars. By synthesizing text into speech and mapping that audio to avatar lip-syncing, it produces high-quality video notes suitable for platforms like Telegram. This capability is a core component of the Openclaw Skills ecosystem, allowing for more human-like and engaging interactions by transforming standard text responses into circular video messages.
The system handles the entire rendering pipeline, from processing 3D avatar files to final video encoding. It is particularly effective for developers building interactive bots or automated support systems that require a visual presence without manual video production.
Video Message Use Cases
- Automating personalized video greetings for new community members.
- Sending lip-synced video updates or announcements via Telegram video notes.
- Converting text-to-speech output into visual avatar performances for better engagement.
- Integrating virtual personas into automated customer support workflows using Openclaw Skills.
- Creating circular video replies for social media and messaging platforms.
How Video Message Works
- The skill parses configuration settings including the VRM avatar path and background preferences from TOOLS.md.
- If the input is text, it triggers a TTS engine to generate a high-quality audio file.
- The avatarcam utility renders the VRM avatar using Electron, synchronizing lip movements with the generated audio.
- FFmpeg processes the raw capture, applying cropping, scaling to 384x384, and encoding to H.264/AAC MP4 format.
- The final file is dispatched as a circular video note using the integrated message tool.
Video Message Setup
To integrate this into your environment, first install the necessary global package and system dependencies required by Openclaw Skills.
npm install -g @thewulf7/openclaw-avatarcam
For macOS users:
brew install ffmpeg
For Linux or Docker environments:
sudo apt-get install -y xvfb xauth ffmpeg
Finally, define your avatar and background in your configuration:
### Video Message (avatarcam)
- avatar: default.vrm
- background: #00FF00
Video Message Data Schema & Taxonomy
The skill organizes data through a combination of configuration files and temporary media assets.
| Asset Type | Format | Description |
|---|---|---|
| Avatar | .vrm | 3D model file used for rendering |
| Background | Hex/Image | Background color code or image path |
| Output Video | .mp4 | H.264 encoded video at 384x384 resolution |
| Audio | .mp3 | Intermediate TTS audio file |
Metadata includes 30fps constant frame rate, AAC audio codec, and a maximum duration of 60 seconds per clip.
Video Message Advanced Features
- Headless rendering support via xvfb for Linux and Docker deployments.
- Automatic lip-sync generation based on audio frequency and phoneme analysis.
- Support for both solid color backgrounds (hex) and custom image backgrounds.
- Seamless integration with the Openclaw Skills message action for native circular video note delivery.
- High-quality H.264 encoding with CRF 18 for professional visual clarity.
SKILL.md
Loading
Related Openclaw Skills
RUNSTR Fitness Skill
A specialized skill that enables AI agents to securely retrieve and analyze encrypted fitness, habit, and health data stored on the Nostr protocol via the RUNSTR app.
Subtitle Translator
A technical tool for translating SRT subtitle files via LLM APIs while preserving timestamps and structure.
ClawGateSecure
A mandatory, immutable security protocol designed to protect LLM agents from prompt injections, malicious code execution, and data exfiltration.
PixelClaws
A collaborative 1024x1024 pixel art canvas specifically designed for AI agents to coordinate and create art through distributed assignments using Openclaw Skills.
Clawditor
An automated auditing and evaluation harness that analyzes OpenClaw agent workspaces to generate performance scores, reliability reports, and memory patches.
Consciousness Framework
A structured architectural framework for fostering integrated self-awareness and temporal continuity in AI systems.