← Back to Skills Marketplace
3075
Downloads
4
Stars
9
Active Installs
3
Versions
Install in OpenClaw
/install avatar-video-messages
Description
Generate and send video messages with a lip-syncing VRM avatar. Use when user asks for video message, avatar video, video reply, or when TTS should be delivered as video instead of audio.
README (SKILL.md)
Video Message
Generate avatar video messages from text or audio. Outputs as Telegram video notes (circular format).
Installation
npm install -g openclaw-avatarcam
Configuration
Configure in TOOLS.md:
### Video Message (avatarcam)
- avatar: default.vrm
- background: #00FF00
Settings Reference
| Setting | Default | Description |
|---|---|---|
avatar |
default.vrm |
VRM avatar file path |
background |
#00FF00 |
Color (hex) or image path |
Prerequisites
System Dependencies
| Platform | Command |
|---|---|
| macOS | brew install ffmpeg |
| Linux | sudo apt-get install -y xvfb xauth ffmpeg |
| Windows | Install ffmpeg and add to PATH |
| Docker | See Docker section below |
Note: macOS and Windows don't need xvfb — they have native display support.
Docker Users
Add to OPENCLAW_DOCKER_APT_PACKAGES:
build-essential procps curl file git ca-certificates xvfb xauth libgbm1 libxss1 libatk1.0-0 libatk-bridge2.0-0 libgdk-pixbuf2.0-0 libgtk-3-0 libasound2 libnss3 ffmpeg
Usage
# With color background
avatarcam --audio voice.mp3 --output video.mp4 --background "#00FF00"
# With image background
avatarcam --audio voice.mp3 --output video.mp4 --background "./bg.png"
# With custom avatar
avatarcam --audio voice.mp3 --output video.mp4 --avatar "./custom.vrm"
Sending as Video Note
Use OpenClaw's message tool with asVideoNote:
message action=send filePath=/tmp/video.mp4 asVideoNote=true
Workflow
- Read config from TOOLS.md (avatar, background)
- Generate TTS if given text:
tts text="..."→ audio path - Run avatarcam with audio + settings → MP4 output
- Send as video note via
message action=send filePath=... asVideoNote=true - Return NO_REPLY after sending
Example Flow
User: "Send me a video message saying hello"
# 1. TTS
tts text="Hello! How are you today?" → /tmp/voice.mp3
# 2. Generate video
avatarcam --audio /tmp/voice.mp3 --output /tmp/video.mp4 --background "#00FF00"
# 3. Send as video note
message action=send filePath=/tmp/video.mp4 asVideoNote=true
# 4. Reply
NO_REPLY
Technical Details
| Setting | Value |
|---|---|
| Resolution | 384x384 (square) |
| Frame rate | 30fps constant |
| Max duration | 60 seconds |
| Video codec | H.264 (libx264) |
| Audio codec | AAC |
| Quality | CRF 18 (high quality) |
| Container | MP4 |
Processing Pipeline
- Electron renders VRM avatar with lip sync at 1280x720
- WebM captured via
canvas.captureStream(30) - FFmpeg processes: crop → fps normalize → scale → encode
- Message tool sends via Telegram
sendVideoNoteAPI
Platform Support
| Platform | Display | Notes |
|---|---|---|
| macOS | Native Quartz | No extra deps |
| Linux | xvfb (headless) | apt install xvfb |
| Windows | Native | No extra deps |
Headless Rendering
Avatarcam auto-detects headless environments:
- Uses
xvfb-runwhen$DISPLAYis not set (Linux only) - macOS/Windows use native display
- GPU stall warnings are safe to ignore
- Generation time: ~1.5x realtime (20s audio ≈ 30s processing)
Notes
- Config is read from TOOLS.md
- Clean up temp files after sending:
rm /tmp/video*.mp4 - For regular video (not circular), omit
asVideoNote=true
Usage Guidance
This skill appears to do what it says: render lip-synced avatar videos and send them via the agent. Before installing, consider: 1) Inspect the npm package (@thewulf7/openclaw-avatarcam) source or run it in a sandbox because global npm installs can run arbitrary code. 2) Ensure TOOLS.md (the skill's config) is present and does not contain sensitive data you wouldn't want read by the skill. 3) Be aware generated videos are sent using the agent's messaging tool—verify that sending such media is appropriate for your privacy requirements. 4) Prefer installing in a controlled environment (container, VM) rather than directly on a sensitive host. If you want higher assurance, ask the skill author for a vetted release URL or review the npm package contents before global installation.
Capability Analysis
Type: OpenClaw Skill
Name: avatar-video-messages
Version: 0.1.2
The skill bundle is classified as benign. It describes a clear workflow for generating and sending video messages using `avatarcam` and `ffmpeg`. The `SKILL.md` provides transparent instructions for installing dependencies via `npm`, `brew`, and `apt`, and for executing the `avatarcam` binary with parameters directly related to its stated purpose. File system operations are limited to creating and cleaning up temporary video files (`rm /tmp/video*.mp4`). There is no evidence of data exfiltration, persistence mechanisms, obfuscation, or prompt injection attempts against the agent to perform actions outside the skill's stated purpose.
Capability Assessment
Purpose & Capability
Name/description (avatar video messages) match what the skill asks for: an 'avatarcam' binary to render VRM avatars and ffmpeg to post-process video. The declared npm/brew/apt installers align with providing those binaries.
Instruction Scope
Runtime instructions are focused on the task (generate TTS, run avatarcam, post via message). They reference reading TOOLS.md for configuration and checking $DISPLAY to decide on xvfb; the registry metadata did not declare TOOLS.md as a required config path or list environment checks, which is a minor mismatch but not a functional red flag. Instructions will run local binaries and send the generated video via the agent's message tool (expected for this capability).
Install Mechanism
Install spec uses a third-party npm package (@thewulf7/openclaw-avatarcam) to provide avatarcam and uses standard brew/apt packages for ffmpeg and xvfb. This is proportionate to the functionality but carries normal supply-chain risk because an unreviewed global npm package executes code on install and provides the avatarcam binary.
Credentials
The skill does not request secrets or credentials and only needs local binaries and (optionally) access to TOOLS.md and temporary files. It references $DISPLAY and Docker env var names in docs but does not require sensitive environment variables — access is proportionate to the task.
Persistence & Privilege
Skill does not request always:true or other elevated persistent privileges. Its install steps create a global npm binary if installed, which is normal for a tool; it does not modify other skills or system-wide OpenClaw configs beyond installing its own binary.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install avatar-video-messages - After installation, invoke the skill by name or use
/avatar-video-messages - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
- Switched configuration and usage instructions to reference TOOLS.md instead of gateway skill settings or openclaw.json.
- Updated install and usage commands to use openclaw-avatarcam as the package name.
- Settings and metadata sections revised for clarity and consistency.
- Expanded platform support documentation, including a table summarizing display dependencies.
- Minor clarifications and formatting improvements throughout documentation.update
v0.1.1
- Switched avatarcam npm package to @thewulf7/openclaw-avatarcam (was openclaw-avatarcam).
- Updated installation instructions and dependencies to use the new package.
- Added an example avatarcam --help command to the usage section for easier reference.
- No functional or workflow changes; documentation and dependency update only.
v0.1.0
Initial release: Generate and send lip-sync avatar video messages as Telegram video notes.
- Create video messages using a customizable VRM avatar and background.
- Converts text to speech, then generates a video with synchronized avatar lip movement.
- Outputs circular video (video note) format ready for Telegram.
- Supports configuration of avatar model and background via dashboard or JSON.
- Requires installation of system dependencies: ffmpeg, avatarcam, and (on Linux) xvfb/xauth.
- Provides detailed usage instructions for multiple platforms, including Docker.
Metadata
Frequently Asked Questions
What is Video Messages from your openclaw?
Generate and send video messages with a lip-syncing VRM avatar. Use when user asks for video message, avatar video, video reply, or when TTS should be delivered as video instead of audio. It is an AI Agent Skill for Claude Code / OpenClaw, with 3075 downloads so far.
How do I install Video Messages from your openclaw?
Run "/install avatar-video-messages" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Video Messages from your openclaw free?
Yes, Video Messages from your openclaw is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Video Messages from your openclaw support?
Video Messages from your openclaw is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Video Messages from your openclaw?
It is built and maintained by thewulf7 (@thewulf7); the current version is v0.1.2.
More Skills