Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- 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
What This Skill Does
Generates video messages with a lip-syncing VRM avatar from text or audio input. Outputs 384x384 MP4 files formatted as circular video notes for Telegram. Supports custom avatars and configurable backgrounds.
Combines TTS generation and avatar lip-sync into a single automated step, letting you send expressive video messages without appearing on camera.
When to use it
- Sending a personalized avatar video reply in Telegram instead of typing
- Delivering TTS responses as video notes rather than audio messages
- Automating video greetings with a virtual avatar
- Creating short video updates using a custom VRM character
- Responding to Telegram messages with a circular video note
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Send me a video message saying hello
- 1Generate TTS audio from the text using the tts tool
- 2Run avatarcam with the audio file and configured background setting
- 3Encode output as a 384x384 H.264 MP4 at 30fps
- 4Send the file as a Telegram circular video note via the message tool
Circular video note delivered to Telegram with the avatar lip-synced to the spoken text