A professional AI video generation skill that converts text scripts and images into high-quality talking avatar presenter videos using cloud-based GPU rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install heygen-ai
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 heygen-ai 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 HeyGen AI?
The HeyGen AI skill enables users to generate high-fidelity AI avatar videos directly through their agent interface. By leveraging Openclaw Skills, this integration automates the process of connecting to remote GPU clusters to handle complex video compositing, text-to-speech synchronization, and H.264 compression. It is specifically designed for marketers and developers who need to produce spokesperson content without expensive filming equipment or local processing power.
This skill streamlines the production pipeline by managing cloud sessions and rendering jobs. It supports a wide array of file formats including MP4, MOV, JPG, and PNG, allowing for a versatile range of input sources. Whether you are building a product demo or a social media campaign, this tool ensures 1080p output quality with a typical turnaround of just one to two minutes.
HeyGen AI Use Cases
- Creating professional marketing spokesperson videos from text scripts.
- Generating educational and training content using AI presenters and static headshots.
- Automating high-volume video production for social media using Openclaw Skills workflows.
- Rapidly prototyping video ads with text overlays and background music.
How HeyGen AI Works
- The skill initializes by checking for a valid NEMO_TOKEN or generating an anonymous client identifier to establish a cloud session.
- User assets such as scripts, images, or audio files are uploaded to the remote processing backend.
- A Server-Sent Events (SSE) stream is opened to process generation and editing commands in real-time.
- The cloud GPU nodes composite the video tracks, apply AI avatar animations, and handle rendering.
- The skill monitors the render status and provides a direct download link for the final 1080p MP4 file.
HeyGen AI Setup
To get started with this integration in Openclaw Skills, you need to configure your environment. On first run, the skill can automatically Provision an anonymous token if one is not provided.
# Optional: Manually set your token
export NEMO_TOKEN="your_nemo_api_token"
# The skill will automatically interact with the backend:
# API Base: https://mega-api-prod.nemovideo.ai
HeyGen AI Data Schema & Taxonomy
The skill organizes video project data using a structured draft JSON schema to track timeline segments and assets.
| Key | Definition | Description |
|---|---|---|
| t | Tracks | A list of all video, audio, and text layers in the project. |
| tt | Track Type | Identifies layer type: 0 for video, 1 for audio, 7 for text. |
| sg | Segments | The specific media clips placed within a track. |
| d | Duration | The length of a segment measured in milliseconds. |
| m | Metadata | Technical specifications for asset rendering and positioning. |
HeyGen AI Advanced Features
- Iterative editing support where the session maintains the timeline state for continuous refining.
- Intelligent mapping of visual GUI instructions (like drag-and-drop) into programmatic API edits.
- Robust error handling for credit management and token expiration within the Openclaw Skills framework.
- Automated status polling for long-running GPU render tasks with user-friendly heartbeat updates.
- Support for batch processing multiple files within a single project session.
SKILL.md
Loading
Related Openclaw Skills
Photo Video Maker Fast
Transform your image collections into polished 1080p videos in under a minute using cloud-accelerated AI.
Video Generation AI Tools
An AI-powered skill for generating professional 1080p videos from text descriptions and image assets using cloud-based GPU rendering.
Video Editing with Arabic — Add Arabic Subtitles to Videos
An AI-powered video localization tool for Openclaw Skills that automates the generation and synchronization of Arabic subtitles.
Cornell Method Notes
A professional note-taking skill that enables AI agents to manage structured Cornell Method documentation using Markdown files.
Steve Jobs Perspective
A strategic advisor skill that applies Steve Jobs' core decision-making lenses to product design, focus, and end-to-end user experiences.
Universal Video Analyzer (Chinese)
A multimodal tool that analyzes video frames and audio to generate comprehensive, structured Chinese reports.
Featured*
