Veo Video Generator for Openclaw

A professional-grade AI skill for generating cinematic 1080p videos with synchronized audio using Google Veo 3.1 technology.

kghamilton89
v1.2.2
Feb 26, 2026
2
1.2k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install veo-video-generator

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install veo-video-generator 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 Veo Video Generator?

The Veo Video Generator is a powerful addition to the library of Openclaw Skills, specifically designed to enable AI agents to create high-quality video content from text descriptions. By utilizing Google's advanced Veo 3.1 model, this skill transforms simple prompts into high-fidelity 1080p video clips, complete with native, synchronized audio. It is engineered for developers and creators who need a reliable, programmatic way to render cinematic assets within an agent-driven environment.

This skill prioritizes both performance and security, offering a streamlined workflow for media creation. Unlike basic generation tools, it is optimized for modern display standards and integrates smoothly into automated pipelines. As one of the more specialized Openclaw Skills, it provides the technical infrastructure necessary to handle complex GenAI API interactions while maintaining a simple interface for the end user.

Veo Video Generator Use Cases

  • Creating short-form cinematic video content for social media and marketing.
  • Prototyping visual assets for mobile applications using a 9:16 aspect ratio.
  • Automating the generation of high-fidelity video b-roll from text scripts.
  • Integrating AI-driven video synthesis into multi-agent creative workflows.

How Veo Video Generator Works

  1. The AI agent identifies a video generation request and initializes the Veo Video Generator skill.
  2. The skill verifies the environment configuration, ensuring the GEMINI_API_KEY is available for API authentication.
  3. The agent executes the underlying Node.js script, passing the user's text prompt as a discrete argument to ensure secure processing.
  4. The script communicates with Google's GenAI API to process the prompt and synthesize a 1080p video with synced audio.
  5. Upon completion, a .mp4 file is saved to the local workspace, and the agent provides the filename to the user for immediate review.

Veo Video Generator Setup

To begin using this skill within the collection of Openclaw Skills, ensure that you have Node.js and npm installed. You must also have a valid Google Gemini API key set in your environment. Run the following command to install the necessary dependencies:

npm install

Ensure that your GEMINI_API_KEY is exported to your shell or provided via your agent's environment configuration.

Veo Video Generator Data Schema & Taxonomy

The skill manages video generation data and metadata through the following structure:

Attribute Specification Detail
Resolution 1080p High-definition output
Aspect Ratio 9:16 Optimized for portrait viewing
Format .mp4 Standard video container with audio
Dependencies node, npm Required execution environment
Auth GEMINI_API_KEY Primary API authentication key

Veo Video Generator Advanced Features

  • Advanced shell injection prevention using discrete argument array invocation for prompt handling.
  • Integrated audio synchronization that matches the visual pacing of the generated video.
  • High-fidelity 1080p rendering capability using the latest Google Veo 3.1 model.
  • Seamless compatibility with other Openclaw Skills for complex media automation and research tasks.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*