An AI-powered video generation skill that leverages Google's Veo 3.1 models to create high-quality 1080p content with sound.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install veo-skill
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 veo-skill 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 Skill?
The Veo Skill integrates Google's advanced video generation capabilities into the Openclaw Skills ecosystem. By utilizing the Monet AI platform, it provides access to the Veo 3.1 and Veo 3.1 Fast models, enabling agents to produce cinematic, high-definition videos from text prompts and reference images.
This skill is designed for developers who need to incorporate professional-grade video production into their automated workflows. Whether you require the high-fidelity audio-visual output of Veo 3.1 or the rapid iteration of the fast model, this skill delivers versatile creative tools through a unified API, ensuring high performance for modern Openclaw Skills applications.
Veo Skill Use Cases
- Creating professional 1080p HD video content for social media platforms like YouTube and TikTok.
- Generating synchronized audio-visual content with intelligent sound generation for digital marketing.
- Using reference images to guide video style and visual consistency in creative projects.
- Rapid prototyping of video concepts using the ultra-fast generation model.
- Automating complex video creation tasks within an AI agent workflow using Openclaw Skills.
How Veo Skill Works
- The skill initiates a video generation task by sending a POST request to the Monet AI API with parameters like model type, prompt, and aspect ratio.
- A required idempotency key is provided to ensure duplicate tasks are not created during network retries within the Openclaw Skills environment.
- The task is processed either asynchronously or via SSE streaming for real-time progress updates.
- For asynchronous tasks, the skill logic polls the status endpoint at recommended 5-second intervals until the status reaches success.
- Upon completion, the skill retrieves a secure URL pointing to the generated 1080p video file.
Veo Skill Setup
To use this skill within the Openclaw Skills framework, you must obtain an API key from the Monet AI platform:
- Register an account at monet.vision.
- Create an API Key at the skills/keys dashboard.
- Configure your environment variable:
export MONET_API_KEY="your_monet_api_key_here"
Veo Skill Data Schema & Taxonomy
The Veo Skill manages task-based data and temporary file storage. Below is the structure for task responses and metadata handling:
| Attribute | Description |
|---|---|
id |
Unique task identifier for tracking |
status |
Current state: pending, success, or failed |
outputs |
Array containing model info, progress, and the public video URL |
idempotency_key |
Required string (UUID) to prevent duplicate requests |
Note on File Storage: Any files uploaded to the system for use as reference images are stored for 24 hours and automatically deleted thereafter.
Veo Skill Advanced Features
- Intelligent Audio Generation: Automatically generates context-aware sound for videos using the Veo 3.1 model.
- Reference Image Guidance: Supports using external image URLs to define style, characters, or composition.
- Multiple Aspect Ratios: Native support for 1:1 (Square), 16:9 (Widescreen), and 9:16 (Vertical) formats.
- SSE Streaming Support: Allows for real-time progress monitoring through Server-Sent Events for interactive Openclaw Skills interfaces.
- Fast Iteration Model: Access to veo-3-1-fast for lower latency generation during testing and development.
SKILL.md
Loading
Related Openclaw Skills
Nano Banana Skill
A professional-grade Google AI image generation skill for Openclaw Skills that enables high character consistency and ultra-wide aspect ratios.
Monet AI Content Generation Skill
A comprehensive multimedia generation skill providing unified access to state-of-the-art AI models for video, image, and music creation.
WhatsApp Image Send
A specialized skill for automating the delivery of images, videos, and documents to WhatsApp contacts through a structured workspace workflow.
Blender Plugin Development
Develop and migrate forward-compatible Blender 4.x and 5.x add-ons with automated scaffolding and API shims using Openclaw Skills.
Presage
An AI-powered market analysis skill for tracking and analyzing Solana-based prediction markets with regulated data.
TixFlow
TixFlow is an AI event assistant that automates the discovery, booking, and calendar coordination of event tickets using KYD Labs and Google Calendar.
Featured*
