A powerful AI video generation tool leveraging Google Veo models via the inference.sh CLI for high-quality, cinematic output.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install google-veo
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 google-veo 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 Google Veo Video Generation?
The Google Veo skill enables developers to generate high-fidelity videos directly from text prompts using the inference.sh CLI. It supports the latest Google Veo 3.1, Veo 3, and Veo 2 models, offering options for both high-speed generation and maximum quality. This integration allows for seamless inclusion of advanced video AI into automated workflows and developer pipelines using Openclaw Skills.
Whether you need cinematic drone shots, realistic product demos, or complex urban scenes, this skill provides a unified interface to access Google's state-of-the-art video generation technology. By utilizing a simple CLI-based approach, it eliminates the complexity of direct API integrations while maintaining granular control over parameters like camera movement, lighting, and style.
Google Veo Video Generation Use Cases
- Creating cinematic B-roll for video production or social media content.
- Developing realistic product visualizations and rotating demos for e-commerce.
- Generating nature timelapses and atmospheric background visuals for websites.
- Rapid prototyping of visual concepts for film, gaming, or marketing campaigns using Openclaw Skills.
- Automating video content pipelines for multi-platform media delivery.
How Google Veo Video Generation Works
- Authenticate with the inference.sh platform using the CLI login command.
- Select the desired Google Veo model version, such as Veo 3.1 Fast for speed or Veo 3.1 for maximum quality.
- Define video parameters including prompts, camera angles, and lighting within a JSON input structure.
- Execute the generation command through the Openclaw Skills interface to trigger the inference.sh backend.
- Receive the generated video output for use in your application or project.
Google Veo Video Generation Setup
To get started with this skill on Openclaw Skills, install the inference.sh CLI and authenticate:
curl -fsSL https://cli.inference.sh | sh && infsh login
Once logged in, you can run a video generation task immediately using the following command:
infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot over a mountain lake"}'
Google Veo Video Generation Data Schema & Taxonomy
The skill utilizes JSON-based input schemas to define video generation parameters. You can inspect the required structure by generating a sample file.
| Parameter | Description | Type |
|---|---|---|
| prompt | The descriptive text for the video generation | String |
| model | The specific App ID (e.g., google/veo-3-1-fast) | String |
| input.json | A file-based input for complex configurations | JSON File |
Example workflows often involve generating a sample input schema first via infsh app sample google/veo-3-1-fast --save input.json to ensure all metadata fields are correctly populated.
Google Veo Video Generation Advanced Features
- Support for multiple Google Veo generations including 3.1, 3, and 2.
- Specialized "Fast" model variants designed for lower-latency iterations.
- Advanced prompt engineering support for camera movements like dolly, pan, and tracking shots.
- Integration with Openclaw Skills to build automated media generation pipelines.
- Real-time progress updates and streaming results for long-running video rendering tasks.
SKILL.md
Loading
Related Openclaw Skills
FLUX Image Generation
A specialized skill for generating high-quality images using FLUX models by Black Forest Labs via a streamlined CLI interface.
Explainer Video Guide
A comprehensive technical framework for producing professional AI-generated explainer videos from script to final cut using CLI automation.
Email Design
Generate high-converting marketing and transactional email designs using AI-powered visuals and industry-standard layout patterns.
Dialogue Audio Generation with Dia TTS
Generate realistic, multi-speaker dialogue audio using advanced speaker tags and emotional cues for professional productions.
Image to Video Conversion
A high-performance guide and toolset for converting static images into dynamic, cinematic videos using state-of-the-art AI motion models.
Image Upscaling
A comprehensive AI toolkit for upscaling, restoring, and increasing image resolution via high-performance inference models.
METADATA
Featured*
