An AI-powered video intelligence tool that uses Google's Gemini model to analyze footage and generate scripts, summaries, or highlights through natural language.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-ai-video-generator
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 gemini-ai-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 Gemini AI Video Generator?
The Gemini AI Video Generator skill brings the power of Google's multimodal Gemini model directly into your AI agent's workflow. As a premier entry in the Openclaw Skills ecosystem, it allows users to interact with video files using plain-language instructions rather than complex timeline editing. By analyzing both visual cues and audio tracks, the skill can understand context, identify key moments, and generate creative outputs like narration scripts, highlight reels, and structured summaries. It is designed to bridge the gap between raw footage and polished content for creators, educators, and developers.
Built on the robust NemoVideo backend, this skill handles the heavy lifting of video processing and model orchestration. Whether you are looking to repurpose long-form content or automate the creation of metadata, this tool provides a developer-friendly interface to high-end video AI. It is a vital part of any toolkit focused on Openclaw Skills for media automation.
Gemini AI Video Generator Use Cases
- Creating 60-second highlight reels from long-form product demos or event recordings.
- Generating structured lecture summaries with precise timestamps for educational content.
- Drafting professional narration scripts based on visual b-roll footage analysis.
- Producing caption tracks and social media descriptions tailored to the specific tone of a video.
How Gemini AI Video Generator Works
- The skill initializes a connection to the NemoVideo backend, checking for a NEMO_TOKEN or generating an anonymous client ID for authentication.
- A project session is created to maintain context for the specific video task and manage credit usage.
- Users upload video files (MP4, MOV, etc.) which are then indexed by the backend for analysis.
- Natural language prompts are enriched with cinematic parameters and sent to the Gemini AI via a Server-Sent Events (SSE) stream.
- Gemini analyzes the visual and audio data to generate the requested output, such as text-based summaries or timeline modifications.
- The final project can be exported via a dedicated render proxy to produce a high-quality video file.
Gemini AI Video Generator Setup
To integrate this skill from the Openclaw Skills library, follow these configuration steps:
- Ensure you have a valid client identifier or set the
NEMO_TOKENenvironment variable. - The skill will automatically attempt to locate a configuration at
~/.config/nemovideo/client_id. - To manually set up the environment, you can use the following commands:
# Create config directory
mkdir -p ~/.config/nemovideo/
# Skill will generate a UUID if one doesn't exist
- Authentication is handled automatically via a POST request to the NemoVideo anonymous-token endpoint if a primary token is not found.
Gemini AI Video Generator Data Schema & Taxonomy
The Gemini AI Video Generator organizes data through a session-based state mapping that includes:
| Field | Description |
|---|---|
draft |
The core project structure containing tracks (t) and segments (sg). |
video_infos |
Technical metadata for all uploaded media files. |
generated_media |
Tracks all AI-generated assets linked to the session. |
track_type |
Categorized as 0 (Video), 1 (Audio), or 7 (Text/Titles). |
All data is processed using the NemoVideo API base at https://mega-api-prod.nemovideo.ai.
Gemini AI Video Generator Advanced Features
- Multimodal processing that synchronizes visual analysis with spoken audio and on-screen text.
- Real-time feedback via SSE streams, allowing for interactive generation and editing.
- Seamless workspace claiming, allowing users to move from the AI agent to the NemoVideo web GUI with a single token.
- Automated render polling that manages complex export tasks in the background.
- Comprehensive error handling for credit management and rate-limiting within the Openclaw Skills framework.
SKILL.md
Loading
Related Openclaw Skills
Smart Auto Note
A semantic AI skill that intelligently categorizes and writes user input into specific Obsidian notes with automatic task archiving.
Sora AI Video Generator
An advanced AI-powered skill that transforms plain text descriptions into polished, high-quality cinematic video clips across multiple formats.
S2 Universal Space Parser
A high-performance spatial intelligence engine that parses physical environments into actionable hardware matrices for AI agents.
oVirt MCP Server
A comprehensive MCP server providing 186 tools to manage oVirt and RHV virtualization infrastructure directly through AI agents.
Story to Prompts
A sophisticated AI skill that converts story synopses into professional-grade, consistent text-to-image prompts with multi-scene storyboarding.
Subtitle Maker
Subtitle Maker is an AI-powered automation tool that transcribes, translates, and synchronizes video captions in over 50 languages with frame-accurate precision.
Featured*
