A command-based video editing tool that transforms raw footage into polished 1080p MP4 clips through simple natural language instructions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-video-editor-by-text
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 ai-video-editor-by-text 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 AI Video Editor by Text?
The AI Video Editor by Text is a specialized tool within the Openclaw Skills ecosystem designed to eliminate the complexity of traditional video editing. Instead of manual timeline manipulation, users provide natural language instructions—such as "cut the pauses" or "add a title"—to a cloud-based rendering pipeline. This skill bridges the gap between raw footage and social-ready content, processing edits in 30-60 seconds for most short clips.
Built on a robust cloud rendering backend, this skill handles everything from track management and text overlays to audio mixing. It allows developers and creators to automate video production workflows directly from their coding environment or agent interface, ensuring high-quality 1080p output without needing professional editing software knowledge.
AI Video Editor by Text Use Cases
- Rapidly trimming interviews and removing silences using simple text commands.
- Generating social media clips from long-form raw footage with specific aspect ratios.
- Automating the addition of title cards, background music, and fade effects across multiple assets.
- Batch processing video files within a single session using Openclaw Skills workflows.
- Iterative video refining where users tweak timeline states through conversation rather than a mouse.
How AI Video Editor by Text Works
- The skill initializes by checking for a NEMO_TOKEN environment variable or automatically generating an anonymous session token.
- A project session is established to track the state of the video timeline, assets, and rendering job IDs.
- The user uploads raw media (up to 500MB) directly to the cloud processing pipeline.
- Natural language instructions are processed via a Server-Sent Events (SSE) stream for real-time interaction.
- The backend updates an internal draft JSON structure that organizes video, audio, and text tracks based on the prompt.
- Upon receiving an export command, a cloud GPU node renders the final 1080p MP4 and returns a secure download link.
AI Video Editor by Text Setup
To integrate this capability into your Openclaw Skills environment, you need to configure the authentication token.
# Set your environment variable for persistent access
export NEMO_TOKEN="your_token_here"
# The skill can also auto-generate a temporary token if the variable is missing
# Configuration and session data are stored in ~/.config/nemovideo/
AI Video Editor by Text Data Schema & Taxonomy
The skill manages a structured JSON timeline state that maps commands to visual elements using a compressed schema:
| Key | Property | Description |
|---|---|---|
t |
Tracks | An array containing all media layers |
tt |
Track Type | Type identifier (0: Video, 1: Audio, 7: Text) |
sg |
Segments | Individual clip data within a specific track |
d |
Duration | Length of the segment in milliseconds |
m |
Metadata | Information regarding file source and render quality |
All processed files are outputted as 1080p MP4 using H.264 compression for maximum compatibility.
AI Video Editor by Text Advanced Features
- Intelligent Timeline Mapping: Translates abstract GUI instructions like "drag" or "click" into precise timeline API calls.
- State Persistence: Sessions maintain the current draft state, allowing for complex, multi-turn editing workflows.
- Real-time SSE Feedback: Provides a live stream of processing events, including heartbeats to confirm backend activity during heavy renders.
- Multi-Track Compositing: Supports simultaneous management of video layers, background music (BGM), and synchronized text overlays.
- Automated Attribution: Includes built-in skill versioning and platform detection for seamless integration within Openclaw Skills environments.
SKILL.md
Loading
Related Openclaw Skills
text-to-video-kiss
An AI-powered video generation skill that transforms text descriptions into high-quality romantic kiss scenes without manual editing.
AI Video Editor Mobile
Perform professional-grade AI mobile video editing using natural language descriptions and a powerful cloud rendering pipeline.
Caption Generator Meme
A professional AI-powered tool designed to generate and overlay humorous captions onto video clips and images for social media content.
What Is AI Video — Generate and Export AI Videos
An AI-powered video automation tool that converts raw screen recordings and clips into polished 1080p MP4 videos using natural language commands.
AI Video Maker Sora
A cloud-based AI video generation tool that transforms text prompts and documents into professional 1080p MP4 videos without manual editing.
Agent Journal
A persistent cross-session journaling system for AI agents powered by BlueColumn semantic memory to store and recall observations, decisions, and user preferences.
Featured*
