An AI-powered video editing skill that enables users to edit MP4, MOV, and AVI files simply by typing instructions like cutting pauses or adding captions.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install text-to-video-editing
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 text-to-video-editing 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 Text to Video Editing?
This skill leverages a cloud-based rendering pipeline to provide a text-driven editing interface for AI agents. Instead of manually using a timeline editor, users can describe complex edits such as adding title cards, removing silence, or generating captions. The backend handles the heavy lifting on GPU nodes, returning 1080p MP4 files in minutes, making it an essential addition for those utilizing Openclaw Skills for content creation.
The system handles the translation of high-level natural language into specific timeline operations, managing tracks for video, audio, and text overlays automatically. By integrating this capability, developers can build workflows that move from raw footage to finished media without ever opening a traditional NLE like Premiere Pro or Final Cut.
Text to Video Editing Use Cases
- Rapidly editing screen recordings into professional 1080p MP4 clips for tutorials.
- Automating the removal of pauses and silence in raw footage for social media content.
- Adding synchronized captions and title cards through simple text commands to improve accessibility.
- Batch processing multiple media files within a single session for consistent styling across a series of videos.
How Text to Video Editing Works
- Establish a secure connection to the backend API using an environment-based NEMO_TOKEN or an anonymous session token.
- Create a project session to maintain the state of the video timeline and track metadata across multiple interactions.
- Upload media files up to 500MB directly to the cloud rendering pipeline for processing.
- Send text-based editing instructions via an SSE (Server-Sent Events) stream for real-time AI processing and intent classification.
- Monitor the draft state and timeline changes using the State API to ensure instructions are accurately applied to the project.
- Execute the export command to trigger a cloud GPU render and retrieve the final 1080p MP4 download URL.
Text to Video Editing Setup
To get started with this skill in the Openclaw Skills ecosystem, ensure your environment is configured for authentication:
# Export your API token to the environment to bypass anonymous limits
export NEMO_TOKEN="your_nemo_token_here"
# The skill can also auto-acquire a free starter token
# valid for 7 days if no environment variable is provided.
Text to Video Editing Data Schema & Taxonomy
The skill uses a structured draft mapping to manage the video timeline and media metadata efficiently:
| Key | Name | Description |
|---|---|---|
t |
Tracks | Array of media layers (video, audio, text) |
tt |
Track Type | 0: Video, 1: Audio, 7: Text |
sg |
Segments | Defined time slices of media used in the edit |
d |
Duration | Length of a specific segment in milliseconds |
m |
Metadata | Media information, codec details, and source URLs |
Text to Video Editing Advanced Features
- Supports complex multi-track compositions including background music (BGM) ducking and dynamic text overlays.
- Real-time status polling via the State API to handle asynchronous edits without a traditional GUI.
- High-performance cloud GPU rendering with H.264 compression for maximum cross-platform playback compatibility.
- Automatic error recovery and re-authentication for long-running Openclaw Skills sessions to ensure render completion.
SKILL.md
Loading
Related Openclaw Skills
AutoTalk
AutoTalk is a specialized conversion engine that transforms dry professional analysis into high-impact spoken scripts for social media.
Scrape
A professional-grade scraping skill designed for legal, compliant, and ethical data extraction using direct HTTP or the SkillBoss API Hub.
Video Summarizer
A multi-platform video transcript extraction and AI summarization tool supporting YouTube and Bilibili with local whisper transcription and visual frame analysis.
Free Video Hook Generator
A cloud-powered AI tool that generates attention-grabbing video hooks and renders them into high-quality MP4 files in seconds.
Exa Neural Search
A high-performance neural search skill for AI agents to perform web searches and deep content extraction via the SkillBoss API Hub.
Notify - Smart Notification Delivery
A sophisticated communication layer for AI agents that manages channel selection, timing, and intelligent batching to prevent notification spam.
Featured*
