An AI-powered video editing skill that automates subtitle generation, translation, and cloud rendering through simple text commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install caption-ai
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 caption-ai 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 Caption AI?
Caption AI is a high-performance video processing tool designed to streamline the creation of social media content and tutorials. By leveraging a cloud rendering pipeline, it allows users to turn raw recordings into polished, captioned 1080p videos without the need for manual timeline editing or complex export configurations.
Built as part of the Openclaw Skills ecosystem, this tool handles everything from AI subtitle generation in multiple languages to aspect ratio adjustments and text overlays. It is particularly effective for creators who need to move from upload to download in under 60 seconds, bypassing traditional heavyweight video editing software.
Caption AI Use Cases
- Automatically adding synchronized captions to YouTube tutorials or social media clips.
- Translating video subtitles into multiple languages such as English and Spanish simultaneously.
- Converting raw video files into platform-ready 1080p MP4 exports via cloud GPU rendering.
- Batch processing multiple video assets within a single session for consistent styling.
- Rapidly adding background music and text overlays to short-form video content.
How Caption AI Works
- Connection: The skill establishes a secure session using a NEMO_TOKEN or acquires a temporary anonymous token for immediate access.
- Upload: Users provide video files via local path or URL, which are then transmitted to the cloud rendering pipeline.
- Intent Processing: Natural language prompts are analyzed to trigger specific actions like 'add captions' or 'change aspect ratio' via an SSE (Server-Sent Events) stream.
- Cloud Synthesis: A remote GPU node composites the video layers, applies AI subtitle generation, and handles compression.
- Export: The system generates a high-quality 1080p MP4 and provides a direct download URL once the render status is complete.
Caption AI Setup
To use this within the Openclaw Skills framework, ensure your environment is configured with the necessary API credentials.
# Set your Nemo Video API token
export NEMO_TOKEN="your_token_here"
# The skill automatically handles session creation
# and anonymous token generation if NEMO_TOKEN is missing.
Caption AI Data Schema & Taxonomy
Caption AI organizes video projects using a session-based state management system. Below is the metadata taxonomy used during the rendering process:
| Component | Key | Description |
|---|---|---|
| Track Type | tt |
0 = Video, 1 = Audio, 7 = Text |
| Timeline | t |
Array of tracks containing media segments |
| Duration | d |
Segment length measured in milliseconds |
| Metadata | m |
Specific attributes for text overlays or video properties |
| Output | format |
Supported formats include MP4, MOV, AVI, and WebM |
Caption AI Advanced Features
- Multi-language AI subtitle generation with automatic timing synchronization.
- Asynchronous cloud rendering that continues processing even if the local session is briefly interrupted.
- Support for iterative editing, allowing users to refine the timeline state across multiple prompts.
- Automated GUI command mapping that translates natural language into complex timeline operations.
- Integrated credit management and session state polling for real-time progress tracking.
SKILL.md
Loading
Related Openclaw Skills
Bilibili AI Subtitle Online
An automated AI subtitle generation tool that converts Bilibili video content into professionally subtitled MP4 files in minutes.
Order & Returns Manager
An end-to-end ecommerce management tool for handling Shopify and WooCommerce orders, returns, and fraud detection via messaging channels.
Video Toolkit
An automated AI video editing suite that converts raw clips into polished 1080p MP4 files using natural language commands and cloud-based GPU rendering.
Best RTK Compressor
A cloud-based AI video compression tool that uses RTK hardware acceleration to optimize high-resolution footage without sacrificing visual quality.
JianYing Editor Skill
A sophisticated Python wrapper for JianYing Pro that enables full automation of video editing workflows, from asset import to final export.
Video Downloader Free
A high-speed video processing skill that converts online URLs into downloadable 1080p MP4 files using remote GPU rendering.
Featured*
