An AI-powered skill that automatically generates and embeds multi-language captions into video files using cloud GPU rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-auto-caption
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-auto-caption 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 Auto Caption?
AI Auto Caption is a robust Openclaw Skills integration designed for content creators and developers who need fast, accurate subtitle generation. By leveraging remote cloud GPU nodes, this skill processes video files like MP4, MOV, and WebM up to 500MB, delivering polished 1080p outputs without taxing local hardware.
The skill simplifies the post-production workflow by handling the heavy lifting of speech-to-text and visual synchronization server-side. Whether you are building for a global audience or improving accessibility, this tool ensures your content is ready for distribution across all major platforms with minimal manual effort.
AI Auto Caption Use Cases
- Automatically adding English and Spanish subtitles to YouTube tutorials.
- Generating captions for social media clips in MP4 or MOV formats to increase engagement.
- Batch processing multiple video files for consistent branding and accessibility across a channel.
- Translating video dialogue for international audiences using AI subtitle generation within Openclaw Skills.
How AI Auto Caption Works
- Initialize a connection by checking for an existing NEMO_TOKEN or generating a new anonymous token for authentication.
- Create a unique session to manage the video editing environment, tracks, and timeline state.
- Upload the target video file or provide a URL to the cloud-based processing backend.
- Send specific captioning and editing instructions through an SSE stream for real-time AI processing.
- Monitor the cloud GPU render queue until the finalized 1080p MP4 file is available for export and download.
AI Auto Caption Setup
To use this within the Openclaw Skills framework, you need to configure your authentication token. You can set it manually or let the skill handle anonymous registration.
# Set your environment variable for persistent access
export NEMO_TOKEN="your_acquired_token"
The skill automatically checks for this token in your environment or configuration paths like ~/.config/nemovideo/. If no token is found, it will automatically provision a temporary token with 100 free credits for immediate use.
AI Auto Caption Data Schema & Taxonomy
The skill organizes its internal timeline using a specific JSON draft schema to track media layers and timing.
| Key | Name | Definition |
|---|---|---|
| t | Tracks | An array of all media layers in the current session |
| tt | Track Type | The category of track: 0 (Video), 1 (Audio), 7 (Text/Captions) |
| sg | Segments | Objects defining the start and end timestamps for media clips |
| d | Duration | The total length of the segment or track in milliseconds |
| m | Metadata | Technical details about the source media assets |
AI Auto Caption Advanced Features
- Multi-language captioning support allowing for simultaneous subtitle tracks in different languages.
- Persistent session management that allows for iterative editing without re-uploading original assets.
- High-performance H.264 cloud rendering optimized for 1080p resolution and platform-specific compression.
- Seamless integration with the broader Openclaw Skills ecosystem for automated video production pipelines.
- Intelligent error handling that automatically manages rate limits and token expiration.
SKILL.md
Loading
Related Openclaw Skills
AI Screen Record
An AI-powered video editing skill that automates the process of cleaning up, enhancing, and exporting professional screen recordings.
Screen Recording Free - AI Video Editor
A cloud-based AI tool designed to edit and clean up free screen recordings for sharing, specifically optimized for educational content and software tutorials.
Screen Recording Online
An AI-powered video editing skill that automates the process of trimming pauses, adding captions, and exporting polished screen recordings via cloud GPUs.
Screen Record Free
An AI-powered video editing skill that automates trimming, captioning, and cloud-based rendering for professional-grade screen recordings.
Windows-Android SSH Remote Control
A secure framework for establishing encrypted remote desktop connections from Android devices to Windows workstations using SSH tunneling.
Free Video Generator
A cloud-based AI tool for generating high-quality 1080p MP4 videos from images and clips without needing local editing software.
Featured*
