An AI-driven video processing skill that automates transcription and hardcoding subtitles into video files via cloud GPU rendering.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install video-subtitle
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 video-subtitle 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 Video Subtitle AI Agent Skill?
The Video Subtitle skill is a high-performance tool designed for the Openclaw Skills ecosystem, enabling developers and creators to automate the transcription and embedding of captions directly into video files. By leveraging a cloud rendering pipeline, it allows users to add subtitles in English and Spanish to my video projects without manual frame-by-frame editing. This skill bridges the gap between raw footage and production-ready 1080p MP4 files, handling everything from aspect ratio adjustments to text overlays through simple natural language commands.
Video Subtitle AI Agent Skill Use Cases
- Rapid captioning for YouTube tutorials, social media clips, and marketing videos.
- Localizing content by adding multi-language subtitles for global distribution.
- Batch processing multiple video assets within a single AI agent session.
- Automating the final export of videos with specific metadata and hardcoded text overlays.
How Video Subtitle AI Agent Skill Works
- The skill establishes a connection to the rendering backend using a NEMO_TOKEN or a temporary anonymous identifier.
- A project session is initialized to track the editing timeline and media assets.
- User-provided video files (up to 500MB) are uploaded to the cloud rendering pipeline.
- Natural language instructions are processed via Server-Sent Events (SSE) to trigger transcription and subtitle placement.
- A cloud GPU node composites the layers, applies H.264 compression, and generates a downloadable 1080p MP4 file.
Video Subtitle AI Agent Skill Setup
To use this skill within the Openclaw Skills framework, ensure you have your environment variables configured:
# Set your API token for persistent access
export NEMO_TOKEN="your_nemo_video_token"
# The skill will automatically handle anonymous token generation
# if the NEMO_TOKEN is not provided.
Video Subtitle AI Agent Skill Data Schema & Taxonomy
The skill manages video projects using a structured session state. Below is the primary data taxonomy:
| Key | Description | Format |
|---|---|---|
| session_id | Unique identifier for the editing project | UUID String |
| draft | The JSON representation of the video timeline | Object (short keys: t, tt, sg) |
| video_infos | Metadata regarding uploaded assets (duration, codec) | Array |
| render_id | The ID of the current export job in the GPU queue | String |
| output.url | The final destination for the rendered MP4 file | URL |
Video Subtitle AI Agent Skill Advanced Features
- Support for diverse media formats including MP4, WebM, AVI, and MOV.
- Automated translation and multi-language subtitle track generation via cloud AI.
- Intelligent intent classification for commands like export, credits check, and status updates.
- High-speed cloud GPU rendering optimized for short-form content under 5 minutes.
- Seamless integration with other Openclaw Skills for end-to-end automated video marketing pipelines.
SKILL.md
Loading
Related Openclaw Skills
Video Script Yijia
Video Script Yijia automates the creation of professional video scripts and 1080p MP4 renders from simple text briefs or uploaded files.
Video Script Automaton
An AI-powered video script generation tool that transforms topics and text into professional scripts and rendered 1080p MP4 videos via cloud GPUs.
Video Object Ops
A high-performance AI tool for manipulating video objects and exporting professional edits directly via text commands.
Video Making Skill
An AI-powered video production skill that automates trimming, audio layering, and rendering through natural language commands.
Caveman Soul Optimizer
A high-efficiency protocol for OpenClaw agents that compresses internal reasoning to save tokens while preserving agent personality and technical accuracy.
Video To
A high-performance AI video conversion tool that transforms footage into platform-ready formats using simple natural language commands.
Featured*
