A high-performance AI video editing skill that generates multi-language subtitles and burns them into 1080p MP4 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 video-caption-maker
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-caption-maker 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 Caption Maker?
Video Caption Maker is a powerful technical integration designed for creators who need rapid, automated subtitling solutions. As part of the Openclaw Skills ecosystem, it leverages a cloud-based GPU pipeline to process video files up to 500MB, delivering professional-grade results in just 30-60 seconds.
This skill eliminates the manual labor of transcription by offering automatic sync for multiple languages, including English and Spanish. By connecting directly to the NemoVideo API, it allows users to upload raw footage and receive a polished, 1080p MP4 file ready for distribution on social media or YouTube.
Video Caption Maker Use Cases
- Automating subtitles for YouTube tutorials and social media clips.
- Creating multi-language video content with English and Spanish captions.
- Burning in text overlays and titles for quick video announcements.
- Batch processing multiple video files within a single project session.
- Rapidly converting MOV or WebM files into captioned 1080p MP4s.
How Video Caption Maker Works
- The user provides a video file via upload or URL to initialize the project.
- The skill authenticates with the NemoVideo API using a NEMO_TOKEN to establish a secure session.
- User instructions (e.g., 'add captions') are sent via a Server-Sent Events (SSE) stream for real-time AI processing.
- A cloud GPU node composites the video layers, synchronizes audio with text, and applies H.264 compression.
- The skill polls the rendering proxy until the status is completed and provides a direct download URL for the final MP4.
Video Caption Maker Setup
To start using this member of the Openclaw Skills library, ensure your environment is configured properly:
# Set your NemoVideo API token
export NEMO_TOKEN="your_token_here"
# The skill will automatically generate a session
# and connect to https://mega-api-prod.nemovideo.ai
If you do not have a token, the skill will generate an anonymous UUID-based token with 100 credits and a 7-day expiry on your first interaction.
Video Caption Maker Data Schema & Taxonomy
The skill organizes video data through a structured session state and timeline draft system:
| Field | Description |
|---|---|
tracks (t) |
Array of media layers in the project |
track type (tt) |
0: Video, 1: Audio, 7: Text/Captions |
segments (sg) |
Individual clips or text blocks within a track |
duration (d) |
Length of the segment in milliseconds |
metadata (m) |
Technical properties of the media assets |
All exported files are standardized to 1080p MP4 (H.264) for maximum compatibility.
Video Caption Maker Advanced Features
- Multi-language auto-sync support for complex captioning requirements.
- Real-time SSE stream monitoring with automated heartbeat 'Still working' status updates.
- Session persistence allowing for iterative editing without re-uploading assets.
- Automatic attribution header injection (X-Skill-Source, X-Skill-Version) for API compliance.
- Intelligent mapping of GUI instructions (click, drag, drop) into executable API actions.
SKILL.md
Loading
Related Openclaw Skills
Editor Background Changer
A cloud-powered AI skill that replaces video backgrounds instantly using simple natural language descriptions.
Brand Voice Copy Kit
A lightweight voice system that translates brand traits into actionable copy pillars, vocabulary banks, and channel-specific adaptation rules.
Influencer Brief Builder
A specialized tool for generating comprehensive, brand-safe collaboration briefs for influencers on TikTok, Instagram, YouTube, Xiaohongshu, and Douyin.
FAQ Objection Crusher
A strategic content tool that transforms customer objections into honest, policy-backed FAQ sections and trust-building sales snippets.
En Español Editor
A professional AI video editor that automatically generates and burns Spanish subtitles into your video clips using a cloud-based GPU rendering pipeline.
Marketplace Description Writer
A professional-grade AI tool for generating structured, shopper-friendly product descriptions across major ecommerce platforms and independent stores.
Featured*
