An AI-powered video processing skill that automates subtitle generation and burns them into 1080p MP4 files using cloud GPU acceleration.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install audio-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 audio-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 Audio Subtitle?
The Audio Subtitle skill is a specialized tool within the Openclaw Skills ecosystem designed to simplify the video editing and transcription workflow. It allows developers and content creators to transform raw video files into professional, subtitled content without requiring local hardware resources. By offloading processing to cloud GPUs, the skill handles complex tasks like audio analysis, text synchronization, and video compositing in under 90 seconds.
This skill is particularly effective for those who need high-quality output in a 1080p MP4 format. It manages the entire lifecycle of a video project, from initial upload to final export, using a session-based architecture that maintains project state even during iterative editing phases. For users of Openclaw Skills, it provides a robust interface for programmatic video manipulation through simple natural language commands or API calls.
Audio Subtitle Use Cases
- Automatically generate subtitles from the audio for social media clips and interviews.
- Produce 1080p MP4 videos with burned-in captions for educational and marketing purposes.
- Batch process multiple video files within a single session for consistent subtitle styling.
- Convert various video formats like MOV or WebM into subtitled MP4 files optimized for sharing.
How Audio Subtitle Works
- The user provides a video file (up to 500MB) or a URL to the Openclaw Skills interface.
- The skill initializes a project session and authenticates with the cloud backend using a NEMO_TOKEN.
- Audio tracks are extracted and processed through an AI-driven transcription engine to create subtitle segments.
- A cloud GPU node composites the subtitle layers onto the video tracks based on the session's timeline state.
- The system triggers a render job that compresses the video into a 1080p H.264 MP4 file.
- The user receives a secure download URL once the export status is marked as completed.
Audio Subtitle Setup
To get started with this skill in Openclaw Skills, you must ensure your environment is configured to communicate with the cloud API. The skill will automatically attempt to provision an anonymous token if one is not found.
# Set your environment variable manually if you have a custom token
export NEMO_TOKEN="your_nemo_token_here"
# Configuration paths are typically stored in:
~/.config/nemovideo/
The skill identifies itself during API calls using the X-Skill-Source header to ensure proper attribution and session management.
Audio Subtitle Data Schema & Taxonomy
The skill organizes video projects using a structured timeline draft. This schema uses short keys to minimize payload size during SSE (Server-Sent Events) transmissions.
| Key | Definition | Values |
|---|---|---|
| t | Tracks | Array of media layers |
| tt | Track Type | 0: Video, 1: Audio, 7: Text |
| sg | Segments | List of timing data for each track |
| d | Duration | Length of segment in milliseconds |
| m | Metadata | Resolution, codec, and file information |
All exported files are standardized to MP4 containers using H.264 encoding at 1080p resolution.
Audio Subtitle Advanced Features
- Real-time processing updates via SSE (Server-Sent Events) stream monitoring.
- Automated credit and token management with re-authentication logic.
- Support for multi-track timeline summaries for complex video projects.
- Intelligent mapping of GUI-style instructions (like click or drag) to programmatic API actions.
- Multi-format support covering MP4, MOV, AVI, WebM, and various audio containers.
SKILL.md
Loading
Related Openclaw Skills
Subtitle to Video
A high-performance cloud-based skill for burning hard-coded subtitles and text overlays directly into video files using remote GPU acceleration.
Editor Change
Automate professional video re-editing and style switching through simple natural language commands.
Editor on Android — Edit and Export Videos Mobile
A high-performance AI video editing tool for Android users to trim, transition, and export 1080p clips via remote GPU nodes.
Content Trend Analyzer
A comprehensive multi-platform trend aggregation tool that transforms raw search and social data into actionable content strategies and structured article outlines.
Video Music Generator
An AI-powered skill that automatically generates mood-matched background music for video clips using cloud GPU rendering.
stream-ai-answer
A universal streaming AI retrieval-augmented generation (RAG) skill providing a four-step visual analysis interface for professional industry applications.
Featured*
