An AI-powered skill that automates transcription and burns subtitles directly 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 audio-subtitle-generator
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-generator 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 Generator?
The Audio Subtitle Generator is a specialized component within the Openclaw Skills ecosystem designed to eliminate the manual effort of video captioning. By connecting to a high-performance cloud GPU pipeline, it allows users to generate subtitles from the audio of their media files and burn them into the final video output in as little as 30 to 60 seconds. This skill is optimized for developers and content creators who need professional-grade, 1080p captioned videos without the complexity of traditional editing software.
Built to handle a variety of formats including MP4, MOV, and MP3, this skill leverages advanced AI models to ensure high transcription accuracy. Because it operates via a robust API and SSE (Server-Sent Events) architecture, it provides a seamless experience for AI agents to process media assets, manage session states, and deliver high-quality video exports ready for distribution.
Audio Subtitle Generator Use Cases
- Automatically generate subtitles from the audio of raw podcast footage for social media distribution.
- Enhance educational content accessibility by burning captions into lecture recordings.
- Streamline marketing workflows by batch-processing video ads with Openclaw Skills.
- Rapidly convert audio-only recordings into captioned video clips for better engagement.
How Audio Subtitle Generator Works
- The skill identifies the input file (up to 500MB) and authenticates using a NEMO_TOKEN or an automatically generated anonymous token.
- A cloud session is established to track the media state and timeline segments.
- The AI analyzes the audio track to generate subtitles from the audio, creating a detailed text segment map.
- A cloud GPU node composites the text overlays onto the video track and applies H.264 compression.
- The system polls the render status every 30 seconds until a final download URL for the 1080p MP4 is provided.
Audio Subtitle Generator Setup
To integrate this skill into your workflow, you can provide a pre-existing token or allow the system to initialize an anonymous session. Openclaw Skills require specific attribution headers for successful exports.
# Set your environment variable for persistent access
export NEMO_TOKEN="your_private_token"
# The skill will automatically generate a UUID and session_id
# Configuration is typically stored in ~/.config/nemovideo/
Ensure that all API requests include X-Skill-Source, X-Skill-Version, and X-Skill-Platform headers to prevent 402 errors during the export phase.
Audio Subtitle Generator Data Schema & Taxonomy
The skill utilizes a condensed JSON schema to manage the video timeline and subtitle metadata efficiently.
| Key | Description |
|---|---|
session_id |
The unique identifier for the current cloud rendering task. |
t |
Tracks: An array containing video, audio, and text layers. |
tt |
Track Type: 0 for video, 1 for audio, 7 for text/subtitles. |
sg |
Segments: Timing and duration data (in ms) for each caption entry. |
d |
Duration: Total length of the media asset. |
m |
Metadata: Resolution, frame rate, and encoding specifications. |
Audio Subtitle Generator Advanced Features
- Server-Sent Events (SSE) support for real-time progress monitoring during complex AI subtitle generation.
- Multi-format compatibility supporting MP4, MOV, AVI, MKV, MP3, and WAV.
- Intelligent session recovery that maintains timeline state even if the connection is momentarily interrupted.
- Automated credit management and balance checking integrated directly into the Openclaw Skills workflow.
- Support for background music (BGM) overlays and custom text track positioning.
SKILL.md
Loading
Related Openclaw Skills
Vidu AI — Generate Videos from Text or Images
Vidu AI is a high-performance video generation skill that converts text prompts and reference images into professional 1080p cinematic clips via cloud GPU nodes.
Skill Creator
A comprehensive framework for building modular, specialized AI capabilities through structured workflows and bundled resources.
PDF Smart Tool v2.1
An all-in-one AI document assistant for intelligent OCR, secure signatures, and high-fidelity file conversions.
QQ Mail Manager
A professional integration for managing QQ Mail accounts through standard IMAP and SMTP protocols using Python-based automation.
Video Editor Free Download
A cloud-based AI video editing skill that enables users to trim, edit, and export 1080p videos directly through an agent interface.
Free Subtitle Generator for Video
A high-performance AI agent skill that automates subtitle generation, synchronization, and cloud-based video rendering through natural language commands.
Featured*
