A high-performance skill that converts text prompts and documents into professional 1080p AI-generated videos.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install text-to-ai
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 text-to-ai 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 Text to AI Video?
The text-to-ai skill is a sophisticated integration for Openclaw Skills designed to streamline the video production process. By connecting your AI agent to remote GPU nodes, it allows for the seamless conversion of written scripts, product descriptions, or raw text files into fully rendered 1080p MP4 videos. This skill is particularly valuable for users who need to generate high-quality visual content without the need for local high-end hardware.
Built to handle professional workflows, the skill supports a variety of document formats including TXT, DOCX, and PDF. Whether you are generating a quick social media clip or a detailed promotional video, the text-to-ai extension handles the complex layout, asset composition, and rendering tasks server-side, returning a polished product in just a few minutes.
Text to AI Video Use Cases
- Rapidly creating 30-second promotional videos from product descriptions for digital marketing.
- Converting written scripts into visual storyboards or draft videos for content creators.
- Automating video generation from blog posts or articles using Openclaw Skills.
- Adding background music and text overlays to raw scripts via simple natural language commands.
How Text to AI Video Works
- The skill initializes by verifying a NEMO_TOKEN or acquiring an anonymous session token from the backend API.
- The user submits a text prompt or uploads a document (up to 500MB) describing the desired video content.
- The agent sends the request to the cloud render pipeline using Server-Sent Events (SSE) for real-time processing updates.
- Remote GPU nodes composite video layers, audio tracks, and text overlays according to the session state.
- The system polls the render status every 30 seconds until the high-quality 1080p MP4 is ready.
- A final download URL is provided to the user, completing the text-to-video workflow.
Text to AI Video Setup
To get started with this skill within the Openclaw Skills ecosystem, ensure your environment is configured:
# Set your API token (Optional: if not set, a free starter token will be generated)
export NEMO_TOKEN="your_nemo_video_token"
# Ensure the skill is placed in the correct directory
# For Clawhub: ~/.clawhub/skills/text-to-ai
# For Cursor: ~/.cursor/skills/text-to-ai
Text to AI Video Data Schema & Taxonomy
The skill manages video projects through a structured session state. Below is the mapping for the internal draft data used during generation:
| Key | Definition | Description |
|---|---|---|
t |
Tracks | The array of media layers (video, audio, text). |
tt |
Track Type | Type identifier: 0 for Video, 1 for Audio, 7 for Text. |
sg |
Segments | The specific timing and duration blocks for each track. |
d |
Duration | The total length of the segment in milliseconds. |
m |
Metadata | Additional file information and asset properties. |
Text to AI Video Advanced Features
- Iterative editing: Maintain session state to tweak and refine videos over multiple prompts without starting over.
- Multi-track processing: Simultaneously manage video visuals, background music (BGM), and text overlays.
- Batch processing: Upload and process multiple text documents in a single session for high-volume content creation.
- GUI-to-API Mapping: Intelligently translates visual instructions like "add a title" into technical API track modifications.
- Automatic attribution: Includes specific platform and version headers to ensure compatibility across different Openclaw Skills implementations.
SKILL.md
Loading
Related Openclaw Skills
Best Video Letter Maker
Automate the creation of heartfelt personal video letters from text, images, and audio using remote GPU-accelerated AI.
Video Film — Edit and Export Cinematic Films
Video Film is a professional AI-driven editing skill that transforms raw footage into cinematic films using natural language commands and cloud GPU rendering.
MCP Builder
Rapidly bootstrap Model Context Protocol servers and tool integrations using natural language descriptions.
Shorts Repurposer
An AI-powered video transformation tool that converts long-form horizontal content into platform-ready vertical shorts with captions and smart cuts.
Coordinator
A professional aggregation node that collects, summarizes, and structures outputs from multiple AI agents to streamline executive decision-making.
Photo Video — Turn Photos Into Shareable Videos
Convert your photos into professional-grade slideshow videos with music and transitions in under 60 seconds using AI.
Featured*
