A comprehensive toolkit for generating high-fidelity AI video, image, and audio content using the Runway Gen-4.5 model suite.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install runwayml
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 runwayml 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 RunwayML AI Video & Media Generation?
This skill provides a robust interface to the RunwayML API, enabling developers to integrate state-of-the-art generative media capabilities into their automated workflows. As a core component of Openclaw Skills, it allows for seamless text-to-video, image-to-video, and advanced audio processing using models like Gen-4.5, Gen-4 Turbo, and Google Veo. Whether you are building automated content pipelines or creative tools, this skill streamlines the interaction with Runway high-performance models.
By utilizing Openclaw Skills for media generation, developers can leverage industry-leading features such as character performance, video-to-video transformation, and high-quality image stylization. The integration simplifies the complexities of asynchronous task management and model selection, providing a developer-friendly bridge to professional-grade AI media production with minimal configuration.
RunwayML AI Video & Media Generation Use Cases
- Automated video content creation for social media marketing using text-to-video prompts.
- Transforming static product photography into dynamic cinematic clips with image-to-video workflows.
- Generating localized voiceovers and sound effects for global multimedia projects via ElevenLabs integration.
- Rapid prototyping of visual concepts using Gen-4 turbo for fast iteration cycles.
- Creating consistent character performances and motion for animation pipelines using the act_two model.
How RunwayML AI Video & Media Generation Works
- Initialize the client by providing the RunwayML API secret to the environment variables.
- Select the desired media model from the available library, such as Gen-4.5 for high-fidelity video or ElevenLabs for audio synthesis.
- Submit a generation task containing specific parameters like prompt text, reference images, and desired aspect ratios.
- Monitor the asynchronous task status through Openclaw Skills which handles the transition from pending to running.
- Retrieve the final generated output URL once the polling mechanism confirms a successful completion.
RunwayML AI Video & Media Generation Setup
To begin using this skill, you must first obtain an API key from the Runway developer portal. Once obtained, configure your environment and install the required dependencies.
# Set your API secret
export RUNWAYML_API_SECRET="your_api_key_here"
# Install the official Node.js SDK
npm install @runwayml/sdk
RunwayML AI Video & Media Generation Data Schema & Taxonomy
The skill manages generative tasks through a structured metadata system to ensure tracking and retrieval of assets.
| Property | Description |
|---|---|
| task_id | Unique identifier for the asynchronous generation process |
| status | Current state of the job: PENDING, THROTTLED, RUNNING, or SUCCEEDED |
| output | An array containing the URLs of the generated media assets |
| model | The specific model identifier used (e.g., gen4.5, veo3.1) |
| ratio | The aspect ratio configuration used for visual outputs |
RunwayML AI Video & Media Generation Advanced Features
- Automatic task polling with a 10-minute timeout using the built-in SDK handler for reliable output retrieval.
- Support for a wide range of aspect ratios including 21:9 ultra-wide for cinematic content and 9:16 for vertical mobile formats.
- Multi-provider integration allowing access to Google Veo for audio-synced video and ElevenLabs for text-to-speech.
- Advanced video-to-video transformation capabilities using the gen4_aleph model for creative style transfers.
- Granular motion control through character performance mapping and camera movement prompts like dolly-in and tracking shots.
SKILL.md
Loading
Related Openclaw Skills
cuihua-i18n-helper
An AI-powered internationalization assistant that automates string extraction, multi-language translation, and quality assurance for modern web applications.
Apache ORC Storage Specialist
A comprehensive reference for the Apache ORC columnar storage format, covering file architecture, compression codecs, and cross-engine integration.
Moark OCR
A high-performance OCR skill that utilizes the GITEE AI API to extract, recognize, and summarize text from image files.
WeryAI Video Watermark Removal
A specialized technical skill for removing watermark overlays from existing HTTPS videos using the WeryAI API.
WeryAI Video Background Remover
A specialized tool for AI agents to programmatically remove or replace video backgrounds with solid colors using the WeryAI API.
OpenClaw Intelligence Officer
An automated industry intelligence system that scrapes global tech platforms, generates AI summaries, and delivers daily reports to your communication apps.
Featured*
