A unified MiniMax API wrapper for generating high-fidelity audio, cinematic images, and professional video clips through a single CLI interface.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install minimax-skill
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 minimax-skill 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 MiniMax Media Generation?
The MiniMax Media Generation skill provides a streamlined interface to the MiniMax suite of generative models. This Openclaw Skills component allows developers to integrate text-to-speech, text-to-image, and text-to-video capabilities into their automated workflows with minimal configuration. By centralizing these distinct media types under a unified command structure, it simplifies the process of creating rich multimedia content for marketing, storytelling, or prototyping.
Built for efficiency, the skill handles the complexities of API polling for long-running video tasks and manages high-fidelity audio exports. It is designed to work seamlessly within the Openclaw Skills ecosystem, ensuring that media generation is both scalable and reproducible across different operating systems like Linux, macOS, and Windows.
MiniMax Media Generation Use Cases
- Creating high-fidelity narration and TTS audio for video projects or narration.
- Generating custom illustrations, posters, and cinematic images from text prompts.
- Producing motion clips and text-to-video segments for automated content pipelines.
- Implementing image-to-video workflows using first-frame and last-frame references.
- Automating bulk media generation for Token Plan project requirements.
How MiniMax Media Generation Works
- Initialize the skill by configuring the required MiniMax API key in the environment variables.
- Execute the unified minimax script via Python, specifying the desired media mode: audio, image, or video.
- Provide prompts or source files to the specific model (e.g., speech-2.8-hd for audio or Hailuo-2.3 for video).
- The skill communicates with the MiniMax API, managing request parameters and polling for task completion where necessary.
- Generated files are saved to the specified output directory for immediate use in other Openclaw Skills workflows.
MiniMax Media Generation Setup
Ensure you have Python 3 and the requests library installed. Set your API key as an environment variable:
export MINIMAX_API_KEY='your_api_key_here'
Install dependencies:
pip install requests
Run the unified command to verify the installation:
python scripts/minimax.py --help
MiniMax Media Generation Data Schema & Taxonomy
The skill organizes outputs based on the requested media type and user-defined paths.
| Media Type | File Format | Configuration Metadata |
|---|---|---|
| Audio | .mp3 | Model (Turbo/HD), Voice ID |
| Image | .jpeg | Aspect Ratio, Model version, N-count |
| Video | .mp4 | First/Last Frame Refs, Subject Reference, Timeout |
MiniMax Media Generation Advanced Features
- Image-to-Video generation using specific first and last frame image references.
- Multi-model support for specific fidelity requirements like speech-2.8-hd for higher audio quality.
- Advanced subject reference workflows using JSON-based subject definitions for video consistency.
- Support for high-latency polling with configurable timeouts up to 1800 seconds for complex video rendering.
- Modular script architecture allowing developers to call mode-specific scripts directly for narrower workflows.
SKILL.md
Loading
Related Openclaw Skills
MiVisionForge-SVOR
An AI-powered CLI tool for stable video object segmentation and removal using SVOR technology.
Household Book OCR
A specialized OCR skill for Openclaw Skills that extracts structured data from household register documents and images.
Design Pattern Selector
An intelligent diagnostic tool for AI agents to identify and apply the optimal Gang of Four design pattern for complex software architecture challenges.
Skill Graphify
Skill Graphify transforms any folder of code, documents, or images into a navigable and queryable knowledge graph with automated community detection.
OO Design Principle Evaluator
A specialized diagnostic tool that evaluates object-oriented architectures against foundational Gang of Four design principles to eliminate brittle inheritance and rigid coupling.
Accessibility Label Audit & Auto-fix (a11y-label-audit)
A comprehensive accessibility tool for scanning and automatically repairing a11y violations in React and TSX components.
Featured*
