Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- No visible changes in this release; documentation and configuration remain the same. - All features, supported models, and usage instructions are unchanged from the previous version.
What This Skill Does
Monet AI provides a unified API for video, image, and music generation across 30+ models from providers including OpenAI, Google, and ByteDance. Tasks are submitted asynchronously and polled for completion. Reference images can guide generation across most models.
One API key and endpoint gives access to models from OpenAI, Google, ByteDance, Runway, and others without managing separate accounts or integrations for each provider.
When to use it
- Generating product demo videos from text prompts
- Creating consistent character images across a content series
- Composing background music with custom lyrics for a video project
- Animating a static character image using a motion reference video
- Replacing a character in existing footage with a specified image
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a 10-second cinematic video of a mountain sunrise
- 1Submits a POST to /api/v1/tasks/async with type 'video', model 'sora-2', the prompt, and a unique idempotency_key
- 2Stores the task ID from the response
- 3Polls GET /api/v1/tasks/{taskId} every 5 seconds until status is 'success' or 'failed'
- 4Returns the output URL from the completed task response
A hosted video file URL at files.monet.vision ready for download or embedding
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.