Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Fix display name to Freepik (was Freepik 1.0.0)
What This Skill Does
Connects to Freepik's AI API to generate images, videos, icons, audio, and stock content from text prompts or reference images. Supports 50+ models including Mystic, Flux variants, Kling, Hailuo, RunWay, Seedream, and ElevenLabs TTS. Most operations are async and use a task-polling pattern.
One API key gives access to 50+ AI media models across image, video, audio, and icon generation, removing the need to manage separate accounts for each provider.
When to use it
- Generating a product mockup image from a text description
- Creating background music for a short promotional video
- Removing the background from a product photo
- Animating a static illustration into a 5-second clip
- Upscaling a low-resolution image to 4K with detail enhancement
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a cinematic 16:9 video of a mountain sunrise
- 1Submit POST request to /v1/ai/video/kling-v3-omni-pro with prompt and aspect_ratio 16:9
- 2Capture task_id from the response
- 3Poll /v1/ai/video/kling-v3-omni/{task_id} every 3 seconds until status is COMPLETED
- 4Extract the result video URL from the response
- 5Present the signed CDN URL to the user
A temporary signed CDN link to the generated video file
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.