Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Documentation update: Bumped version in SKILL.md from 2.0.0 to 2.0.1. - No functional changes; content and usage remain the same.
What This Skill Does
Provides access to 37 AI video generation models, including Sora, Kling, Veo 3, Seedance, Hailuo, WAN, and Grok, through a single API key. Supports text-to-video, image-to-video, first-last-frame interpolation, and auto-generated audio.
One API key and one interface covers 37 models across multiple providers, removing the need to manage separate accounts for Sora, Kling, Veo, and others.
When to use it
- Animating a product photo into a short promo clip
- Generating a cinematic scene from a written description
- Creating a portrait-format reel from a still image
- Comparing how different models interpret the same prompt
- Adding auto-generated audio to a Seedance or Veo 3.1 video
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Animate this product photo into a 6-second widescreen video with audio
- 1Upload the image via upload_file tool to receive a hosted file URL
- 2Call generate_video with model seedance-1.5-pro, the file URL as image_urls, duration 6, aspect_ratio 16:9, and generate_audio true
- 3Report estimated generation time to the user
- 4Poll check_task every 10-15 seconds and relay progress percentage
- 5Share the result URL and remind the user links expire in 24 hours
Video URL with auto-generated audio, valid for 24 hours
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.