Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates videos from text prompts using the Volcengine (ByteDance) video generation API. Accepts an optional first frame image via URL or local path to control the video's starting visual. Downloads the output file directly to a specified path.
Handles Base64 conversion of local images and automatic file download in one script, removing manual API wrangling steps.
When to use it
- Generate a product demo video from a text description
- Create animated content from a static reference image
- Batch-produce short clips with a scripted prompt
- Preview scene concepts by specifying an opening frame
- Automate video creation in a CI or content pipeline
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate a video of a cat walking through snow, save as cat_snow.mp4
- 1Confirm output filename is cat_snow.mp4 and compose the prompt
- 2Check for MODEL_VIDEO_API_KEY or ARK_API_KEY in the environment
- 3Run: python scripts/video_generate.py "cat_snow.mp4" "a cat walking through snow"
- 4Wait for the API to return a video URL
- 5Download the video to cat_snow.mp4
cat_snow.mp4 saved to disk; video URL printed to console
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.