Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
No changes detected in this version. - The skill definition and documentation remain unchanged from the previous version.
What This Skill Does
Edits and transforms existing videos using 25+ AI models via the EachLabs Predictions API. Covers lip sync, subtitle generation, style transfer, video extension, upscaling, audio merging, face swap, and translation. Operates through a poll-based prediction flow.
Accessing 25+ specialized video AI models through a single consistent API avoids managing separate integrations for each provider.
When to use it
- Sync new voiceover audio to a talking-head video
- Add auto-generated subtitles to a recorded presentation
- Upscale a low-resolution video before publishing
- Extend a short clip with a continuation scene
- Translate video speech into another language
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Add subtitles to my video at https://example.com/video.mp4
- 1Check model info with GET /v1/model?slug=auto-subtitle to confirm input schema
- 2POST to /v1/prediction with model 'auto-subtitle', version '0.0.1', and video_url input
- 3Poll GET /v1/prediction/{id} until status is 'success' or 'failed'
- 4Extract the output video URL from the response
URL to the video file with burned-in subtitles
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.