Syncs audio to video faces through fal.ai's lip sync API. You'd reach for this when you need to localize video content without reshooting, create explainer avatars that speak scripted audio, or generate quick social media clips with talking heads. It's a workflow skill from the fal.ai community team, so you're relying on their hosted service for the heavy lifting. The actual implementation lives upstream in their GitHub repo. Useful if you already have video footage and want to match new audio to it, less so if you're starting from scratch and need full avatar generation.
npx skills add https://github.com/nexu-io/open-design --skill fal-lip-sync