← All skills & workflows

video

ai-video-gen

Generate AI video and images through a **backend router** — the skill owns the task vocabulary (text→video, image→video, lipsync, upscale, foley, stills) and dispatches each job to whichever backend is authenticated and cheapest for the requested model. Three backends

Inputs

  • request — What to produce
  • scope — Company or client-id
  • backend — Force a backend: veo | higgsfield | inference-sh (default: auto)
  • request — What was requested

How you ask

  • Generate a marketing video using Veo 3
  • Create a text-to-video clip for our social media
  • Animate this product image into a video with Seedance
  • Generate an AI video using Wan 2.5 for our launch

Outputs

  • auth-guidance (text)
  • mp4 (video)
  • video-prompt (markdown)
Leveladvanced
Inputconversation
Outputvideo-script
Setup[install]
Roles[Head of Marketing, Content Manager]