1) Copy one sentence, paste it into your agent
Your agent downloads the build, verifies the signature, and installs every official Skill in one go. No account is needed for this step.
How it works
How ScaleMuse turns one sentence into a finished video
ScaleMuse is a set of video Skills for the AI agent you already use. One sentence installs it into Codex, Claude Code, Cursor, or WorkBuddy; you say what video you want, and it renders on your own computer.
Three steps
2) Say what video you want
"Make me a 45-second, 9:16 explainer about AI chips." The entry Skill picks the right method, asks only when it needs your call, and checks in with you all the way to the final cut.
3) The video renders on your computer
Project, timeline, and render all stay local. Credits are charged only when voice, image, or video models are used, and you see the cost before it happens.
Why it is built this way
Free wherever it can be: Skills and the local app cost nothing. Credits apply only to voiceover, speech recognition, and image or video generation, quoted before you submit.
Local by default: Footage, projects, and renders never leave your machine. Only the model calls you approve send the necessary inputs to ScaleMuse.
Editable and shareable: A Skill is just a folder with a SKILL.md inside. Fork an official one or write your own, publish it, and anyone can install it with one sentence.