Documentation

Install ScreenPilot, ask your AI app for a video, and learn every tool, command and setting.

Start

• Getting startedWhat ScreenPilot does, how a video gets made in four steps, and your first video in three asks to your AI app.
• Install ScreenPilotInstall ScreenPilot on Windows, macOS or Linux, add it to your AI apps, uninstall it, and fix common problems.

Use it

• Command lineEvery screenpilot command and its useful flags, grouped by job: record, edit, render, combine recordings, drive the desktop and set up, with the full workflow in one block.
• MCP toolsThe tools ScreenPilot gives an AI app, grouped by job: recording, footage, storyboard, render, combining recordings, desktop control and diagnostics.
• Storyboard referenceThe storyboard.json format: segments, holds, zooms, captions, highlights, narration, cards, overlays, music, extends, theme and output, with a full example.
• VoicesChoose a narration voice: Edge voices over the internet, speech models on your own computer, or any program you define. Setup, limits and fixes.
• Combine recordingsJoin several storyboards into one video with sequence.json, and insert a new feature clip into the middle of an existing demo without re-recording it.
• Let the agent driveThe agent performs the demo itself on your real desktop: write a take.json, rehearse it, perform it while recording, then edit and render.

Reference

• Safety and privacyWhat the agent can touch when it drives your desktop, how to stop it, how to limit it, what is logged, and what leaves your computer.
• PlatformsWhat ScreenPilot can do on each desktop: recording, driving, window control and click logging, plus requirements, per-OS notes and limits.
• FAQ and troubleshootingShort answers to common questions about ScreenPilot, plus fixes for the problems people hit most: permissions, dialogs, freezes and missing zooms.