Media
4 items
Description
Record clicks and screenshots on any web app, then edit and export step-by-step guides as HTML, PDF, PowerPoint or JSON. Capture user interactions across any web application and turn them into clear, structured, step-by-step guides — each step paired with a contextual screenshot that highlights exactly what was clicked. Every step is saved in editable JSON and HTML, so you can review, reorder, annotate, and refine the workflow before sharing it. Export the finished guide as HTML, PDF, PowerPoint, or JSON for documentation, onboarding, training material, or automated workflows. KEY FEATURES • One-click recording of clicks, inputs, and navigation on any website • Automatic screenshots with the interacted element highlighted • Built-in editor to edit, annotate, reorder, and add notes to each step • AI step descriptions — an LLM analyzes a screenshot and writes a detailed, professional description of the step • AI image translation — regenerate a screenshot with its on-screen text translated into another language • Per-step audio narration (microphone or system/tab audio) embedded in your exports • Export to HTML, PDF, PowerPoint, or JSON — and re-import JSON to keep editing PRIVACY • Your recordings are stored locally in your browser — nothing is sent to our servers. • The AI features are optional and run only when you add your own Google Gemini API key. When used, the relevant screenshot and text are sent directly from your browser to Google's Gemini API for processing; your key is stored only on your device.