15 components in 3 categories
Voice, upload and camera components for AI
Not every request to an AI starts as typed text. These components handle the other ways in: voice (a voice orb, a live transcript, push to talk, a voice picker, a speaking spectrum), files (invoice extraction, image tagging, a file queue with summaries, a spreadsheet turned into a chart, a link reader) and the camera or pen (scan a page, handwriting to text, sketch to picture, describe this image).
Each one shows the whole journey from input to result, including the moment the AI is reading, so a visitor can tell it is working. They run in the browser with scripted content; connect them to your own speech, upload or vision service when you rebuild them.
Each one is three small files (HTML, CSS and vanilla JS, no framework) and a prompt that rebuilds it in Claude, Cursor, v0 or Lovable. All of them are free with an account.