OCR (extract text)

Turn images, PDFs, and documents into editable text in seconds.

Written By Zack (Zense AI)

Last updated About 1 month ago

OCR (Optical Character Recognition)

OCR (Optical Character Recognition) reads text from an image or document so you can copy, edit, and reuse it β€” perfect for digitising old worksheets or handwritten notes.

OCR is a quick way to turn scanned worksheets, photos of whiteboards, or PDF handouts into editable text you can paste into Chat or save to Library.

Extract text

Upload a file and wait a moment β€” extractions also run in the background so you can keep uploading more.

  1. Open Explore Tools β†’ OCR.
  2. Drop a file or click Browse files to upload.
  3. Wait a moment while it processes β€” extractions also run in the background, so you can keep uploading.
  4. The extracted text appears, ready to use.

Supported files

Clear, high-contrast scans give the most accurate results.

  • PNG, JPEG
  • PDF
  • PPTX, DOCX
  • Up to 50MB per file

Work with the results

Copy the text, download it, or reopen past extractions from History.

  • Copy the text to your clipboard or Download it.
  • Multi-page documents show text per page, and embedded images are saved per page too.
  • Your past extractions are kept in History so you can reopen them.

Tip: Clear, high-contrast scans give the most accurate results.