Workspace / AI / OCR

AI

Image to text (OCR)
Text you can actually copy.

Pull the words out of a screenshot, scan or photo in 15 languages, ready to copy or download.

Runs entirely in your browser
Upload your images
JPG, PNG, WebP, AVIF, HEIC · 50 MB max
Waiting for an imageProcessed on your device
Output settings
Tesseract OCR

Language of the text

Sharp, straight screenshots and scans read best. Photos of a screen or page at an angle lose accuracy.

Tesseract OCR~15 MB per language

Downloads the language once, then works offline.

Downloads once on first use, then runs offline. Your images are never uploaded.

Your files never leave your device
Fast local processing
Start over anytime

How did this tool do?

Guide

How to use it

  1. 01Drop a screenshot or scan, or paste one with Ctrl+V.
  2. 02Pick the language of the text and tap Read text.
  3. 03Open the file to read it, then copy it or download a .txt.

Good to know

Questions, answered

Which languages are supported?

15, including English, Spanish, French, German, Portuguese, Russian, Arabic, Hindi, Japanese, Korean and Chinese. Each language downloads once, the first time you pick it.

How do I get the best results?

Straight, sharp images with good contrast. Crop to the text you need, and if a photo is slightly rotated, straighten it with the Rotate tool first.

Does it keep the layout?

Line breaks are kept, but columns and tables come out as plain text in reading order.

Is my image sent to a server?

No. The AI model itself is downloaded to your browser the first time you use the tool, then everything runs on your device — the image never leaves it. After that first download the tool works offline.