Skip to content
Tool Dock

Image to Text (OCR)

Extract text from photos and screenshots in 13 languages, right in your browser.

Drop your file here

PNG · JPG · WebP · GIF · BMP · AVIF · Stays on your device

Options
  • Runs in your browser
  • Nothing is uploaded
  • Free, no sign-up

How to use it

  1. Choose a photo, scan or screenshot that contains text.
  2. Pick the language of the text. The first run downloads that language's data (a few MB), which is cached afterwards.
  3. Run it, then copy the recognised text.

Why Tool Dock

  • FastEverything runs on your own device, so there is no queue and no waiting for uploads.
  • PrivateYour files and text never leave the browser. Close the tab and they are gone.
  • Batch friendlyDrop several files at once and download each result, or all of them together.

Questions

How accurate is it?

Clear, straight, well-lit text is recognised very accurately. Handwriting, heavy skew and low-resolution photos reduce accuracy; cropping to the text helps.

Is the image sent to a server?

No. Recognition runs in your browser with Tesseract compiled to WebAssembly. The language files are downloaded once from our servers and cached locally.

Why is the first run slow?

Your browser has to download the OCR engine and language data (about 5–10 MB) the first time. Later runs reuse the cached files.

All tools