Image to Text (OCR)

Extract text from photos, screenshots and scanned documents with OCR (optical character recognition). Recognition runs in your browser: the OCR engine is downloaded once, and your image is never uploaded.

Your files never leave your device.

Loading tool…

Good to know: The first run downloads the open-source Tesseract OCR engine and the selected language model (about 5–15 MB) from a public CDN; your image itself stays on your device. Handwriting and very stylised fonts are recognised poorly.

How to use the Image to Text (OCR)

1Choose an image, screenshot or photo of a document (or paste one with Ctrl/⌘ + V).
2Select the language of the text.
3Click “Extract text”, then copy or download the result.

What is the Image to Text (OCR)?

OCR turns the pixels of letters into editable text. This tool uses Tesseract, a widely used open-source OCR engine, compiled to WebAssembly so it runs in the browser.

Accuracy depends mostly on the image: sharp, well-lit, straight text at 300 DPI or higher gives the best results. Crop the image to the text area and increase contrast for difficult photos.

Frequently asked questions

Which languages are supported?

English, German, French, Spanish, Italian, Portuguese, Dutch, Turkish, Persian, Arabic, Russian, Chinese (simplified), Japanese and Hindi. Each language model is downloaded the first time you use it.

Can it read handwriting?

Only neat block capitals. Tesseract is designed for printed text, so cursive handwriting is usually not recognised.

Is the Image to Text (OCR) free and private?

Yes. The Image to Text (OCR) is free, needs no account, and processes your files entirely in your browser. Files are never uploaded to a server or stored.

All image tools →