Free browser tool

Image to Text (OCR)

Pull text out of screenshots, scans, and photos. Recognition runs in your browser with Tesseract.js — your image never leaves your device.

Runs in your browser No image upload
Drop an image here or click to choose a JPG, PNG, or WebP file

Your file is processed on your device only.

Copy text from any image

Screenshots, scanned documents, and photos of signs all contain text you may want to reuse. Optical character recognition (OCR) reads that text so you can copy it instead of retyping.

This tool uses Tesseract.js, a free OCR engine that runs as WebAssembly in your browser. The engine file and language data download from a CDN the first time you use it; your image itself is never uploaded.

FAQ

OCR questions

Is my image uploaded to a server?

No. Text recognition runs entirely in your browser with Tesseract.js (WebAssembly). The OCR engine downloads from a CDN on first use, but your image stays on your device.

How accurate is it?

Accuracy depends on image sharpness and text clarity. Clean, high-contrast print and screenshots work well. Handwriting and decorative fonts are less reliable.

Which languages are supported?

This tool recognizes English by default. Tesseract supports many languages; the engine downloads the needed language data on first use.

Which formats can I use?

JPG, PNG, and WebP images. Very large images may be slower on low-memory devices.

Related tools

Clean up before OCR