How to Get Text Out of a Photo or Scanned Document

A photo of a receipt, a screenshot of a paragraph, a scanned printed page - the text is right there, but you can't select it, search it, or paste it anywhere. To a computer it's just pixels until something actually reads it.

Pull the text out

• Open Image to Text (OCR) and drop in the photo or scan.
• The image is read on your device and the recognized text appears in a box you can copy from directly or download as a plain .txt file.

Why this beats retyping it

Retyping a paragraph by hand is slow and it's easy to introduce a typo nobody notices until later. Optical character recognition (OCR) reads the actual shapes of the letters and reconstructs the text directly, which is faster and more faithful to the original for anything longer than a sentence or two.

Starting from a PDF instead of a photo?

If the text you need is inside a scanned PDF rather than a standalone photo, PDF to Text (OCR) reads it directly - drop in the whole PDF and it recognizes each scanned page in order, no need to pull an image out first.

Getting the best result

OCR reads shapes, so the clearer the shapes, the better the result. A sharp, well-lit, right-side-up photo with plain printed text will come back close to perfect. Heavy blur, glare, low resolution, a steep skew, or handwriting all make it harder, and it's worth retaking a photo rather than feeding in a bad one if the result looks off.

Common questions

Is my photo uploaded anywhere? No, recognition runs entirely in your browser using WebAssembly. The image never leaves your device.

Why did the first run feel slower? Your browser downloads the OCR engine the first time you use the tool. It stays available for the rest of your session after that.

Does it handle handwriting? It's built and tuned for printed text. Handwriting recognition is a much harder, different problem and results on it will be inconsistent.