About image-to-text (OCR)
Image to Text uses OCR (optical character recognition) to pull the words out of a picture — a photo, scan or screenshot — and turn them into editable, selectable text you can copy or download. It recognises many languages and runs entirely in your browser, so your images are never uploaded to a server. It is perfect for copying text you can only see as an image.
How Image to Text works
How to extract text from an image
- Drop an image or screenshot onto the box, or click to choose one.
- Pick the language of the text and click Extract text.
- Wait a moment while it recognises the words, then copy or download the result.
For the best results
Use a clear, high-contrast, straight image where the text is in focus. Printed text reads far better than handwriting, and bigger, sharper text gives cleaner results. The first run downloads a small language model, so it takes a little longer; later runs are quicker.
Private and free
OCR happens locally in your browser using a WebAssembly engine — your images never leave your device, there is no sign-up, and there are no limits.
Common uses
- Copy text from a screenshot or photo
- Digitise a printed document or receipt
- Grab text from an image you cannot select
- Extract a quote or code from a picture
- Pull text out of a scanned page
- Convert a sign or label photo to text
- Capture text from a slide or diagram
- Get editable text without retyping