Image to Text (OCR)

Reads the text in a photo, scanned image or screenshot and turns it into text you can copy. Use it when you want to move words from a picture into a document or message without typing them again.

How to use

1. Under "Text languages", select only the languages that appear in the image. You can select several of the 11 languages at once.
2. Drop the image onto the page or click to choose it; a screenshot can be pasted with Ctrl+V.
3. If needed, drag over the picture to choose the area to read, use the rotate buttons to make the lines level, or change "Enlarge".
4. Press "Read text" and the result appears under "Recognized text". Correct it, then press "Copy" or "Save as .txt".

How it works

• The open-source Tesseract engine reads the text inside the browser; the image never leaves the device. The first run is slower because the engine (about 4 MB) and language data are downloaded, and the page shows how much.
• Printed text and screenshots work best. Handwriting, very small or blurry text, curved pages and busy backgrounds are often misread, so always check the result.
• Under "Line breaks", "Join lines into paragraphs" removes the breaks at the end of each line in the image and keeps blank lines as paragraph breaks.

Questions and answers

How do I copy text from a picture?

Upload the picture and press "Read text". Fix any wrong characters in the result, then press "Copy" and paste the text where you need it.

How can I get better OCR results?

Drag to select only the text, rotate the image so the lines are level, and set "Enlarge" to 2× or 3× for small text. Selecting only the languages in the image also helps.

Can it extract text from a PDF?

No, it accepts image files only. Convert the PDF page to an image or take a screenshot first, then upload that.

Does it recognize handwriting?

The engine is made for printed text, so handwriting is often misread. Even with neat handwriting, check every line of the result.