Image to Text Converter (OCR)
Pull editable text out of images, screenshots and scanned pages in seconds, in 45 languages.
How to use: Image to Text (OCR)
- 1
Add an image
Drop a photo, screenshot or scan with text. You can add several images.
- 2
Pick languages
Select every language in the text and click Recognize text.
- 3
Copy or save
Edit the recognized text if needed, copy it or download it as a .txt file.
About OCR
OCR, or optical character recognition, converts pictures of text into characters you can select, copy, search and translate. It saves retyping when you need a quote from a screenshot, a paragraph from a photo of a book, details from a receipt, a sign in a foreign language or the text of a scanned letter.
Drop one or more images — JPG, PNG, WebP, BMP, TIFF or HEIC — and choose the languages in the text. You can combine several, for example English with German or with Chinese. Recognition runs on your device with the Tesseract engine; the language data is downloaded once and then cached. Small images are upscaled automatically, because OCR works best when letters are at least about 20 pixels tall.
The result appears next to the image with an estimated accuracy. Fix any mistakes directly in the text box, then copy the text or download it as a .txt file; with several images you can copy all texts at once. For a formatted document instead, use JPG to Word.
Everything runs locally in your browser — your images are never uploaded to a server.