Select one or more JPG, PNG, WEBP or HEIC images, such as photos of pages or screenshots.
Pick the language of the text: English, Spanish, Portuguese or Indonesian.
Click Extract text, then copy the text or download it as a .txt file.
Image to text reads the words in a picture (OCR) and gives them back as text you can copy, edit and paste. It works on photos of documents, letters, receipts, book pages and whiteboards, and on screenshots of chats, slides and error messages. The text appears beside the picture with every line marked, so you can check it.
The text is read by Tesseract, an open-source OCR engine, running in your browser. Your images are never uploaded, which matters for IDs, contracts and private messages. Join lines into paragraphs gives running text for documents; leave it off to keep the lines as they are.