Get the text out of a receipt, a sign, a slide or a scanned page without typing it again. Drop the picture below; the words are read on your device.
1
Drag the file onto the box above, or click Choose Files. Up to 20 photos of one document are read in the order you add them, or one PDF of up to 20 pages.
2
The assistant reads the printed words in your browser, page by page, and tells you when the text is ready. A long or busy page takes a little longer.
3
You get one .txt file with all the text, the pages separated by a blank line, to preview or download. Your pictures stay as they were.
A photo of a page is only pixels: you cannot search it, copy a line out of it or paste it into an email. Text recognition turns the printed words into plain text, so the lines of a receipt can go into a spreadsheet, a quote into a message, or a scanned letter into a document you can edit.
It works best on clear, upright, printed English at a readable size. Handwriting, blurry or tilted photos, decorative fonts and pages with columns or tables come out wrong or incomplete, so check the text against the picture. Turning a sideways photo the right way up first helps.
The reading happens in your browser, so the picture is not uploaded. To reply to you about the result, the assistant is given the file's name and the start of the text it found, up to 2,000 characters, but never the image itself.
English only. Text in other languages comes out wrong or empty.
No. It is made for printed text; handwritten notes are not recognized reliably.
It keeps the line breaks as printed. Ask for flowing text instead and each paragraph becomes one line, ready to paste into a document. Columns and tables are not kept, and their reading order may be off.
No. It works in a modern web browser on a computer or a phone, with no account to create, nothing to install and no watermark on the result.
No. Every result is saved as a new file, and the file you dropped stays exactly as it was.