Image to Text
Get editable text out of screenshots, photos of documents and scans. Choose the languages in the image and copy or download the result.
INPUT
Drop an image here
Drop a file here or use Open file.
OUTPUT
Open an image, choose the languages and press Recognize text.
Your image is read on this device. The recognition program and language data are downloaded from jsDelivr the first time.
How to extract text from an image
Open the image
Drop a screenshot, photo or scan onto the input or use Open file.
Choose the languages
Select every language that appears in the image, then press Recognize text.
Copy the text
Check the result, correct anything that was misread, and copy or download it.
What OCR is good at
Optical character recognition reads printed text best: screenshots, documents, receipts and slides. Handwriting, decorative fonts and very small or blurred text are much harder.
Better results
Use a sharp, well-lit image where the text is straight and fills most of the frame. Cropping to the text first, with Crop Image, often helps.
Frequently asked questions
Is my image uploaded?
No. Recognition runs in your browser with Tesseract. The program and the language data (a few megabytes per language) are downloaded from jsDelivr the first time; your image is never sent.
Which languages are supported?
English, Turkish, Spanish, Arabic, German, French and Hindi. Select several if the image mixes languages.
Can it read PDFs?
This tool reads images. For scanned PDFs, use PDF OCR.