Image to Text (OCR)

What it does

Image to Text (OCR) pulls editable text out of images, screenshots and PDFs from within Chrome, using a right-click menu or a screen crop. It helps students, office workers and researchers who need to reuse text that is locked inside pictures.

Key features

• Right-click any image and choose Extract Text to get editable text
• Crop part of the current screen to run OCR on a specific region
• Recognises text in a wide range of languages and handles rotated images
• Converts PDFs as well as images and can play the extracted text as audio
• Detects links and email addresses contained in the image or PDF

Use cases

• Copying a quote from a screenshot shared in a chat
• Turning a scanned PDF page into text you can edit
• Collecting email addresses or links shown in an image

Getting started

Right-click an image on a page and select Extract Text, or open the extension and use the crop tool to select the area of the screen you want to read.

Good to know

Accuracy drops with low-resolution, handwritten or heavily stylised text, so check results before relying on them.