Image

Image to Text

Pull the words out of any image. Upload or drop a photo, screenshot, or scan and this tool reads the text with OCR, ready to copy in 13 languages. The image is read in your browser, so it never leaves your device.

Drop an image hereor upload a photo, screenshot, or scan to read its text

Your image is read in your browser. It is never uploaded to a server.

How to use it

1. Add an image

Upload a photo, screenshot, or scan, or drop a file straight onto the tool.

2. Pick the language

Choose the language of the text so the engine reads the right alphabet.

3. Extract the text

Press Extract text. The engine loads once, then reads the image and shows a progress bar.

4. Copy or edit

Read the text in the box, fix any stray characters, and copy it with one click.

Common questions

Does my image get uploaded anywhere?

No. The text is read in your browser with a WebAssembly OCR engine that runs on your own device. The picture itself is never sent to a server, so the tool keeps working offline once the page and the language model have loaded.

Why is the first run slower?

The first time you use a language, your browser downloads that language model one time, which is a few megabytes. The browser then caches it, so later runs in the same language start much faster. The progress bar shows when the model is downloading and when the image is being read.

Which languages and file types are supported?

You can read 13 languages, including English, Spanish, French, German, Chinese, Japanese, Korean, Arabic, and Hindi. For images, any PNG, JPG, WebP, BMP, GIF, or TIFF your browser can decode will work.

How accurate is the text?

Accuracy depends on the image. Clear, high-contrast, upright text reads very well, while blurry photos, handwriting, low light, and heavy backgrounds read less well. The text box is editable, so you can fix small errors before you copy, and choosing the correct language improves the result.

What is OCR?

OCR stands for optical character recognition. It is the process of turning the letters in a picture into real, selectable text that you can copy, search, and edit. This tool uses Tesseract, a long-established open-source OCR engine, compiled to run inside your browser.