Image to Text (OCR)
Read the English and Korean text in photos, screenshots and scanned images, then copy it or save it as TXT. Reads many images at once and straightens tilted photos. Your images are never uploaded.
Your files never leave this device. Everything is processed inside your browser and nothing is uploaded to a server.
When to use Image to Text (OCR)
Copy text from photographed papers
Pull the text out of a phone photo of a receipt, notice or business card and paste it instead of retyping. Handy for names, phone numbers and amounts.
Copy text from screenshots
Get the text from app screens that do not let you select it, chat screenshots or lecture slides. Light text on dark bubbles is found and read separately.
Turn many images into text at once
Add several scans or screenshots and each one is read and shown side by side. "Download TXT" saves them all in one TXT file, with each file name as a heading.
How to use the Image to Text (OCR) tool
- Click "Choose image files" or drag images onto the screen. You can add several at once.
- Choose the languages to recognize (English, Korean).
- The first time, click "Download data" to get the text recognition data. You will see the size first, and if you already downloaded it for OCR PDF, it is not downloaded again.
- Click "Recognize text" and wait. The text of each image appears next to it, and the lines that were read are boxed on the image.
- Fix any mistakes right in the text box, then click "Copy all" or "Download TXT". To copy one image only, click its "Copy".
Frequently asked questions
Which images can it read?
Any image your browser can open, such as JPG, PNG, WebP, GIF and BMP. iPhone photos (HEIC, HEIF) are read in every browser, including Chrome and Edge. It reads printed text and on-screen text in photos, screenshots and scans, in English and Korean.
Why do I need to download data?
Recognizing text needs an engine and language data (about 6 MB for English, 7 MB with Korean). These are public files from this site. Once downloaded they are kept in this browser, so they are ready next time. OCR PDF uses the same data, so downloading it in either tool is enough. Other browsers, devices and private windows need to download it again, and clearing browser data removes it.
How accurate is it, and what if it reads badly?
Sharp photos of printed text and screenshots are mostly read correctly. Blurry photos, shadows or glare, very small text, decorative fonts and dense tables may have mistakes, so check important content. Shooting in good light, straight on and close enough that the text fills the frame helps a lot. You can also crop to the part you need with "Crop & Rotate Image" first.
Can it read handwriting or vertical text?
The engine is made for printed text, so it reads very little handwriting. Only horizontal text is supported, not vertical writing. Scripts other than English and Korean, such as Chinese or Japanese, are not read.
What about tilted or sideways photos?
Phone photos are turned upright using the orientation saved in the photo. Text lines tilted up to 20° are straightened before reading. Sideways or upside-down images are turned and read again when almost nothing could be read, which takes a little longer. A page shot at an angle so it looks like a trapezoid is not corrected, so shoot straight on.
Can I get a searchable PDF?
This tool only extracts the text. For a PDF that keeps the original look and lets you search and copy the text, make a PDF with "Image to PDF" and then use "OCR PDF".
Are my images really not uploaded?
Yes. Only the recognition engine and language data are downloaded. Your images and the recognized text stay on this device, and copied text only goes to this device’s clipboard. The recognition engine is Tesseract (Apache License 2.0).
Are my files uploaded to a server?
No. Files are processed only inside your browser and are never sent to any server. Only the code and character mapping data needed for processing are downloaded from this site; your files themselves never leave your device. You can check this yourself in the Network tab of your browser's developer tools.
Are my files safe even with ads on the page?
Yes. Ads only run outside the tool area. The tool area, where you choose and process files, is an isolated space your browser keeps separate, so other scripts on the page, including ads, cannot read your file content or file names. The tool area is blocked from connecting anywhere other than this site. When you drag a file onto the page, the tool area expands to fill the screen so the isolated space receives the file.