Drop an image with text
A screenshot, a photo of a page or a scan — the text comes back in seconds
or paste a screenshot with Ctrl+V / ⌘V
Reads JPG · PNG · WebP · AVIF · HEIC · GIF · BMP — 55 languages — nothing is uploaded
About this tool
Turn a picture of text into text you can copy
Drop in a screenshot, a photo of a page or a scan and copy the words out of it, in 55 languages. Free, with no sign-up, and the image never leaves your device.
The recognition engine is Tesseract, the open-source OCR engine first developed at HP and then for many years by Google, compiled to run inside this page. It finds each line and word, highlights them on the image so you can see what it read, and gives you editable text to copy or save. Paste a screenshot with Ctrl+V or ⌘V and the text appears in a few seconds.
- Free, no sign-up
- Nothing uploaded
- No watermark
Built for real-world images
Small screenshots are enlarged and converted to greyscale before recognition, which is what OCR reads best. Words it is unsure about are marked in amber so you know what to check.
55 languages, two at once
Latin, Cyrillic, Greek, Arabic, Hebrew, Indian scripts, Thai, Chinese, Japanese and Korean. Pick a second language for documents that mix them, such as English with Spanish.
Private by design
Online OCR services usually upload your image. Here the engine runs in your browser tab, so receipts, IDs and private documents stay on your device.
Step by step
How to convert an image to text
Add your image
Drop a JPG, PNG, WebP or HEIC, press Browse files, or paste a screenshot with Ctrl+V or ⌘V.
Pick the language
Choose the language of the text, and a second one if it mixes two. The first run downloads that language once; after that it is cached.
Copy or save the text
Check the highlighted words, correct anything in the text box, then copy it or download it as a .txt file.
Get the most out of it
Tips for the best results
- Use the sharpest image you haveOCR reads clean, in-focus text far better. Crop away everything but the text, and photograph documents square-on in good light.
- Match the layoutAutomatic suits pages and screenshots. Choose Single line for one line of text and Scattered for signs, memes and labels spread around an image.
- Pick the right languageThe language decides which characters the engine expects. Text in the wrong language comes out garbled, especially accents and non-Latin scripts.
- Handwriting is hardTesseract is trained on printed text. Neat handwriting may partly work, but cursive usually will not.
Keep going
More free tools
Questions
Common questions
Everything here runs in your browser, so the answer to “where does my file go?” is always: nowhere. More in the general FAQ.
How do I extract text from an image?
Drop the image on this page or paste it with Ctrl+V or ⌘V, choose the language of the text, and the tool reads it in a few seconds. Correct anything it got wrong in the text box, then copy the text or download it as a .txt file.
Is this image to text converter free?
Yes. There is no sign-up, no limit on images and no watermark. It is free to run because the OCR engine works on your own device rather than on a server.
Are my images uploaded?
No. The image is read inside your browser tab. The only downloads are the OCR engine and the language data, fetched once from a public CDN and then cached; your image is never sent anywhere.
Which languages are supported?
55, including English, Spanish, French, German, Portuguese, Russian, Arabic, Persian, Urdu, Hebrew, Hindi, Bengali, Tamil, Thai, Vietnamese, Indonesian, Chinese (simplified and traditional), Japanese and Korean. You can combine two languages for documents that mix them.
How accurate is it?
On clear printed text, such as screenshots and good scans, nearly every word is right. Accuracy drops with blur, low resolution, unusual fonts, busy backgrounds and handwriting. Words the engine is unsure about are highlighted in amber so you can check them.
Can it read handwriting?
Only partly. Tesseract is trained on printed text, so tidy block capitals may work, but joined-up handwriting usually does not.
Can I convert a PDF to text?
This tool reads images. For a scanned PDF, take a screenshot of the page or export it as an image first. A PDF that already contains text lets you select and copy it directly.
Why does the first run take longer?
The first time, the browser downloads the OCR engine and the language data, about 7 MB together for English. Both are cached, so later images start straight away.