Tools › Image tools
Image to text: copy the text out of a picture
Convert an image to text online: copy text from photos, scans and screenshots in 25 languages, or paste from the clipboard. Save a .txt. Runs on your device.
Copy words that are stuck in an image
A screenshot or photo contains pixels where you see letters. Tesseract reads those pixels in the browser and puts the result in an editable text box. The outlines over the picture show where it found words or lines. A server-based OCR service needs the image first. Nibbo does the reading and keeps the editable result on your device.
How it works
- Paste a screenshot or choose one or more images from your device.
- Select the languages visible in the image and start recognition.
- Compare the editable result with the picture. Check the areas outlined with dashed boxes first.
- Correct the text and copy it, or download TXT for one image or for the whole batch.
Check the characters that matter
For a screenshot of an error dialog, crop out unrelated menus before recognition and compare the result with the original before pasting it into a ticket. An uppercase O can look like a zero in an error code. For a label on a parcel or shelf, photograph it straight on in good light and check part numbers next to the picture. With several images, review each text box before exporting them together.
Images, languages and the file cap
Start with a screenshot from the clipboard or drop an image such as a PNG or JPEG. Choose the written language and read the dashed outlines as prompts to check the text. Small or decorative type and handwriting can produce errors. Free allows up to 3 GB per file. On the device where you sign in, Pro removes the size cap. Large batches can still use a lot of browser memory.
Clipboard images stay local
Pasting a screenshot gives this tab the image so it can read the text. The browser may fetch the OCR engine and language files. The pixels and recognised text are processed in the tab and stay off Nibbo’s server.
Questions
How do I copy text from an image or a screenshot?
Paste the screenshot with Ctrl+V or drop the image on Nibbo image to text. Tesseract reads it in your browser in 25 languages; edit the text, then copy it or save a .txt. Nothing is uploaded.
How do I get the text out of a PDF?
Use PDF to text: it extracts the text to a .txt file and reads scanned pages with OCR. To keep the PDF and make the scan searchable, use OCR PDF.
Does it work offline?
After the first use, yes. The OCR engine and language files (about 2–3 MB per language) are downloaded once from this site and kept in your browser.
Are my images uploaded?
No. Recognition happens on this device; only the OCR engine and language files (about 2–3 MB per language) are downloaded once from this site.
Which languages can it read?
English, Spanish, Portuguese, French, German, Italian, Polish, Turkish, Russian, Ukrainian, Uzbek (Latin and Cyrillic), Kazakh, Indonesian, Vietnamese, Thai, Hindi, Bengali, Urdu, Arabic, Persian, Chinese (Simplified and Traditional), Japanese and Korean, up to three at once.
Can it read handwriting?
Only neat block letters, and not reliably. It is built for printed and on-screen text.
I have a scanned PDF, not an image.
Use OCR PDF: it adds a searchable text layer to the PDF and also gives you the text.