Tigrinya Image to Text (OCR)

Turn a photo, screenshot or scanned PDF of printed Tigrinya into text you can copy, edit and paste, without typing it again on a Ge’ez keyboard. Letters, notices, news, forms and pages that mix Tigrinya with English and numbers are read too. It runs on your device and works offline after the first use.

  • Never uploaded
  • Free, no sign-up
  • No watermark
  • Works on phones
  • Works offline after one download

Your files are read on your device and never uploaded.

Works offline after one download.

How to copy Tigrinya text from a photo

  1. Add photos, screenshots or a scanned PDF of printed Tigrinya pages, or take a photo of a page. Rotate any page that is sideways.
  2. Keep “Tigrinya + English” selected and tap “Read text”. Phone photos are cleaned up first to remove shadows.
  3. Check the highlighted words, fix anything that’s wrong, then copy the text or download it as a .txt, .docx or searchable PDF file.

Why use Picsawa

  • Private by designFiles are processed on your device and never uploaded.
  • Free, no sign-upNo account, no watermark and no daily limits.
  • Works everywherePhones, tablets and computers, in any modern browser.

About the Tigrinya Image to Text tool

Tigrinya is written in the Ge’ez (Ethiopic) script like Amharic, but it uses letters Amharic does not, such as the ቐ row, and writes ኣ where Amharic writes አ. This reader runs Tesseract’s Tigrinya model together with its Amharic and English models: in our test that halved the errors of the Tigrinya model on its own, and it also reads the numbers, dates and English words on a page.

In our test on twelve lines of printed Tigrinya (a greeting, notices, news, a form, a proverb, a time, a phone number and an email address) in four common fonts (Nyala, Ebrima, Abyssinica SIL and Noto Sans Ethiopic) at two sizes, about 98 of every 100 letters were read correctly, and about 99 in larger, clear print. Small screenshot text and decorative fonts need more checking, which is why unsure words are highlighted.

Unlike the Amharic page, no word list changes the text, because Tigrinya words differ from Amharic ones. What you see is what the reader found; only words that first came out as English letters inside a Tigrinya line are read again.

The result is standard Unicode Tigrinya, so you can paste it into Word, Google Docs, Telegram, WhatsApp or an online form. Your files are never uploaded: the reader and its models (about 6 MB) download once and stay in your browser, so after that it also works offline.

Frequently asked questions

How accurate is the Tigrinya text?

On clear printed text, about 98 of every 100 letters are read correctly in our tests with common fonts such as Nyala and Ebrima. Small screenshot text, decorative fonts and dark or blurry photos need more checking, which is why unsure words are highlighted.

Does it work for Tigrinya from Eritrea and from Tigray?

Yes. Both are written with the same Ge’ez letters, and the reader does not depend on one spelling or a word list. As with any text reader, check names and rare words.

Can I paste the Tigrinya text into Word or Telegram?

Yes. The text is standard Unicode, so it pastes into Word, Google Docs, Telegram, WhatsApp or any form that accepts Ge’ez letters. The .docx download marks it as Tigrinya and sets an Ethiopic font.

Are my files uploaded?

No. The text is read in your browser with an on-device engine. Your photos, PDFs and the text never leave your phone or computer, so private letters and forms stay private.

Can it read a scanned PDF?

Yes. Add the PDF and each of its pages appears in the list, up to 50 pages at a time; a password-protected file opens after you type its password. You can copy the text, download it as .txt or Word (.docx), or get a searchable PDF: the same pages with the text hidden underneath, so you can search and copy it.

Can it read handwriting?

No. It reads printed or typed text: letters, books, forms, notices, screenshots. Handwriting usually comes out wrong.

How do I get the best result?

Photograph the page flat and straight, in good even light, close enough that the text fills the photo. Rotate pages upright before reading. Screenshots of clear text work very well.

Why does the first read take longer?

The first time, the reading engine and language models are downloaded once (about 6 MB for Amharic + English). They are then kept in your browser, so the next time starts right away, even offline.

What do the highlighted words mean?

Yellow words are ones the reader wasn’t sure about, so please check them. Green words were changed automatically: Amharic words corrected with a list of common Amharic words, or Ge’ez words read again after first coming out as English letters. Tap one to switch back to what was read. You can edit all of the text before you copy it.

Guides

Step-by-step guides for ID and visa photos, upload size limits in KB, stickers and text recognition, each with its sources. All guides →