Persian & Arabic OCR that respects RTL
Extracting text from Persian and Arabic scans is more than running an English model on a different alphabet. Reading order, character variants, and mixed LTR/RTL layouts all matter.
Textora supports fas (Persian) and ara (Arabic) language packs, including mixed pairs such as English + Persian. Choose the language that matches your document before processing for the best results.
For scanned PDFs, pages are rasterized then recognized asynchronously. You can download plain text or structured JSON from the workspace when the job completes.
Ready to try? Use the image-to-text tool or PDF OCR.