Pashto OCR — Image to Text & PDF
له عکسونو او سکین شویو اسنادو څخه پښتو متن په اسانۍ وباسئ
- Extended Arabic script support
- RTL layout engine
- Calligraphic & print fonts
Free image OCR. No account needed. PDFs use pages.
Open OCR for all languagesDaniel in Pashto, 1895
Real scan. Unedited OCR.
۳۹۱ دائئیل
د دائيل نبي کتاب
اول باب
اد يهوداه د بادشاه یهو يتم د بادشاهي په دريم كال د بابل بادشا
بنوکد نضر اورشليم ته راغي او هغه في كير كړه او خداوند د يهوداه Y
بادشاه يهو يقيم له څنو لوښسو دبيت الله سره في دهغه په لاس
ورکړ ده هغه د سنتار په زمکه کښ د خپل معبود کور ته یوورل
او هغه لوښي ئي دخپل معبود په خزاني کښ داخل کړل
او بادشاه د خپلو خواجه سرایانو سردار اشپناز ته حکم وکړ
چه د بني اسرائيلو د بادشاه له اولاد نه او له امیرانو نه د یوڅو را خام
كري تم هسي خوانان چه عیب په کښ نه وي بلکه ښائسته او په حکمت
کښ ماهره او په هري خبري کښ پوه او صاحب د علم وي اوچه په
بادشاهي محل کښ د ودريدلو لايق وي او هغوي ته د د كسد يانو|
علم او ژبي ورزده کړي شي ة او بادشاه هغوي لره له بادشاهي خوراک A
نه او د خپل څښاک له شرابو نه د هري ورثي بخره مقزره کړه په دي
شان في هغوي تر دريو کالو پوري و پالل چه په آخر هغوي د بادشاه
په حضور و دريږي، او د هغوي په مخ کښ له بني يهوداه نه دانتيل
حنانیاه او میشائیل او عزرياه وو، او د خواجه سرایانو سردار له هغو
نه په هر یوه باند نوم کیښود په دانتيل في بلطشضر او په حنانياه في
شدرک او په ميشائيل في ميسک او په غزرياه ئي عبدنجو
لیکن دانتيل پخپل زړه کښ اراده وکړه چه خپل څان به د
بادشاهي خوراک او د هغه د څښاک له شرابو نه ناپاک نه کړي او ده
د خواجه سرایانو سردار نه عرض وکړ چه خپل څان ناپاک نه کړي و او 9
الله دانيل ته د خواجه سرایانو د سردار په نظر کښ فضل او رحمت
1 DRight-to-left text preserved
Source:Scan by Satdeep Gill / Wikimedia Commons, resized from the original PDF.CC BY-SA 4.0.
Pashto OCR converts images, scans and PDFs containing Pashto (پښتو) text into editable, searchable digital text. FastOCR reads Pashto online: upload an image with no account, or a PDF with a free account, then copy the text or download a searchable PDF. Accuracy depends on scan quality, so check the result against your original.
Try it with your Pashto document
Drop your file here
PDF, PNG, JPG, WebP, BMP, HEIC
PDF up to 1 GB · images up to 20 MB
Tips for a clear photo
- Lay the page flat.
- Use even light, with no shadows.
- Turn off the flash to avoid glare.
- Fill the frame with the page.
What is Pashto OCR & Developer API?
Developer API docs →Pashto OCR is the automated process of converting scanned multi-page PDFs up to 1GB and documents into editable, searchable Pashto text while preserving right-to-left reading order, connected script, and diacritics. FastOCR reads printed text in this script and generates full-text searchable PDFs with selectable text overlays. For engineering teams building RAG pipelines, vector search databases, or automated document ingestion, FastOCR also provides a Pashto OCR REST API at api.fastocr.org with 20 free pages a month for every signed-in account. The API accepts PDF files up to 1 GiB, and PNG, JPG, JPEG, GIF, WebP and BMP images up to 20 MiB. An image counts as one page.
Extended Arabic script support
Full recognition of specific Pashto letters like ټ, ڼ, ړ, ږ, ښ, ې, ۍ.
RTL layout engine
Native right-to-left text ordering and line assembly.
Calligraphic & print fonts
Handles Naskh, Nastaliq, and digital Pashto typography.
Searchable PDF output
Creates PDFs with invisible text layer for full-text search.
Translate after extraction
Extract Pashto text and translate to English, Dari, or 100+ languages.
Why Pashto OCR Is Challenging
- Recognizing unique Pashto letters with dot modifiers (ښ, ږ, ړ, ڼ, ټ)
- Handling right-to-left cursive script connections in varying print qualities
- Processing mixed Pashto and Dari/Persian or Urdu documents
How to Extract Pashto Text from a PDF & Images
- Go to fastocr.org
- Upload your Pashto image or PDF. Language is detected automatically.
- Wait for processing — images take seconds, PDFs show a progress bar.
- Download results: searchable PDF, raw text file, or copy text directly.
Tips for Better Pashto OCR Accuracy
- Scan at 300+ DPI to preserve fine dot accents above and below Pashto characters
- Ensure pages are properly oriented upright for correct RTL line flow
Common Use Cases for Pashto OCR
- Digitizing Pashto news articles, literature, and educational material
- Extracting text from legal documents, land deeds, and administrative records
- Processing official correspondence and identity papers in Pashto
FastOCR vs Standard OCR Apps for Pashto
| Capability | FastOCR Dedicated Cloud AI | Standard Online OCR Tools |
|---|---|---|
| Pashto Script Recognition | ✅ Full native cloud recognition for Pashto (Nastaliq & Naskh cursive ligatures) | ❌ Most online tools do not support Urdu or Arabic at all |
| Right-to-Left (RTL) Layout Flow | ✅ Preserves proper bidirectional RTL reading order | ❌ Scrambles character order backwards (left-to-right) |
| Searchable PDF Output | ✅ Dual-layer searchable PDF with coordinate-aligned text overlay | Plain unformatted text dump only or unsupported |
| Instant Web Access | ✅ Zero software installation (runs in mobile & desktop browser) | Requires local CLI libraries or complex desktop setup |
Frequently Asked Questions
Does Pashto OCR handle all unique Pashto letters correctly?
Yes. FastOCR supports all unique Pashto characters including ټ, ڼ, ړ, ږ, ښ, ې, and ۍ with native RTL layout preservation.
Is Pashto OCR free?
Image OCR is free without registration. PDF processing requires a free account.
Dedicated Pashto Tools
Explore Specialized OCR Workflows
FastOCR provides dedicated AI text recognition engines optimized for complex document types and formats:
Free for images. No registration required.
Related Articles & Resources
Free Pashto OCR
Upload & Extract TextLast updated: July 24, 2026