15 Languages Supported

Full PII detection across 15 languages with native NLP models. Process documents in English, German, Spanish, French, and 11 more languages—including RTL support for Arabic.

Supported Languages

en
English
English
spaCy NLP
de
German
Deutsch
spaCy NLP
es
Spanish
Español
spaCy NLP
fr
French
Français
spaCy NLP
it
Italian
Italiano
spaCy NLP
pt
Portuguese
Português
spaCy NLP
nl
Dutch
Nederlands
spaCy NLP
pl
Polish
Polski
spaCy NLP
ru
Russian
Русский
spaCy NLP
ja
Japanese
日本語
spaCy NLP
zh
Chinese
中文
spaCy NLP
ko
Korean
한국어
spaCy NLP
arRTL
Arabic
العربية
Transformer
hi
Hindi
हिन्दी
Transformer
tr
Turkish
Türkçe
Transformer

Language Features

Auto-Detection

Our system automatically detects the language of your document and applies the appropriate NLP models for optimal detection.

  • No manual selection needed
  • Mixed-language support

RTL Support

Full right-to-left text support for Arabic, ensuring proper detection and display of PII in RTL documents.

  • Arabic language support
  • Proper text direction

Lazy Loading

Language models are loaded on-demand for memory efficiency. English is preloaded; others load when first requested.

  • Memory efficient
  • Fast startup time

Country-Specific Formats

Beyond language support, we detect country-specific ID formats and patterns for comprehensive PII coverage.

European Formats

  • German Personalausweis
  • UK National Insurance Number
  • Spanish DNI/NIE
  • Italian Codice Fiscale
  • French INSEE Number
  • Dutch BSN

Global Formats

  • US Social Security Number
  • IBAN (all countries)
  • International phone formats
  • Passport numbers
  • VAT numbers
  • Credit card formats

Process Documents in Any Language

Start with 300 free tokens per month. All 15 languages included.

Create Free Account