PII Detection in 23 European Languages
PII detection across 23 European languages
PrivacyPromptAI supports 23 European languages, detecting and redacting PII in each with high accuracy. Our pattern recognition adapts to language-specific naming conventions, address formats, and phone number patterns.
Supported Languages
Active language: English
— Click any language below to change it
🇬🇧
English
English
🇩🇪
German
Deutsch
🇫🇷
French
Français
🇪🇸
Spanish
Español
🇮🇹
Italian
Italiano
🇵🇹
Portuguese
Português
🇳🇱
Dutch
Nederlands
🇸🇪
Swedish
Svenska
🇩🇰
Danish
Dansk
🇫🇮
Finnish
Suomi
🇳🇴
Norwegian
Norsk
🇵🇱
Polish
Polski
🇨🇿
Czech
Čeština
🇬🇷
Greek
Ελληνικά
🇭🇺
Hungarian
Magyar
🇷🇴
Romanian
Română
🇧🇬
Bulgarian
Български
🇭🇷
Croatian
Hrvatski
🇸🇰
Slovak
Slovenčina
🇸🇮
Slovenian
Slovenščina
🇪🇪
Estonian
Eesti
🇱🇻
Latvian
Latviešu
🇱🇹
Lithuanian
Lietuvių
Language-Specific Features
Our PII detection adapts to each language:
- Name Patterns: Recognizes language-specific name structures (e.g., Hungarian surname-first, Spanish double surnames)
- Phone Numbers: Handles country-specific formats (+33 for France, +49 for Germany, etc.)
- Addresses: Understands postal code formats and address ordering per country
- National IDs: Detects country-specific ID formats (NIE in Spain, BSN in Netherlands, etc.)
- Special Characters: Properly handles diacritics (ñ, ü, ø, ł, etc.)
Automatic Language Detection
PrivacyPromptAI automatically detects the language of your document. No manual selection needed!
You can also process multilingual documents — the tool will detect PII regardless of language mixing.
Don't See Your Language?
We're continuously expanding language support. Request your language!
Request LanguageFrequently Asked Questions — Language Support
Yes. The detection engine applies all 23 language pattern sets simultaneously, so a document containing English names, German phone numbers and French addresses will have all three types detected correctly. You can also manually select a primary language in the dropdown to prioritise country-specific patterns for ambiguous cases like national ID formats.
Selecting your document's primary language improves detection of country-specific patterns — for example, Romanian CNP numbers, UK National Insurance Numbers, or Polish PESEL codes. Universal patterns like email addresses, IBANs and credit cards are detected regardless of language setting. For best results, select the language that matches the nationality conventions in your document.
Yes. Language support is expanded based on user demand. If you need a language not currently in our list of 23, please contact us → with the language name and any specific PII patterns your use case requires (ID formats, phone number conventions, postcode structure). We prioritise requests with clear use cases.
Yes. Greek and Bulgarian are both supported, including name detection using Cyrillic and Greek character sets. The NER engine handles Unicode character ranges across all supported scripts. Postcodes, phone numbers and national IDs for both countries are also detected. See the full features list → for details.
The NER engine adapts to cultural name conventions. Hungarian documents use surname-first ordering (e.g. "Kovács János"); Spanish and Portuguese names often include two surnames (e.g. "García López"). The engine is trained on multilingual corpora that reflect these variations. Selecting the correct primary language in the dropdown improves detection for names that follow less common ordering conventions. When in doubt for cross-cultural documents, always review the redacted output to catch any edge cases the engine may not handle perfectly.
Pattern-based detection (emails, IBANs, phone numbers, IP addresses) is equally accurate across all 23 languages because it does not depend on linguistic training data. Named Entity Recognition quality is generally stronger for major languages (English, German, French, Spanish) where larger training corpora exist, and slightly lower for smaller EU languages (Maltese is not supported; Estonian, Latvian and Lithuanian may see lower name recall). For all languages, universal identifiers are caught reliably. Contact us → if you need higher accuracy for a specific language.
Yes. Changing the language in the dropdown updates the detection settings for the next redaction run — it does not erase or modify any text already in the tool. Your redacted output and original input text remain in place until you clear them. This means you can process a document in one language, switch to another, and run a second redaction pass — useful for multilingual documents where you want to optimise detection for two language sets separately. Your language preference is also saved to localStorage so it persists across sessions.
Related Resources