Native Spanish PII detection with support for Spain and Latin American variants. Recognize regional identifiers (DNI, CURP, RUT), cultural naming patterns, and Spanish-specific data formats.
Native Spanish understanding
Spanish-trained NLP models for name, address, and entity recognition with regional variant support.
Detect DNI (Spain), CURP/RFC (Mexico), RUT (Chile), CUIT (Argentina), and other country-specific IDs.
Understand two-surname convention, compound names, and cultural naming patterns across regions.
Recognize Spanish address conventions including street types (Calle, Avenida) and postal codes by country.
Detect phone numbers for Spain and Latin American countries with proper country code handling.
Support for Spain plus 19 Latin American Spanish-speaking countries with regional customization.
Simple integration, powerful results
Send your documents, text, or files through our secure API endpoint or web interface.
Our AI analyzes content to identify all sensitive information types with 99.7% accuracy.
Sensitive data is automatically redacted based on your configured compliance rules.
Receive your redacted content with full audit trail and compliance documentation.
Get started with just a few lines of code
import requests
api_key = "your_api_key"
url = "https://api.redactionapi.net/v1/redact"
data = {
"text": "John Smith's SSN is 123-45-6789",
"redaction_types": ["ssn", "person_name"],
"output_format": "redacted"
}
response = requests.post(url,
headers={"Authorization": f"Bearer {api_key}"},
json=data
)
print(response.json())
# Output: {"redacted_text": "[PERSON_NAME]'s SSN is [SSN_REDACTED]"}
const axios = require('axios');
const apiKey = 'your_api_key';
const url = 'https://api.redactionapi.net/v1/redact';
const data = {
text: "John Smith's SSN is 123-45-6789",
redaction_types: ["ssn", "person_name"],
output_format: "redacted"
};
axios.post(url, data, {
headers: { 'Authorization': `Bearer ${apiKey}` }
})
.then(response => {
console.log(response.data);
// Output: {"redacted_text": "[PERSON_NAME]'s SSN is [SSN_REDACTED]"}
});
curl -X POST https://api.redactionapi.net/v1/redact \
-H "Authorization: Bearer your_api_key" \
-H "Content-Type: application/json" \
-d '{
"text": "John Smith's SSN is 123-45-6789",
"redaction_types": ["ssn", "person_name"],
"output_format": "redacted"
}'
# Response:
# {"redacted_text": "[PERSON_NAME]'s SSN is [SSN_REDACTED]"}
Spanish is the world's fourth most spoken language, with over 500 million speakers across Spain, Latin America, and significant populations in the United States and elsewhere. Organizations operating in Spanish-speaking markets handle vast amounts of Spanish-language data requiring privacy protection—customer records, correspondence, legal documents, healthcare records, and more. Effective Spanish data protection requires native language understanding, not translated English patterns.
Our Spanish language processing goes beyond simple translation of detection rules. Spanish-trained NLP models understand the language's unique characteristics: two-surname naming conventions, regional vocabulary differences, country-specific identifiers, and address formats that vary across the Spanish-speaking world. This enables accurate PII detection across Spain, Mexico, Argentina, Colombia, and all other Spanish-speaking nations.
Spanish naming conventions present unique challenges for PII detection systems designed primarily for English patterns:
Two Surnames: The traditional Spanish naming system includes two surnames—paternal (from father) followed by maternal (from mother). "María García López" has first name "María," paternal surname "García," and maternal surname "López." Both surnames should be detected as part of the full name.
Compound First Names: Compound names like "María del Carmen," "José Luis," or "Juan Carlos" are single first names, not first and middle names. Detection must recognize these as unified name elements.
Name Particles: Particles like "de," "del," "de la," and "de los" connect name elements (e.g., "Luis de la Cruz"). These particles are part of the surname and should be included in detection.
Regional Variations: Naming practices vary by country. Some Latin American countries increasingly use single surnames. Spain maintains the traditional two-surname system with recent legal changes allowing parental choice of surname order.
Common Names: Spanish has highly frequent given names (José, María, Juan, Ana) and surnames (García, Rodríguez, Martínez). Context analysis helps distinguish common names from other text occurrences.
Each Spanish-speaking country maintains unique national identifier systems requiring specific detection rules:
Spain - DNI/NIE: The Documento Nacional de Identidad (DNI) is issued to Spanish citizens with format 8 digits + 1 letter (e.g., 12345678Z). The Número de Identidad de Extranjero (NIE) for foreign residents uses format X/Y/Z + 7 digits + letter. The final letter is a check digit calculated from the number.
Mexico - CURP/RFC: The Clave Única de Registro de Población (CURP) is an 18-character identifier encoding personal information: 4 letters from name + 6 digits (birth date) + gender + 2 letters (state) + 3 letters (disambiguation) + 1 check digit. The Registro Federal de Contribuyentes (RFC) for tax purposes uses a similar structure.
Chile - RUT/RUN: The Rol Único Tributario (RUT) identifies all persons and entities for tax purposes. Format: 7-8 digits + check digit (0-9 or K). The Rol Único Nacional (RUN) for individuals uses the same format.
Argentina - CUIT/CUIL: The Clave Única de Identificación Tributaria (CUIT) for businesses and Código Único de Identificación Laboral (CUIL) for individuals use format: 2 digits (type) + 8 digits (ID) + 1 check digit.
Colombia - Cédula: The Cédula de Ciudadanía for nationals and Cédula de Extranjería for foreigners. Numerical format varies by generation with 8-10 digits.
Spanish address formats differ significantly from English conventions and vary by country:
Spain Addresses: Spanish addresses typically list street type and name first, then number: "Calle Mayor, 25, 3º B, 28013 Madrid." Common street type abbreviations include C/ (Calle), Avda. (Avenida), Pza. (Plaza), Pº (Paseo). Floor indicators use ordinal numbers (3º) with optional door letters (B).
Latin American Variations: Each country has conventions: Mexican addresses often include colonia (neighborhood) names. Argentine addresses may use "altura" for street numbers. Colombian addresses use coordinate systems in some cities (Calle 45 # 23-15).
Postal Codes: Formats vary: Spain uses 5-digit codes (28013), Mexico uses 5 digits (06600), Argentina uses 4-digit codes or 8-character alphanumeric (C1425ABC). We validate codes against known ranges.
Spanish phone number formats vary by country:
Spain: 9-digit numbers starting with 6 or 7 for mobile, 8 or 9 for landline. International format: +34 XXX XXX XXX.
Mexico: 10-digit numbers with 2 or 3 digit area codes. Mobile numbers require "044" or "045" prefixes domestically. International format: +52 XX XXXX XXXX.
Argentina: 10-digit numbers with varying area code lengths. "15" prefix for mobile when dialing locally. International format: +54 9 XX XXXX XXXX (mobile includes "9" after country code).
We detect all major Spanish-speaking country phone formats with proper international code handling (+34, +52, +54, +57, +56, etc.).
Spanish varies significantly across regions, affecting vocabulary and detection patterns:
Vocabulary Differences: Words for common items vary (coche/carro/auto for car, ordenador/computadora for computer). Our models recognize regional vocabulary in context.
Pronoun Systems: Spain uses "vosotros" (you plural informal) while Latin America uses "ustedes." Argentine Spanish uses "vos" instead of "tú." These grammatical differences affect named entity recognition.
Spelling Conventions: Some variations in spelling and accent usage exist between regions. Our processing handles these variations.
Spanish-language financial data has specific patterns:
Currency Formats: Euro (€) in Spain, Peso ($) in Mexico/Argentina/Colombia, and various other currencies. Decimal notation uses comma (1.234,56) in Spain and some countries, period (1,234.56) in others.
Bank Identifiers: Spain uses IBAN format ES + 2 check + 20 digits. Latin American countries have their own bank account formats—Mexican CLABE (18 digits), Argentine CBU (22 digits), etc.
Tax Identifiers: RFC in Mexico, RUT in Chile, CUIT in Argentina, and NIF in Spain all require specific format recognition beyond the national ID numbers.
The United States has over 60 million Hispanic residents, creating unique data protection needs:
Bilingual Documents: Documents mixing Spanish and English are common in healthcare, legal, financial, and government contexts. Our detection handles code-switching within documents.
Dual Naming Systems: US Hispanics may use both Spanish (two surnames) and English (middle name) naming conventions in different contexts. Detection handles both patterns.
US + Origin Country IDs: Records may contain both US identifiers (SSN, driver's license) and origin country identifiers (CURP from Mexico, DNI from home country).
Spanish-language data protection intersects with multiple regulatory frameworks:
Spain/EU: GDPR applies fully to Spain, with LOPDGDD (Ley Orgánica de Protección de Datos) providing Spanish implementation. DNI numbers are considered high-sensitivity identifiers.
Mexico: LFPDPPP (Ley Federal de Protección de Datos Personales en Posesión de los Particulares) governs private sector data protection with ARCO rights (Acceso, Rectificación, Cancelación, Oposición).
Argentina: Law 25,326 on Personal Data Protection provides comprehensive privacy rights. Argentina has EU adequacy status for data transfers.
Other Countries: Colombia, Chile, Peru, and other countries have enacted data protection legislation with varying requirements.
Spanish language processing serves diverse industry needs:
Healthcare: Spanish-speaking patient populations require Spanish-language medical records, consent forms, and communications. Proper handling of medical terminology and abbreviations in Spanish context.
Financial Services: Banks serving Hispanic markets handle Spanish-language applications, correspondence, and records. Cross-border operations between US and Latin America require multi-country support.
Legal: Immigration law firms, international litigation, and Hispanic-serving legal practices process Spanish documents requiring careful redaction.
Call Centers: Customer service operations in Spanish generate transcripts and records requiring PII protection.
RedactionAPI has transformed our document processing workflow. We've reduced manual redaction time by 95% while achieving better accuracy than our previous manual process.
The API integration was seamless. Within a week, we had automated redaction running across all our customer support channels, ensuring GDPR compliance effortlessly.
We process over 50,000 legal documents monthly. RedactionAPI handles it all with incredible accuracy and speed. It's become an essential part of our legal tech stack.
The multi-language support is outstanding. We operate in 30 countries and RedactionAPI handles all our documents regardless of language with consistent accuracy.
Trusted by 500+ enterprises worldwide





Spanish typically uses two surnames (paternal + maternal): "María García López". Our NLP understands this structure, detecting both surnames as part of the name. We also handle compound first names (María del Carmen), name particles (de, del, de la), and regional variations.
We detect major national identifiers: DNI/NIE (Spain), CURP/RFC (Mexico), RUT/RUN (Chile), CUIT/CUIL (Argentina), CPF (Brazil for Portuguese), Cédula numbers (Colombia, Ecuador, etc.), and other country-specific identifiers with format validation.
Yes, we recognize regional differences in vocabulary (coche vs. carro), spelling conventions, address formats, and identifier types. You can configure for specific regions or use broad Spanish coverage.
Spanish addresses use conventions like "Calle Mayor, 25, 3º B" with abbreviations (C/, Avda., Pza.), floor indicators (3º), and door letters. Latin American addresses vary by country—we support each country's format.
Full support for Spanish diacritics (á, é, í, ó, ú, ü, ñ). Detection works correctly regardless of whether text uses proper accents. Names like "José" and "Jose" are both recognized.
Yes, our detection handles code-switching and bilingual documents common in US Hispanic communities and international business. Both Spanish and English PII patterns are detected regardless of language mixing.