Detect and redact physical addresses in formats from 150+ countries. Street addresses, cities, states, postal codes, and geographic identifiers with intelligent parsing.
Understanding addresses worldwide
Recognize address formats from 150+ countries including US, UK, EU, Asian, and Latin American patterns.
Identify individual components: street number, street name, unit, city, state/province, postal code, country.
AI distinguishes addresses from similar text patterns through contextual analysis and format validation.
Full address redaction, preserve city/state only, ZIP code handling per HIPAA rules, or custom patterns.
Validate postal codes against country formats. HIPAA-compliant ZIP handling (first 3 digits rules).
Handle addresses spanning multiple lines, embedded in paragraphs, or in structured form fields.
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]"}
Physical addresses reveal where people live, work, and conduct their daily activities. This location information is among the most sensitive personal data, enabling everything from targeted marketing to stalking and harassment. Under privacy regulations worldwide, addresses qualify as personal data requiring protection, making accurate address detection and redaction essential for compliance.
Address detection presents unique challenges due to the extraordinary variety of formats used globally. US addresses follow different conventions than UK addresses, which differ from German, Japanese, or Brazilian formats. Even within a single country, addresses may be written in multiple valid formats. Effective detection must handle this diversity while avoiding false positives from text that merely resembles addresses.
Address formats vary significantly across countries and regions. Our system understands these variations:
United States: Street number + street name + unit, city, state abbreviation, ZIP code (12345 or 12345-6789). Common variations include directionals (N, S, E, W), street type abbreviations (St, Ave, Blvd), and unit designators (Apt, Suite, #).
United Kingdom: Building number/name + street, locality, post town, postcode (format: A9 9AA, A99 9AA, AA9 9AA, etc.). UK addresses often include building names and may span 5-7 lines.
Germany: Street name + number (reversed from US), postal code + city. German postal codes are 5 digits. Street names may include compound words.
Japan: Prefecture, city, ward, district, block, building - written largest to smallest (opposite of Western convention). May be written in kanji, hiragana, or romanized.
HIPAA Safe Harbor has specific rules for geographic data. All geographic subdivisions smaller than a state must be removed, with special handling for ZIP codes. The first three digits of a ZIP code may be retained only if the geographic unit contains more than 20,000 people according to census data. Our system implements these rules automatically, referencing current census population data.
Different use cases require different levels of address redaction. Full redaction removes the entire address. Partial redaction might preserve city and state for geographic analysis while removing street-level details. Our component parsing enables granular control over what's redacted and what's preserved.
Real-world addresses include many variations beyond standard formats: PO Boxes, rural routes, military addresses (APO/FPO/DPO), university addresses with building codes, business addresses with attention lines, and addresses in developing countries with informal systems. Our detection handles these edge cases while maintaining accuracy.
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





We support address formats from 150+ countries including US (123 Main St, City, ST 12345), UK (123 High Street, London, SW1A 1AA), European formats, Asian formats (which often reverse order), Latin American formats, and more. Our parser adapts to each country's conventions.
HIPAA Safe Harbor allows retaining the first 3 digits of a ZIP code only if the geographic unit contains more than 20,000 people. We implement these rules automatically - ZIP codes in low-population areas are fully redacted while others can show the first 3 digits.
Yes, we parse addresses into components: street number, street name, unit/apartment, city, state/province, postal code, and country. This enables granular redaction - you might redact street details while preserving city/state for geographic analysis.
Our AI identifies addresses embedded in paragraphs, not just structured fields. Contextual clues like "lives at," "located at," "send to," and address-like patterns help identify addresses within narrative text.
We detect PO Boxes, military addresses (APO/FPO), rural routes, highway contract routes, and other non-standard formats. International variations like "care of" addresses and attention lines are also recognized.
Optional address validation can verify addresses against postal databases for supported countries. This confirms the address is real and helps distinguish valid addresses from false positives. Validation is available as an add-on service.