Remove street addresses from text

A home address is the identifier people most regret sharing, and it is the one most likely to be sitting in a document you were about to paste into a chatbot — on an invoice, a delivery note, a CV, a rental application.

This page detects addresses as whole units: house number, street name and type, optional unit or suite, and the city, state and postcode that follow. Standalone US state + ZIP pairs and UK postcodes are caught separately.

Replace with
network while you type: 0 requests

Your text

0 characters

Safe to paste

waiting for text
The cleaned version appears here as you type — highlighted so you can see exactly what changed.
CtrlEnter
no personal data yet Everything below happens in this browser tab. Nothing is uploaded, and nothing you type is saved.

    Preset: street addresses, postcodes and GPS coordinates.

    What to look for — 30 detectors, custom terms, exceptions

    People & organisations

    Government & health IDs

    Financial

    Technical & secrets

    Location

    For the things no word list can know: internal codenames, unusual surnames, a product that isn’t public yet. Custom terms are never saved.
    Values on this list stay in the text and out of the mapping — useful when the model needs your own company name to answer usefully.
    Step 3 — paste the AI’s answer here to put the real values back

    The model replies using the placeholders. Paste its answer below and every [NAME_1] becomes the real name again — using the mapping held in this tab, which is the only copy that exists.

    How it works

    1. Open this page — the detectors are already set for “Remove addresses”.
    2. Paste your text, or drop a .txt, .md, .csv, .json or .log file onto the panel.
    3. Check the highlights: every match is coloured by type, and one click keeps a type as-is.
    4. Copy the safe version and paste it into the AI tool of your choice.
    5. Paste the model’s reply back into step 3 to restore the real values.

    Matching an address without matching every sentence

    The pattern requires a leading house number, at least one capitalised word, and a street type from a fixed list — Street, Avenue, Road, Boulevard, Lane, Drive, Court, Circle, Place, Terrace, Trail, Parkway, Highway, Way, Square and their abbreviations. Requiring the capitalised word is what stops “2 hours drive” and “3 days on the way” from being read as addresses.

    When a city, state and ZIP follow the street line, they are absorbed into the same match, so the whole address becomes one placeholder instead of three fragments. Coordinates are matched separately, at four or more decimal places — the precision that pins a building rather than a city.

    Why geography is so identifying

    HIPAA Safe Harbor does not just remove street addresses: it removes every geographic subdivision smaller than a state, and only allows the first three digits of a ZIP code when the area they cover holds more than 20,000 people. That threshold exists because location narrows a population fast — combined with a birth date and a gender, a fine-grained location has been shown in published studies to identify a large share of people uniquely.

    The same logic applies outside healthcare. If you scrub the name but leave the address, you have not de-identified anything: you have simply moved the identifier one field to the right.

    Tips

    Detectors are pattern-based and imperfect: read the highlighted output before you paste it anywhere, and confirm your own confidentiality obligations against the current rules for your profession, employer or jurisdiction. Compiled 2026-07-29.

    Frequently asked questions

    Does it detect addresses without a house number?

    No. “Market Street, Philadelphia” alone is indistinguishable from ordinary prose about a street, so a leading number is required. Add such lines to custom terms if they matter in your document.

    What about international postcodes?

    US ZIP and ZIP+4 (when preceded by a state code) and UK postcodes are detected. Canadian, Indian, Australian and European formats are not yet covered — the UK format is distinctive enough to match safely, while several others collide with ordinary numbers.

    Is the address looked up or geocoded?

    Never. There is no maps API, no geocoding, no network request. That would send the exact data you are trying to protect to a third party.