Remove phone numbers from text
Phone numbers are written a dozen ways in the same document — (415) 555-2671, 415.555.2671, +44 20 7946 0958, 4155552671. This page detects all of those and maps every formatting of the same number onto one placeholder.
Only the phone detector is active here, so names, emails and everything else are left exactly as you pasted them.
Your text
Safe to paste
Preset: phone numbers only.
Mapping — 0 values (only visible in this tab)
| Placeholder | Real value | Uses |
|---|
Check a few rows before you paste — this is the fastest way to spot a detector that grabbed the wrong thing. Nothing here is stored or sent anywhere.
What to look for — 30 detectors, custom terms, exceptions
People & organisations
Government & health IDs
Financial
Technical & secrets
Location
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
- Open this page — the detectors are already set for “Remove phone numbers”.
- Paste your text, or drop a .txt, .md, .csv, .json or .log file onto the panel.
- Check the highlights: every match is coloured by type, and one click keeps a type as-is.
- Copy the safe version and paste it into the AI tool of your choice.
- Paste the model’s reply back into step 3 to restore the real values.
The formatting problem
A find-and-replace on a phone number finds one spelling of it. The detector here works the other way round: it looks for digit groups in phone-like shapes, then checks the digit count (10 to 15, covering NANP through international numbers) and rejects anything sitting inside a longer run of digits, which is how card numbers and order IDs avoid being mistaken for phone numbers.
Because comparison happens on the digits alone, (415) 555-2671 and 415-555-2671 collapse onto the same placeholder — so a model reading the scrubbed text can still tell it is one number written twice.
One deliberate exclusion
Dates that look like grouped numbers (2026-07-29) are skipped, because dates belong to their own detectors and being aggressive here would make ordinary business text unreadable.
The reverse case is worth knowing too: a valid UK NHS number is ten digits and can look exactly like a US phone number. That is why NHS detection is off by default site-wide, and why you should not rely on the phone detector to catch health identifiers.
Tips
- Extensions (“ext 214”) are captured as part of the number.
- If your text has serial numbers being caught as phones, add them to the “never redact” list.
- Use the fake-values style to get numbers from the 555-0100 to 555-0199 block, which NANPA reserves for fiction — nothing you paste can dial a real person.
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 work for numbers outside the US?
Yes, for the common international patterns: a leading + and country code, followed by grouped digits, up to fifteen digits total (the E.164 maximum). Numbers written without a country code and without separators are only caught at ten digits, which is the NANP length.
Will it redact prices, dates or reference numbers?
It should not. Anything under ten digits or over fifteen is ignored, digit runs inside longer numbers are skipped, and ISO-style dates are excluded. If something slips through, switch it back with the “never redact” list.
Does the tool look numbers up anywhere?
No. There is no carrier lookup, no validation service, no network request at all — everything is pattern matching in your browser.