PII Pseudonymizer
Detect and pseudonymize personally identifiable information (PII) in your text automatically.
Original Text
Output format
Placeholders for documents and data you pass on. Stand-in names when the text should stay readable, for example for a language model.
Pseudonymized Text
💡 Tip: You can edit the text, for example paste a language model's answer, and then click “Get real values back”. This works in both forms until 30 minutes after its last use, at the latest 8 hours after its first use.
Statistics
Entities found
0
Text reduction
0%
Detected Entities
The two output modes in detail
You choose how values are replaced. Detection is the same either way. Use placeholders for documents and for data you pass on. Use stand-in names when the text should stay readable.
Original: Carola Wendt works at Holzbau Brenner GmbH, carola.wendt@example.org.
With placeholders
Every detected value is replaced by a placeholder: the kind of value in capitals, then eight characters as an identifier, all in square brackets.
[PERSON:5c868a01] works at [ORGANISATION:3c2a1679], [EMAIL:2aa30689].
Typical use case: Documents, handing data to other programs, API integrations. A placeholder is recognisable as replaced at once and can be mapped back by a program.
With stand-in names
Names, companies, addresses and numbers are replaced by made-up values. Within one session the same value always gets the same stand-in.
Kurt Rother works at Pfeiffer Cronjäger Vokuhl, carlyn@cormier.test.
Typical use case: Texts that should stay readable, for example for a language model (ChatGPT, Claude, Gemini). A stand-in name looks like a real name: whoever reads the text cannot see what was replaced.
Both modes via API: Set the query parameter in your API call
?marker_format=tagged
or
?marker_format=faker.
We do not store your text. The mapping stays until 30 minutes after its last use, at the latest 8 hours after its first use, so you can get the real values back.
