PII Redactor
Detect and redact personally identifiable information from text, transcripts, and OCR output
Input
Enter the text you want to process
Whether to redact PII values or just detect them. Default: true
Types of PII to detect. Default: email,phone,name,ssn,location
How to redact PII values. Default: label
Enable LLM-based fallback detection for ambiguous cases. Default: false
Maintain original string formatting using format-preserving techniques. Default: false
Generate a hashed log of detected PII values for audit purposes. Default: false
Include the unredacted version in the output for internal use. Default: false
Language code of the input (ISO format). Default: en
Output
{
"pii": {
"detected": [
{
"type": "email",
"value": "[email protected]",
"start": 15,
"end": 36,
"confidence": 0.98
},
{
"type": "phone",
"value": "555-123-4567",
"start": 44,
"end": 56,
"confidence": 0.95
}
],
"redacted_text": "Please contact [REDACTED:EMAIL] or call [REDACTED:PHONE].",
"original_text": "Please contact [email protected] or call 555-123-4567.",
"hash_log": {
"[email protected]": "9e107d9d372bb6826bd81d3542a419d6",
"555-123-4567": "e4d909c290d0fb1ca068ffaddf22cbd0"
}
},
"metadata": {
"input_length": 128,
"language": "en",
"timestamp": "2025-05-24T23:45:00Z"
}
}Ready to run PII Redactor on your data? Spin it up in Studio — no infra to host.
Run this in StudioAlready have embeddings? Skip extraction — search your own vectors with MVS, from $25/mo for up to 1M vectors.
Try MVS →