What is PII Redaction?
PII redaction automatically detects and removes sensitive information from both transcripts and audio recordings. This ensures compliance with privacy and security requirements while maintaining the overall context of conversations.Example
Original:How It Works
- Transcript Redaction
- Audio Redaction
We identify the entities to be redacted from the call using state of the art models. We then replace the text with relevant placeholders.Example tokens:
<PERSON>- Person names<LOCATION>- Geographic locations<EMAIL>- Email addresses<PHONE>- Phone numbers<SSN>- Social Security Numbers<CREDIT_CARD>- Credit card numbers
Using Redaction
Add theredact_fields parameter when sending calls to the observe API endpoint:
If
redact_fields is not provided or is an empty array, no redaction will occur.Available Fields
person_name- Person namesage- Age informationphone_number- Phone numbersemail_address- Email addressesdate- Specific datestime- Time informationlocation- Physical locations and addressesorigin- Origin informationgender_sexuality- Gender and sexuality informationphysical_attribute- Physical descriptionsoccupation- Occupation detailsusername- Usernamespassword- Passwordsip_address- IP addressesurl- URLsfilename- File namesevent- Event informationvehicle_id- Vehicle identification numbersdob- Date of birthhealthcare_number- Healthcare identification numbersmedical_professional- Medical professional informationcredit_card- Credit card numbersaccount_number- General account numbersbank_account- Bank account numbersmoney- Financial amountsssn- Social Security Numberspassport_number- Passport numbersdriver_license- Driver’s license numbersnumerical_pii- Other numerical PII
Pricing
Redacting any fields costs 0.4 credits per minute, regardless of how many fields are selected.