Supported Entity Types

When using Deepgram's hosted pre-recorded product, our redaction functionality can redact over 50 unique entity types. The complete inventory of supported entity types is listed in the charts below, divided into three groups: PII (Personally Identifiable Information), PHI (Protected Health Information), and PCI (Payment Card Industry).

Note that some entities, such as name and location, also have subtypes. For instance, location_city is a subtype of location. This means that, in a phrase such as I live in Boston, the location name Boston will be detected as both location and location_city, with the more specific label (in this case, location_city) appearing in the output. Other entity types are groupings of related categories. For example, healthcare_number captures health plan beneficiary numbers and medical record numbers, both of which are outlined as identifiers in the HIPAA Safe Harbor provision. Similarly, numerical_pii covers a broad range of entity types such as MAC addresses and cookie IDs.

While entity types have English names, international variants are also redacted. For example, ssn covers American Social Security Numbers, as well as many equivalent identification numbers used in different regions worldwide, such as the Canadian Social Insurance Number or the German Sozialversicherungsnummer.

Individual entity classes can be redacted with redact=entity_class.

🚧

This functionality is only available for Deepgram's hosted and pre-recorded transcription product. When using Deepgram's on-prem offering or live streaming product, only the basic Redaction functionality is available.

PII (Personally Identifiable Information)

To redact all PII, set redact=pii. Individual classes of PII can be redacted with redact=entity_class.

Label Description Regulatory Compliance
account_number Customer account or membership identification number
age Numbers associated with an individual’s age GDPR, HIPAA, Quebec Privacy Act, APPI
date Specific calendar dates, which can include days of the week, dates, months, or years HIPAA, Quebec Privacy Act
date_interval Broader time periods, including date ranges, months, seasons, years, and decades HIPAA
dob Dates of birth.
See also: DATE, DATE_INTERVAL
CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
driver_license Driver's permit numbers.
See also: VEHICLE_ID
CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
duration Periods of time, specified as a number and a unit of time
email_address Email addresses CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
event Names of events or holidays
filename Names of computer files, including the extension or filepath
gender_sexuality Terms indicating gender identity or sexual orientation, including slang terms CPRA, GDPR, GDPR Sensitive, APPI Sensitive
healthcare_number Healthcare numbers and health plan beneficiary numbers CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
ip_address Internet IP address, including IPv4 and IPv6 formats CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
language Names of natural languages GDPR, GDPR Sensitive, APPI Sensitive
location Metaclass for any named location reference; See subclasses below GDPR, HIPAA, APPI
location_address Full or partial physical mailing addresses, which can include: building name or number, street, city, county, state, country, zip code CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
location_city Municipality names, including villages, towns, and cities CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
location_coordinate Geographic positions referred to using latitude, longitude, and/or elevation coordinates CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
location_country Country names GDPR, APPI
location_state State, province, territory, or prefecture names GDPR, APPI
location_zip Zip codes (including Zip+4), postcodes, or postal codes CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
marital_status Terms indicating marital status APPI Sensitive
money Names and/or amounts of currency
name Names of individuals, not including personal titles such as ‘Mrs.’ or ‘Mr.’ CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
name_family Names indicating a person’s family or community; often a last name in Western cultures and first name in Eastern cultures CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
name_given Names given to an individual, usually at birth; often first / middle names in Western cultures and middle / last names in Eastern cultures CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
name_medical_professional Full names, including professional titles and certifications, of medical professional, such as doctors and nurses CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
numerical_pii Numerical PII that doesn't fall under other categories
(e.g., medical device serial numbers, computer numbers like MAC addresses and cookie IDs)
CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
occupation Job titles or professions Quebec Privacy Act, APPI
organization Names of organizations or departments within an organization Quebec Privacy Act, APPI
organization_medical_facility Names of medical facilities, such as hospitals, clinics, pharmacies, etc. Quebec Privacy Act, APPI
origin Terms indicating nationality, ethnicity, or provenance CPRA, GDPR, GDPR Sensitive, Quebec Privacy Act, APPI Sensitive
passport_number Passport numbers, issued by any country CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
password Account passwords, PINs, access keys, or verification answers CPRA, APPI
phone_number Telephone or fax numbers CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
physical_attribute Distinctive bodily attributes, including terms indicating race CPRA, GDPR, GDPR Sensitive, APPI Sensitive
political_affiliation Terms referring to a political party, movement, or ideology CPRA, GDPR, GDPR Sensitive, Quebec Privacy Act, APPI Sensitive
religion Terms indicating religious affiliation CPRA, GDPR, GDPR Sensitive, Quebec Privacy Act, APPI Sensitive
ssn Social Security Numbers or international equivalent government identification numbers CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
time Expressions indicating clock times
url Internet addresses CPRA, GDPR, HIPAA, Quebec Privacy Act
username Usernames, login names, or handles CPRA, GDPR, APPI
vehicle_id Vehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers CPRA, GDPR, HIPAA, APPI
zodiac_sign Names of Zodiac signs

PHI (Protected Health Information)

Label Description Regulatory Compliance
blood_type Blood types CPRA, GDPR, HIPAA, Quebec Privacy Act
condition Names of medical conditions, diseases, syndromes, deficits, disorders CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI Sensitive
dose Medically prescribed quantity of a medication
drug Medications, vitamins, and supplements CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI Sensitive
injury Bodily injuries, including mutations, miscarriages, and dislocations CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI Sensitive
medical_process Medical processes, including treatments, procedures, and tests CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI Sensitive
statistics Medical statistics HIPAA, Quebec Privacy Act

PCI (Payment Card Industry)

To redact all PCI, set redact=pci. Individual classes of PCI can be redacted with redact=entity_class.

Label Description Regulatory Compliance
credit_card Credit card numbers CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
credit_card_expiration Expiration date of a credit card CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI
cvv 3- or 4-digit card verification codes and equivalents CPRA, GDPR, HIPAA, Quebec Privacy Act, APPI