Skip to main content

PII Redaction

The PII Redaction model lets you minimize sensitive information about individuals by automatically identifying and removing it from your transcript.

Personal Identifiable Information (PII) is any information that can be used to identify a person, such as a name, email address, or phone number.

When you enable the PII Redaction model, your transcript will look like this:

  • With hash substitution: Hi, my name is ####!
  • With entity_name substitution: Hi, my name is [PERSON_NAME]!

You can also Create redacted audio files to replace sensitive information with a beeping sound.

Supported languages

PII Redaction is available in multiple languages. See Supported languages.

Redacted properties

PII only redacts words in the text property. Properties from other features may still include PII, such as entities from Entity Detection or summary from Summarization.

Quickstart

Enable PII Redaction by setting redact_pii to true in the transcription config.

Use redact_pii_policies to specify the information you want to redact. For the full list of policies, see PII policies.

Example output

Smoke from hundreds of wildfires in Canada is triggering air quality alerts
throughout the US. Skylines from Maine to Maryland to Minnesota are gray and
smoggy. And in some places, the air quality warnings include the warning to stay
inside. We wanted to better understand what's happening here and why, so we
called ##### #######, an ######### ######### in the ########## ## #############
###### ### ########### at ##### ####### ##########. Good morning, #########.
Good morning. So what is it about the conditions right now that have caused this
round of wildfires to affect so many people so far away? Well, there's a couple
of things. The season has been pretty dry already, and then the fact that we're
getting hit in the US. Is because there's a couple of weather systems that ...

Create redacted audio files

In addition to redacting sensitive information from the transcription text, you can also generate a version of the original audio file with the PII "beeped" out.

To create a redacted version of the audio file, use the set_redact_pii() method on the TranscriptionConfig with redact_audio to True.

Use get_redacted_audio_url() on the transcript to get the URL to the redacted audio file.

Supported languages

You can only create redacted audio files for transcriptions in English and Spanish.

Maximum audio file size

You can only create redacted versions of audio files if the original file is smaller than 1 GB.

Example output

https://s3.us-west-2.amazonaws.com/api.assembly.ai.usw2/redacted-audio/ac06721c-d1ea-41a7-95f7-a9463421e6b1.mp3?AWSAccessKeyId=...

API reference

Request

curl https://api.assemblyai.com/v2/transcript \
--header "Authorization: YOUR_API_KEY" \
--header "Content-Type: application/json" \
--data '{
"audio_url": "YOUR_AUDIO_URL",
"redact_pii": true,
"redact_pii_policies": ["us_social_security_number", "credit_card_number"],
"redact_pii_sub": "hash",
"redact_pii_audio": true,
"redact_pii_audio_quality": "mp3"
}'
KeyTypeDescription
redact_piibooleanEnable PII Redaction.
redact_pii_policiesarrayPII policies for what information to redact.
redact_pii_substringMethod used to substitute PII in the transcript. Can be entity_name or hash.
redact_pii_audiobooleanCreate a redacted version of the audio file.
redact_pii_audio_qualitystringQuality of the redacted PII audio file. Can be mp3 or wav.

Response

KeyTypeDescription
textstringTranscript with redacted PII.

The response also includes the request parameters used to generate the transcript.

PII policies

account_numberCustomer account or membership identification numberPolicy No. 10042992; Member ID: HZ-5235-001
banking_informationBanking information, including account and routing numbers
blood_typeBlood typeO-, AB positive
credit_card_cvvCredit card verification codeCVV: 080
credit_card_expirationExpiration date of a credit card
credit_card_numberCredit card number
dateSpecific calendar dateDecember 18
date_of_birthDate of birthDate of Birth: March 7,1961
drivers_licenseDriver's license number.DL# 356933-540
drugMedications, vitamins, or supplementsAdvil, Acetaminophen, Panadol
email_addressEmail addresssupport@assemblyai.com
eventName of an event or holidayOlympics, Yom Kippur
gender_sexualityTerms indicating gender identity or sexual orientation, including slang termsfemale; bisexual; trans
healthcare_numberHealthcare numbers and health plan beneficiary numbersPolicy No.: 5584-486-674-YM
injuryBodily injuryI broke my arm, I have a sprained wrist
ip_addressInternet IP address, including IPv4 and IPv6 formats192.168.0.1
languageName of a natural languageSpanish, French
locationAny Location reference including mailing address, postal code, city, state, province, country, or coordinates.Lake Victoria, 145 Windsor St., 90210
medical_conditionName of a medical condition, disease, syndrome, deficit, or disorderchronic fatigue syndrome, arrhythmia, depression
medical_processMedical process, including treatments, procedures, and testsheart surgery, CT scan
money_amountName and/or amount of currency15 pesos, $94.50
nationalityTerms indicating nationality, ethnicity, or raceAmerican, Asian, Caucasian
number_sequenceNumerical PII (including alphanumeric strings) that doesn't fall under other categories
occupationJob title or professionprofessor, actors, engineer, CPA
organizationName of an organizationCNN, McDonalds, University of Alaska, Northwest General Hospital
passport_numberPassport numbers, issued by any countryPA4568332; NU3C6L86S12
passwordAccount passwords, PINs, access keys, or verification answers27%alfalfa, temp1234, My mother's maiden name is Smith
person_ageNumber associated with an age27, 75
person_nameName of a personBob, Doug Jones, Dr. Kay Martinez, MD
phone_numberTelephone or fax number
political_affiliationTerms referring to a political party, movement, or ideologyRepublican, Liberal
religionTerms indicating religious affiliationHindu, Catholic
urlInternet addresseshttps://www.assemblyai.com/
us_social_security_numberSocial Security Number or equivalent
usernameUsernames, login names, or handles@AssemblyAI
vehicle_idVehicle identification numbers (VINs), vehicle serial numbers, and license plate numbers5FNRL38918B111818; BIF7547

Troubleshooting

Why is the PII not redacted in my transcription?
Make sure that at least one PII policy has been specified in your request, using the redact_pii_policies parameter. If you're still experiencing issues, please reach out to our support team for assistance.
Why is my webhook not being sent?
There could be several reasons why your webhook isn't being sent, such as a misconfigured URL, an unreachable endpoint, or an issue with the authentication headers. Double-check your request and ensure that the webhook_url parameter is included with a valid URL that can be reached by AssemblyAI's API. If you're using custom authentication headers, ensure that the webhook_auth_header_name and webhook_auth_header_value parameters are included and are correct. If you're still having issues, please contact our support team for assistance.
Why does my redacted audio file sound worse than the original?
By default, the API returns redacted audio files in MP3 format, a lossy format. Lossy formats remove audio information to reduce file size, which may cause a reduction in quality. The difference may be particularly noticeable if the submitted audio is in a lossless file format. To retain as much quality as possible, you can instead return your redacted audio files in a lossless format, by setting redact_pii_audio_quality to wav.