Identify and redact sensitive information from transcripts including PII, PCI, and PHI data, profanity, and filler words.

Use cases

You can use redaction in many ways:

  • Maintain compliance and protect consumer data – Anonymize protected information and store redacted versions of transcripts containing sensitive information to achieve and maintain compliance with HIPAA, CCPA, GDPR, and PCI SSC.
  • Employee training – Enable re-use of real world samples with protected data redacted. You can replace redacted data with useful mock data for training.
  • Call center data sharing – Redact personal information from customer call transcripts for downstream sharing and analysis.


  • Redact PII, PCI, and PHI data – Choose to redact one or all categories of PII, PCI, and PHI data from conversations.
  • Redact profanity – Automatically redact profane phrases from conversations. This setting is enabled by default.
  • Remove filler words – Automatically remove small meaningless words such as um, ah, and _hmm _from conversations. This setting is enabled by default.

Feature availability

Redaction is available for recorded (async) and real-time (streaming and telephony) conversations:

Redact PII, PCI, and PHI data
Redact profanity
Remove filler words

Generate a redacted transcript

Filler words and profanity are redacted by default for all conversations.

To generate a redacted transcript or change redaction settings and output options, see Redaction.

Next steps