Universal-3 Pro Streaming, the most accurate real-time transcription model for voice agents, is now live! Learn more

PlaygroundChangelogCommunitySign In
OverviewAPI ReferencePre-recorded STTStreaming STTSpeech UnderstandingGuardrailsLLM Gateway
OverviewAPI ReferencePre-recorded STTStreaming STTSpeech UnderstandingGuardrailsLLM Gateway
  • Models & features
    • Getting started
    • PII redaction
    • Content moderation
    • Profanity filtering
    • Speech threshold
Models & features

Guardrails

Protect sensitive content in your transcripts with guardrail features.

Guardrails help you filter, redact, and moderate transcript content to meet compliance and safety requirements.

PII Redaction

Automatically detect and redact personally identifiable information from transcripts and audio.

Content Moderation

Detect sensitive content like hate speech, violence, and other topics in your audio.

Profanity Filtering

Filter profanity from your transcripts by replacing profane words with asterisks.

Speech Threshold

Prevent transcription of files with insufficient speech, reducing unnecessary processing.

Was this page helpful?

PII Redaction

Next
Built with
LogoLogo
PlaygroundChangelogCommunitySign In