Method

Content strong language

Strong language detection (audio transcript)

What we measure and how

Audio is submitted to AWS Transcribe for a word-level transcript. The transcript is then scanned against the spec's `prohibited_keywords.banlist`; matches are reported with their timestamps. Skipped cleanly when the spec disables the check or no speech is detected.

Spec fields consulted

These Universal Media Delivery Profile paths resolve this check's thresholds against your spec snapshot at the moment the job was submitted.

• · constraints.content.classification.strong_language.enabled
• · constraints.content.classification.prohibited_keywords.enabled
• · constraints.content.classification.prohibited_keywords.banlist

The full UMDP schema: /umdp.

Related methods

• Content explicit
• Content prohibited keywords
• Content scene classification
• Content violence

Method identifier: content_strong_language