Method

Content prohibited keywords

Prohibited-keyword detection (audio transcript)

What we measure and how

Same Transcribe-based path as `content_strong_language` but matched against the spec-supplied `prohibited_keywords.banlist` (not the system's strong-language list). Returns the matched word + timestamp + surrounding context for each hit.

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

The full UMDP schema: /umdp.

Related methods

• Content explicit
• Content scene classification
• Content strong language
• Content violence

Method identifier: content_prohibited_keywords