Capability change
Capability change announced May 21, 2026
Deepgram documents a capability change: “Profanity Filtering Now Supported for All Multilingual Models; Korean Spacing Improvements 🆕 Profanity Filtering for Multilingual Models Deepgram’s…”
- Hosting route
- First-party API
- Affected scope
- Languages: multi
- Announced
- May 21, 2026
- First seen by ModelClock
- Oct 3, 2026
What the provider published
developers.deepgram.com ↗Profanity Filtering Now Supported for All Multilingual Models; Korean Spacing Improvements
🆕 Profanity Filtering for Multilingual Models
Deepgram’s Profanity Filtering feature is now available for all multilingual models: Nova-2 multilingual, Nova-3 multilingual, and Flux multilingual (
language=multi). You can enable profanity filtering in your API requests by setting theprofanity_filter=trueparameter. When enabled, inappropriate language is automatically replaced with asterisks (****) in the transcript.
Read from the provider's text; the quote is the provider's exact lines.