Profanity Filtering
Profanity Filter looks for recognized profanity and replaces it with asterisks.
profanity_filter boolean Default: false
Deepgram’s profanity filtering feature masks offensive language in transcripts using asterisks. Profanity filtering is available for the following languages:
ar, ar-AE, ar-SA, ar-QA, ar-KW, ar-SY, ar-LB, ar-PS, ar-JO, ar-EG, ar-SD, ar-TD, ar-MA, ar-DZ, ar-TN, ar-IQ, ar-IRbebnbsbgcazh, zh-CN, zh-TWzh-HKzh, zh-CN, zh-Hanszh-TW, zh-Hanthrcsda, da-DKnlen, en-US, en-AU, en-CA, en-GB, en-IE, en-IN, en-NZetfinl-BEfr, fr-CAdede-CHelgu, gu-INhehi, hi-Latnhuiditjaknko, ko-KRlvltmkmsmrnofaplpt, pt-BR, pt-PTrorusrsksles, es-419, es-LATAMsv, sv-SEtltaqtateth, th-THtrukurviProfanity filtering is supported for all multilingual models: Nova-2 multi, Nova-3 multi, and Flux multi (language=multi).
To enable Profanity Filtering, use the following parameter in the query string when you call Deepgram’s /listen endpoint :
profanity_filter=true
To transcribe audio from a file on your computer, run the following cURL command in a terminal or your favorite API client.
Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.
Filtered results will appear in the transcript as ****