Profanity Filtering
Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely.
profanity_filter boolean. Default: false
This feature is available for base tier models only.
Enable Feature
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.
curl \
--request POST \
--header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
--header 'Content-Type: audio/wav' \
--data-binary @youraudio.wav \
--url 'https://api.deepgram.com/v1/listen?profanity_filter=true'
Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.
Results
Once applied, results will appear in the transcript.
| Truth | Before profanity filter | After profanity filter |
|---|---|---|
| Well d**n it. What am I supposed to do with that information? I mean f**k that's a f**k ton of information you're giving me. Holy hell. | Well d**n it. What am I supposed to do with that information? I mean f**k that's a f**k ton of information you're giving me. Holy hell. | Well bam it. What am I supposed to do with that information? I mean that's a ton of information you're giving me. Holy hell. |
Use Cases
Some examples of use cases for the profanity filter include:
- Customers who handle volatile customers and need to remove profanity for training purposes.
- Customers who want to prevent profane words from ever appearing in transcripts.
By default, Deepgram applies its general AI model, which is a good, general purpose model for everyday situations. To learn more about the customization possible with Deepgram's API, check out the Deepgram API Reference.
Updated 8 days ago