Deepgram’s latest update offers enhanced redaction options for customers submitting pre-recorded audio to our hosted endpoint.

Customers can now select specific types of entities, like locations, URLs, or names, to be redacted from their transcriptions.

Here’s an example of how to accomplish redacting different types of entities (in this case, city names, ages, and emails):

curl \
  --request POST \
  --header 'Authorization: Token YOUR_DEEPGRAM_API_KEY' \
  --header 'Content-Type: audio/wav' \
  --data-binary @youraudio.wav \
  --url ''

For more information, head over to our developer documentation.

Stop building work-arounds for STT systems that don't work.

Start FreeTalk to an expert