Deepgram Audio Intelligence

Audio intelligence is not a separate endpoint. It is five query parameters on /v1/listen, the same endpoint that returns the transcript. You get the transcript and the analysis in one response, from one API call. This skill gets a verified request working and states the limits precisely.

Decide first

• Your input is audio (a file, a URL, a call recording) and you want analysis: stay here, use POST https://api.deepgram.com/v1/listen.
• Your input is already text (a transcript, an email, a chat log, a support ticket): the parameters below do not apply. Use the Read API, POST /v1/read. Open the text-intelligence skill.
• You only want the transcript: drop these parameters and open the speech-to-text skill.
• You are streaming live audio: see the matrix (detect_entities only).

Feature matrix