Fact · Speech recognition
Deepgram's documentation says to use the diarize_model parameter for speaker diarization in both batch and streaming requests, and that the older diarize parameter is deprecated.
Checked against its source on October 17, 2026
In the source's own words
“Use diarize_model instead for both batch and streaming requests”
Speaker Diarization, Deepgram, n.d., Using diarize (deprecated) section.
Open the original- What it measures
- Deepgram's diarization page shows the parameter in a cURL example for pre-recorded audio and describes the streaming behaviour in its own section.
- What it does not show
- Parameter names and model versions change. The page is vendor documentation, so the accuracy of the labels is not measured here.