Vendor page
Speaker Diarization
Deepgram, n.d.
Read the originalRead on October 17, 2026
- What it is
- Deepgram's developer documentation for speaker diarization, which labels each word with a speaker. It covers the diarize_model parameter for pre-recorded and streaming requests and notes that the older diarize parameter is deprecated.
- How much weight it carries
- Vendor documentation, so it is reliable for how the product is called and not for accuracy claims. Parameter names change between versions, so check the current reference before you write code.
Facts taken from this source
- 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.
“Use diarize_model instead for both batch and streaming requests” (Using diarize (deprecated) section)
- Deepgram's documentation says its diarization recognizes speaker changes and assigns a speaker to each word in the transcript.
“Diarize recognizes speaker changes and assigns a speaker to each word in the transcript” (Overview)