# Sam Witteveen — 'Nemotron 3 Diarization - Who Said That?'

> Sam Witteveen looks at NVIDIA's new open model for answering 'who said that?' in a conversation.

- Org: Sam Witteveen
- Date: 2026-09-23
- Category: video
- Source: https://www.youtube.com/watch?v=PZuuOXNB3Vw
- Canonical page: https://ai-tldr.dev/releases/sam-witteveen-nemotron-3-diarization-sep23/

## In short

Sam Witteveen's 23 September 2026 video covers NVIDIA Nemotron 3 Diarization, released the same day: a 100M-parameter open model that labels who is speaking, for up to eight speakers, live or on recordings.

## What it is

'Nemotron 3 Diarization - Who Said That?' went up on Sam Witteveen's channel on 23 September 2026, the day NVIDIA released the model. Nemotron 3 Diarization is a 100M-parameter open-weight model that splits audio by speaker, for up to eight people, in streaming or offline mode.

## How it works

NVIDIA's model follows the Sortformer approach: it numbers speakers in the order they first talk, so labels stay stable from one audio chunk to the next. A 31-layer Transformer encoder reads 16 kHz audio, and latency can be set from 30.4 seconds down to 0.32 seconds. NVIDIA reports a 14.72% error rate, #1 on VoiceArena's Diarization-Bench.

## Why it matters

Speaker labels are the missing piece in most meeting notes and call transcripts. The model adds them next to an existing speech-to-text system rather than replacing it, and NVIDIA says it cuts diarization error by about 40% versus its earlier four-speaker Streaming Sortformer.

## Who it's for

engineers building transcription and meeting tools

## Links

- [Watch on YouTube](https://www.youtube.com/watch?v=PZuuOXNB3Vw)
- [Sam Witteveen](https://www.youtube.com/channel/UC55ODQSvARtgSyc8ThfiepQ)
- [NVIDIA Blog Post](https://huggingface.co/blog/nvidia/nemotron-diarization)