# Baseten — NVIDIA Nemotron 3 Diarization: real-time speaker labels at a cent per audio hour

- Company: Baseten (baseten.co)
- Announced: 2026-09-23T15:14:39+00:00
- Category: not stated
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.baseten.co/blog/nvidia-nemotron-3-diarization
- Record: https://forck.live/items/21701-nvidia-nemotron-3-diarization-real-time-speaker-labels-at-a-cent-per-audio-hour
- Subject: Baseten

NVIDIA Nemotron 3 Diarization answers who spoke when, 300ms–1s behind live, alongside any ASR. Authors Published September 23, 2026 Share Published September 23, 2026 Use NVIDIA Nemotron 3 Diarization from Baseten’s Model Library , with presets for prerecorded and streaming diarization, and real-time diarized transcription. This is an open, end-to-end diarization model that replaces the usual segmentation-plus-embedding pipeline and its tuning with a single pass, labeling up to eight speakers at a configurable interval as low as every 320ms. We optimized it on an RTX PRO 6000, which can sustain over 500 concurrent hour-long diarization streams (190 with transcription added). The same per-speaker activity can be used to inform VAD, endpointing, and turn-taking for voice agents. An end-to-end streaming architecture Speaker diarization segments an audio stream by when each distinct speaker is talking, outputs timings for each distinct voice, and assigns every span a consistent speaker label. In conjunction with transcription, diarization can attribute transcribed words to who said them in a conversation. …

---

Record: https://forck.live/items/21701-nvidia-nemotron-3-diarization-real-time-speaker-labels-at-a-cent-per-audio-hour
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md