# NVIDIA's Nemotron-3-Diarization Supports Offline and Streaming Speaker Diarization

DevFeed: [NVIDIA's Nemotron-3-Diarization Supports Offline and Streaming Speaker Diarization](<https://devfeed.tech/articles/nemotron-3-diarization-here-s-what-you-need-to-know-60271.md>)

Original publisher: [Read original article](<https://hackernoon.com/nemotron-3-diarization-heres-what-you-need-to-know?source=rss>)

Author: aimodels44

Published: 2026-09-25T21:04:34Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Nemotron](<https://devfeed.tech/topics/nemotron.md>), [asr](<https://devfeed.tech/topics/asr.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Streaming](<https://devfeed.tech/topics/streaming.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [NeMo](<https://devfeed.tech/topics/nemo.md>), [processing](<https://devfeed.tech/topics/processing.md>), [C++](<https://devfeed.tech/topics/c-plus-plus.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-model-guide](<https://devfeed.tech/tags/ai-model-guide.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [asr](<https://devfeed.tech/tags/asr.md>), [c-plus-plus](<https://devfeed.tech/tags/c-plus-plus.md>), [diarization](<https://devfeed.tech/tags/diarization.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [inference](<https://devfeed.tech/tags/inference.md>), [latency](<https://devfeed.tech/tags/latency.md>), [nemotron](<https://devfeed.tech/tags/nemotron.md>), [nemotron-3-diarization](<https://devfeed.tech/tags/nemotron-3-diarization.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [nvidia-nemo](<https://devfeed.tech/tags/nvidia-nemo.md>), [python](<https://devfeed.tech/tags/python.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [speaker-diarization](<https://devfeed.tech/tags/speaker-diarization.md>)

## AI overview

NVIDIA's Nemotron-3-Diarization is an open-weight speaker diarization model for identifying who spoke when in real-world audio. One checkpoint supports offline and streaming processing for up to eight speakers, with configurable resolution and chunked inference without a stated maximum duration.

## Source excerpt

Nemotron-3-Diarization is an open-weight speaker diarization model from NVIDIA that identifies who spoke when in real-world audio.