DigestAI news desk

Cut through the AI noise.

Generative AI & Models1 min read

Nvidia releases free Nemotron 3 Diarization model for real-time speaker identification

The model weights are freely available and can process both recordings and live audio streams. It detects overlapping speech and works with adjustable audio buffers ranging from 30.4 down to 0.32 seconds, though shorter buffers reduce accuracy.

1 source

Key points

  • Identifies up to eight speakers in real time with 14.72% error rate on Diarization-Bench
  • Cuts error rate by 41% average versus Streaming Sortformer across eight scenarios

On the Diarization-Bench from VoiceArena, the model achieves a 14.72 percent error rate, placing it first ahead of the next best system at 19.3 percent. The benchmark counts overlapping speech and small misalignments at speaker transitions as errors. Compared to its predecessor Streaming Sortformer, Nemotron 3 Diarization cuts the error rate by an average of 41 percent across eight test scenarios using a 1.04-second buffer. When paired with a speech recognition system like Parakeet, it can produce transcripts with anonymous speaker labels.

Model page: Nemotron 3 Diarization →

The story so far

2 episodes →
  1. Nvidia releases free Nemotron 3 Diarization model for real-time speaker identificationthis story
Full story from The Decoder · by Jonathan KemperOpen source ↗

Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real time

The Decoder · 27 September 2026

Loading the full article…

This text was published by The Decoder and written by Jonathan Kemper. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page
NvidiaNemotron 3 DiarizationStreaming SortformerParakeet

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Generative AI & Models

All →

Related stories