{"version":1,"type":"story","url":"https://digestai.news/story/nvidia-releases-free-nemotron-3-diarization-model-for-real-time-speake","json":"https://digestai.news/story/nvidia-releases-free-nemotron-3-diarization-model-for-real-time-speake.json","markdown":"https://digestai.news/story/nvidia-releases-free-nemotron-3-diarization-model-for-real-time-speake.md","slug":"nvidia-releases-free-nemotron-3-diarization-model-for-real-time-speake","headline":"Nvidia releases free Nemotron 3 Diarization model for real-time speaker identification","summary":"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.\n\nOn 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.","keyPoints":["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"],"whyItMatters":"A free, high-accuracy diarization model enables better meeting transcripts, call analytics, and voice applications without licensing costs.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Nvidia"],"models":["Nemotron 3 Diarization","Streaming Sortformer","Parakeet"],"people":[]},"firstPublishedAt":"2026-09-27T11:01:13Z","updatedAt":"2026-09-27T11:01:13Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"The Decoder","title":"Nvidia drops a free 100M-parameter model that identifies up to eight speakers in real time","url":"https://the-decoder.com/nvidia-drops-a-free-100m-parameter-model-that-identifies-up-to-eight-speakers-in-real-time","publishedAt":"2026-09-27T11:01:13Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":{"title":"Nvidia Launches Free Nemotron Speaker Tracking","url":"https://digestai.news/thread/nvidia-releases-nemotron-3-diarization-a-100m-parameter-model-tracking-up-to-8","storyCount":2},"cite":{"text":"Digest AI, \"Nvidia releases free Nemotron 3 Diarization model for real-time speaker identification\", 27 September 2026, https://digestai.news/story/nvidia-releases-free-nemotron-3-diarization-model-for-real-time-speake","publisher":"Digest AI","title":"Nvidia releases free Nemotron 3 Diarization model for real-time speaker identification","datePublished":"2026-09-27T11:01:13Z","url":"https://digestai.news/story/nvidia-releases-free-nemotron-3-diarization-model-for-real-time-speake"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}