**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**
NVIDIA has released Nemotron 3 Diarization, an open-weight model designed to identify which speaker is talking in real-time and recorded conversations. The 100M-parameter model supports up to eight speakers and currently ranks first on Voice Arena's Diarization-Bench leaderboard. It achieves a 14.72% Diarization Error Rate while maintaining low latency for streaming applications.
- ▪NVIDIA Nemotron 3 Diarization is an open-weight model with 100 million parameters that supports up to eight speakers.
- ▪The model ranks #1 on Voice Arena's Diarization-Bench with a Diarization Error Rate of 14.72%.
- ▪It utilizes an arrival-time ordering approach to maintain stable speaker labels across streaming audio chunks.
- ▪The system achieves an average 40% relative reduction in Diarization Error Rate at a latency of 1.04 seconds.
- ▪Nemotron 3 Diarization can be integrated with Automatic Speech Recognition to produce speaker-attributed transcripts.
Hugging Face Blog files mainly under ai. We currently carry 33 of its stories.
Story provenance
Source · retrieval · rights · ranking — open for full record
inspect →
Story provenance
Attribution is not the same as permission. This drawer separates discovery metadata, excerpts, WeSearch-generated summaries, reuse status, and whether the publisher receives the visit. Nothing here claims a legal grant the publisher has not made.
Record
| Original publisher | Hugging Face Blog |
| Canonical URL | https://huggingface.co/blog/nvidia/nemotron-diarization |
| Publication time | Wed, 23 Sep 2026 13:17:01 GMT |
| Retrieval time | 2026-09-23T13:19:30.708Z |
| Last seen | 2026-09-23T13:19:30.708Z |
| Headline source | Publisher (no WeSearch rewrite) |
| Excerpt source | publisher body |
| Excerpt method | First ~120 words (~800 chars) of extracted publisher body, fair-use limited. |
| Summary | WeSearch · cerebras-chat (WeSearch summarizer) |
| Summary source text | contentText |
| Citation coverage | Summary is a WeSearch-generated derivative; primary citation is the original publisher URL. |
| Cluster | wJOVxXzQbHzj · 1 stories |
| Cluster logic | Grouped by semantic title/content similarity across sources within a rolling window. Same-publisher template collisions are excluded from coverage comparison. |
| Ranking reason | Story pages are not engagement-ranked. Hub feeds use recency, with optional source-diversified chronological ordering (cap consecutive stories per source). No personalized ranking. |
| Publisher visit | Yes — open original |
| Substitutes article? | No — link-out required for full text |
Rights status (four layers)
WeSearch handling by dimension
| Indexing | May the item be indexed (stored, ranked, made findable)? | Allowed |
| Snippet | May a short excerpt of the publisher's text be shown? | Allowed |
| AI summary | May WeSearch generate its own short summary of the article? | Limited |
| Retrieval / RAG | May the content be exposed for third-party retrieval-augmented generation? | Not asserted |
| Model training | May the content be used to train AI models? | Not asserted |
| Commercial reuse | May the content be reused commercially? | Not permitted |
Basis: Derived from the published RSS/Atom feed. Contact: [email protected]. Reviewed: 2026-07-24.
Opening excerpt (first ~120 words) tap to expand
Back to Articles Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization Enterprise + Article Published September 23, 2026 Upvote - Francesco fciannella Follow nvidia Maryam Motamedi maryameee Follow nvidia Taejin Park taejinp Follow nvidia Ivan Medennikov imedennikov Follow nvidia Adi- margolin Amargolin Follow nvidia Turn overlapping conversations into speaker-aware data with one open-weight, 100M-parameter model - ranked #1 in Voice Arena's initial Diarization-Bench results.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at Hugging Face Blog.
Discussion
0 commentsMore from Hugging Face Blog
