DigestAI news desk

Cut through the AI noise.

Listen
Model · audio model

Nemotron 3 Diarization

Nemotron 3 Diarization is an audio model from Nvidia, first covered on 23 September 2026. It is available as open weights you can download and run (licence: OpenMDW License 1.1).

Last updated

At a glance

Made by
Nvidia
Type
Audio model
Availability
Open weights
Licence
OpenMDW License 1.1
Context window
Not stated
First seen
23 September 2026

Taken from the coverage, not from our own testing; "not stated" means none of the reports we read gave it. All tracked models →

1 story about Nemotron 3 Diarization

  1. Generative AI & Models new

    Nvidia releases Nemotron 3 Diarization, a 100M-parameter model tracking up to 8 speakers

    Nvidia announced the open‑weight speaker diarization model Nemotron 3 Diarization on Hugging Face. The 100 million‑parameter model can identify who spoke when in audio streams, handling up to eight overlapping speakers…

    1 source
    MarkTechPost
Other models from Nvidia
NVIDIA-Nemotron-3-Nano-4B-GGUFNemotron 3 Ultra
hot Anthropic releases Claude Opus 5.5 with $4 input and $20 output pricing, claiming 40% lower cost than Opus 5 new Google launches Gemini 3.8 Flash and Flash‑Lite text‑to‑speech models hot OpenAI's GPT-6 Astra: Changing Work and Research new UN security council to hear AI risk briefings from OpenAI, Anthropic and Hugging Face hot YouTube adds AI draft feedback and dynamic thumbnails to Studio app new User discovers Claude Code -p calls bypass flat-rate plan, causing API billing hot Anthropic releases Claude Opus 5.5 and OpenAI counters with cheaper GPT-6 Sol and Luna models new Google Antigravity SDK adds support for local Gemma 4 26B models