Nemotron-3-Diarization-preview

transcription

Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call analytics, and voice-agent pipelines—resolving who spoke when with generic speaker labels and timestamps in a single streaming pass, offline or in real time.

Capabilities

Infrastructure
Streaming

Details

Model IDnvidia/Nemotron-3-Diarization-preview
Provider DeepInfra
Creator NVIDIA
Family—
License—
Statusactive
Typetranscription
Input modalitiesspeech
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Languages—
Release date—
Sourceofficial

Endpoints

audio transcriptionsPOST
https://api.deepinfra.com/v1/openai/audio-transcriptions

API

GET/v1/models/deepinfra/nvidia/Nemotron-3-Diarization-preview

Nemotron-3-Diarization-preview

nvidia/Nemotron-3-Diarization-preview

Nemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call analytics, and voice-agent pipelines—resolving who spoke when with generic speaker labels and timestamps in a single streaming pass, offline or in real time.

Changes · 2 entries
nvidia/Nemotron-3-Diarization-previewcreateca7a400Nov 2, 2026, 03:02 AM
nvidia/Nemotron-3-Diarization-previewcreate28ec4f5Sep 23, 2026, 06:40 AM