Nvidia releases free 100M-parameter model for real-time speaker diarization

Nvidia released Nemotron 3 Diarization, a free 100-million-parameter model that identifies speakers in real time and supports up to eight participants. It aims to improve practical applications in voice interaction scenarios.

• NVIDIA releases Nemotron 3 speaker diarization model2026-09-23
• Forum asks whether any hidden-gem GPUs remain2026-09-26
• DIY Builder Creates Dual RTX 3090 Inference Rig2026-09-26
• Nvidia's SoL-Pi System Cuts Coding Agent Token Usage Nearly in Half2026-09-26
• Cramer Recommends Nvidia and CrowdStrike AI Stocks2026-09-26