**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**

NVIDIA released a new diarization model under the Nemotron 3 brand on Hugging Face to identify and segment individual speakers during real-time audio streams. This tool enables developers to build applications that automatically track who is speaking during multi-person conversations, such as automated meeting transcription services or live broadcast captioning.