Nemotron 3 Diarization
Open-weight real-time speaker diarization model
Free
Audio Generation
100M
parameters
Apache 2.0
license
Sep 2026
released
NVIDIA released Nemotron 3 Diarization on September 23, 2026, a 100-million-parameter open-weight model that tracks up to eight overlapping speakers in real-time streaming audio. It targets call-center and meeting-transcription pipelines that need to know who said what as the audio comes in, rather than after the fact.
// similar models in Audio Generation
Eleven v4
ElevenLabs' top-ranked text-to-speech model with a real-time Turbo variant
ElevenLabs · Audio Generation · Paid
Whisper
OpenAI's open-weight speech recognition and transcription model
OpenAI · Audio Generation · Free
Gemini 3.8 Live
Google's real-time speech-to-speech model for production voice agents
Google DeepMind · Audio Generation · Paid
GPT-Live-1
OpenAI's full-duplex voice model that listens and speaks at the same time
OpenAI · Audio Generation · Freemium
Eleven Multilingual v2
ElevenLabs' flagship text-to-speech model across 29 languages
ElevenLabs · Audio Generation · Freemium
Eleven v3
ElevenLabs' most expressive text-to-speech model with fine-grained emotional control
ElevenLabs · Audio Generation · Freemium