Get Zlio on your home screenOne tap, full screen, like an app.
AI Voice · first seen 29 October 2026, 07:09 UTC
Nvidia releases Nemotron 3.5 Transcribe speech model
Efficient open speech model that matches larger ASR rivals at a fraction of active parameters.
Nvidia launches Nemotron 3.5 Transcribe, a free 30B-parameter speech-to-text model that reportedly matches rivals using one-sixth the active parameters, competing with Qwen ASR and Nvidia's Parakeet.