Daily
@trydaily
Hey, we recognize the voice agent in that demo. 😀 Congratulations to the team at NVIDIA AI on this great new speech-to-text model release. Nemotron Speech ASR is a very fast, very good, completely open transcription model, designed from the ground up for low-latency use cases
NVIDIA AI Developer@NVIDIAAIDev · Jan 6Just launched #CES2026, the new open-source NVIDIA Nemotron Speech ASR model is here to solve latency drift and redundant compute.
Its cache-aware streaming architecture eliminates the need for buffered inference, giving you stable, sub-100ms latency (24ms median T-T-F) and up
Its cache-aware streaming architecture eliminates the need for buffered inference, giving you stable, sub-100ms latency (24ms median T-T-F) and up
1:24 1 4