Tech AI LatestNVIDIA releases Nemotron 3.5 Transcribe, an open speech model for 40 languages, and Granary v2
NVIDIA released Nemotron 3.5 Transcribe on 28 October 2026, an open-weight speech model for 40 languages with speaker labels, plus the Granary v2 dataset.
Summary
NVIDIA released Nemotron 3.5 Transcribe on 28 October 2026, an open-weight speech model on Hugging Face and ModelScope under the OpenMDW-1.1 licence. One 30B-parameter checkpoint with about 4B active parameters transcribes 40 languages, translates 31, labels speakers in 13 and answers questions about recordings up to an hour long. NVIDIA also published Granary v2, a 463,062-hour speech data manifest in 48 languages, with fine-tuning recipes.