Artificial intelligence / news brief
NVIDIA Releases an Open-Weight Speech Model for 40 Languages
- Event
- Published
NVIDIA released Nemotron 3.5 Transcribe, a 34B-parameter speech model with about 4.3B active parameters for transcription, translation, speaker attribution and audio questions. Weights, a technical report and Granary v2 data are available under stated licenses; benchmark results are primarily vendor-reported, the model needs an 80GB H100 in the reference setup and does not stream live audio.
Why it matters
One downloadable model now combines several recorded-audio workflows, but practical accuracy, hardware cost and language quality still need independent testing.
Sources
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B model card (external site)NVIDIA · primary source ·
- Voice AI in vogue: Nvidia releases new open transcription model (external site)TechCrunch · coverage ·
- Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognition (external site)The Decoder · coverage ·
- Nvidia releases Nemotron 3.5 Transcribe for speech in 40 languages (external site)Silicon Report · coverage ·