🎉 NVIDIA Nemotron 3.5 Transcribe is here—with day-0 serving through vLLM + NeMo Speech.
40 languages. Recordings up to an hour. Promptable transcripts, speaker labels and audio Q&A.
Open weights in BF16, FP8 and NVFP4.
NVIDIA releases Nemotron 3.5 Transcribe with day-0 vLLM serving
AINVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable 30B MoE model with about 4B active parameters. It supports transcription in 40 languages, recordings up to an hour, speaker labels, and audio Q&A, with weights in BF16, FP8 and NVFP4, and serving through vLLM and NeMo Speech on day 0.
@vllm_project
Meet NVIDIA Nemotron 3.5 Transcribe 🎙️ An open-weight, promptable 30B MoE model with ~4B active parameters that brings transcription in 40 languages, speaker attribution, translation, contextual prompting and audio understanding into one checkpoint. Watch it keep track of who said what when everyone’s talking at once. 1/ 🧵
This story is featured in top picks: “NVIDIA releases Nemotron 3.5 Transcribe, a 30B-A4B open-weight speech model”
Source details
vLLM · x.comPublished · added here
Original title: 🎉 NVIDIA Nemotron 3.5 Transcribe is here—with day-0 serving through vLLM + NeMo Speech.