---
id: "2026-10-28-nvidia-nemotron-3-5-transcribe"
url: "https://postcutoff.com/e/2026-10-28-nvidia-nemotron-3-5-transcribe/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2026-10-28"
date_precision: day
category: open-source
importance: 3
confidence: high
status: [Confirmed]
sources: 5
editor: human editor
human_review: null
version: "2026-10-29"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2026-10-28-nvidia-nemotron-3-5-transcribe/

# NVIDIA releases Nemotron 3.5 Transcribe, an open-weight 30B-A4B speech model for transcription, diarization and translation in 40 languages, with the Granary v2 dataset

On Oct 28, 2026 NVIDIA released Nemotron 3.5 Transcribe (34B total, ~4.3B active), an open-weight speech-augmented model that turns recordings of up to an hour into transcripts, speaker-attributed text, word timestamps, translations or answers, chosen by the prompt, in 40 languages. NVIDIA reports the best scores of any open model on the Open ASR Leaderboard test sets (English mean WER 4.71%, multilingual 4.62%). It also published Granary v2, an open multilingual speech dataset (463,062 hours, 48 languages).

## Key facts
- Weights on Hugging Face under the OpenMDW-1.1 licence (BF16, FP8, NVFP4), plus NIM/build.nvidia.com, NGC and NeMo Speech on GitHub, all dated Oct 28; served with vLLM 0.32.0
- Architecture: ASR encoder plus Nemotron-3-Diarization speaker encoder feeding the hybrid Mamba-Transformer MoE Nemotron 3.5 Lightning 30B-A3B; CTC timestamp head; native multi-token prediction and an optional DFlash2 draft model; 65,536-token context
- Vendor benchmarks (captured Oct 12): English Open ASR mean WER 4.71% vs Qwen3-ASR-1.7B 4.94%; long-form 10.98% vs Parakeet-TDT-0.6B-v3 13.37%; multilingual Open ASR (7 languages) 4.62% vs 6.49%; multi-speaker mean cpWER 15.80% vs 16.83% for DiCoW v3.3 + DiariZen
- Throughput (NVIDIA): up to 2,238 seconds of audio per second on one RTX PRO 6000 Blackwell Server Edition (NVFP4 with DFlash2); runs from Jetson Thor and DGX Spark to data-centre GPUs
- Limits: offline model, not real-time streaming; audio understanding and reasoning evaluated only in English; recordings up to 1 hour per the model card (SiliconANGLE's 'answering questions about 100 hours of audio' is not in the card; its 'under three minutes for 100 hours' is a batch-throughput figure)
- Training data: ~1.72M unique hours (6.53M with repeats), ~372M audio examples; Granary v2 public manifest 463,062 hours across 48 languages and 16 corpora (Granary v1: 25 languages); includes data licensed from David AI

## What happened

NVIDIA folded the usual speech pipeline (voice activity detection, transcription, diarization, translation, question answering) into
one open model driven by prompts, built on its Nemotron 3.5 Lightning language model. The release includes the training-data pipeline
(Granary v2) so others can fine-tune it.

## Why it matters

It is the strongest open-weights transcription model by NVIDIA's own measurements on public leaderboard sets, and its permissive licence
lets companies run meeting and call transcription on their own GPUs. Independent leaderboard results were not yet available on Oct 29.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): 181 days after its cutoff
- Claude Opus 5.5 (training cutoff June 2026): 120 days after its cutoff
- Gemini 4 Hydrogen (training cutoff March 2026): 211 days after its cutoff
- Grok 4.7 (training cutoff May 2026): 150 days after its cutoff

## Sources

1. [Hugging Face: NVIDIA-Nemotron-3.5-Transcribe-30B-A4B model card](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B) (huggingface.co, official)
2. [NVIDIA: Nemotron 3.5 Transcribe technical report (PDF)](https://research.nvidia.com/labs/nemotron/files/NVIDIA-Nemotron-3.5-Transcribe-Technical-Report.pdf) (research.nvidia.com, paper)
3. [Hugging Face: Granary v2 dataset](https://huggingface.co/datasets/nvidia/Granary-v2) (huggingface.co, code)
4. [SiliconANGLE: Nvidia releases all-in-one adaptable Nemotron 3.5 audio transcription and translation model (Oct 28)](https://siliconangle.com/2026/10/28/nvidia-releases-all-in-one-adaptable-nemotron-3-5-audio-transcription-and-translation-model/) (siliconangle.com, press)
5. [TechCrunch: Voice AI in vogue: Nvidia releases new open transcription model (Oct 28)](https://techcrunch.com/2026/10/28/voice-ai-in-vogue-nvidia-releases-new-open-transcription-model/) (techcrunch.com, press)

## Changes

- 2026-10-29 (filed): Created. Model file nemotron-3-5-transcribe added (news agent)

## Related

- 2026-08-11: [NVIDIA releases open Nemotron 3.5 Lightning and NeMo Switchyard model router](https://postcutoff.com/e/2026-08-11-nvidia-nemotron-3-5-lightning/index.md)
- Models: [NVIDIA Nemotron 3.5 Transcribe (30B-A4B)](https://postcutoff.com/m/nemotron-3-5-transcribe/) (`nemotron-3-5-transcribe`)