# NVIDIA's Nemotron 3.5 Transcribe Brings Promptable ASR

> A sparse 30B mixture-of-experts model handles multilingual transcription, translation, and speaker diarization from a single system.

Published by The Open Weights on Oct 7, 2026. Canonical: https://theopenweights.com/news/nemotron-3-5-transcribe-30b-a4b-9bnc

## Key facts

- Company: NVIDIA
- Model: Nemotron 3.5 Transcribe 30B-A4B
- Version: 3.5
- Category: Speech → Text
- Modalities: Speech → Text
- License: Other (Open weights, commercial use allowed)
- Parameters: 30B (mixture of experts)
- Active parameters: 4B
- Architecture: Nemotron3_5TranscribeForConditionalGeneration
- Precision: BF16
- Weights size: 67.5 GB
- Languages: multilingual
- Significance: notable
- Published: 2026-10-07
- Last verified: 2026-10-29
- Hugging Face: https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
- Canonical URL: https://theopenweights.com/news/nemotron-3-5-transcribe-30b-a4b-9bnc

NVIDIA has released [Nemotron 3.5 Transcribe 30B-A4B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B), a speech recognition model that leans on a mixture-of-experts design to keep inference light while scaling capacity. The model totals roughly 30 billion parameters but activates only about 4 billion per token, a now-familiar pattern that aims to deliver larger-model quality at a smaller compute cost.

The headline feature is that it is promptable: rather than a fixed transcription pipeline, the model can be steered toward different tasks through instructions. According to NVIDIA's [release write-up](https://huggingface.co/blog/nvidia/nemotron-transcribe-granary), that includes multilingual transcription, speech translation, and speaker diarization from a single system.

## What it does

- Multilingual automatic speech recognition
- Speech-to-text translation across languages
- Speaker diarization to separate who said what
- Prompt-based control over the output task

Combining these capabilities in one promptable model is the interesting part. Teams typically stitch together separate systems for transcription, translation, and diarization; folding them into a single checkpoint simplifies deployment and could reduce the glue code and latency that usually come with multi-stage audio pipelines.

Why it matters: open ASR has lagged behind the pace of open text and image models, and a sparse, instruction-driven option from a major vendor gives developers a flexible building block for captioning, meeting tools, and voice interfaces. The model ships under a custom NVIDIA license, so prospective users should review the terms before building on it.

## Get the model

- [Hugging Face](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B)

## Sources

- [nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B) — Hugging Face, Oct 7, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "NVIDIA's Nemotron 3.5 Transcribe Brings Promptable ASR", The Open Weights, Oct 7, 2026, https://theopenweights.com/news/nemotron-3-5-transcribe-30b-a4b-9bnc