# NVIDIA releases open-weight speech model for transcription and translation

_Published Wednesday, October 28, 2026 at 11:20 AM EDT · AI · Latest · Tier 2 — Notable_

![NVIDIA releases open-weight speech model for transcription and translation — Primary](https://blogs.nvidia.com/wp-content/uploads/2026/10/nv-blog-1280x680-2-1.jpg)

NVIDIA released Nemotron 3.5 Transcribe, an open-weight speech model that combines transcription, speaker labeling, translation and answers to questions about recorded audio. The company says it transcribes 40 languages, including seven Indic languages, and accepts plain-language prompts with specialized vocabulary and formatting instructions.

The model is available on Hugging Face in BF16, FP8 and NVFP4 formats, with support for RTX Spark and DGX Spark systems, Jetson AGX Thor devices and GeForce RTX 5090 GPUs. Developers can deploy NVFP4 versions through NeMo-Speech.cpp or vLLM. Open weights let developers choose whether to process audio on a desktop or in the cloud; NVIDIA's accuracy rankings are company-reported.

## Sources

- [News Releases - NVIDIA Newsroom](https://blogs.nvidia.com/blog/local-ai-rtx-spark-laptops-updates-models-agents-games/)

---
Canonical: https://techandbusiness.org/newswire/ChyzZUtuT1SKk0p_yP0VUd
Published: 2026-10-28T15:20:32.777Z
Story chronology: 2026-10-28T15:00:46.000Z
Retrieved: 2026-10-28T18:12:39.620Z
Publisher: Tech & Business (techandbusiness.org)