# NVIDIA launches Nemotron 3.5 Transcribe model for advanced multilingual transcription

Published: 2026-10-28 · Updated: 2026-10-28 · Category: Product Launch

Source page: https://www.sipply.dev/story/nvidia-launches-nemotron-3-5-transcribe-model-for-advanced-9acc9684 · 中文: https://www.sipply.dev/zh/story/nvidia-launches-nemotron-3-5-transcribe-model-for-advanced-9acc9684

## Summary

NVIDIA has introduced the Nemotron 3.5 Transcribe model, enhancing the capabilities of multilingual transcription. This new model features advanced functionalities such as speaker attribution, translation, and audio question answering, making it a versatile tool for various applications. It is now accessible on platforms like Hugging Face and ModelScope, where it has already demonstrated top performance on multiple Automatic Speech Recognition (ASR) leaderboards, indicating its competitive edge in the market.

## Key takeaways

- Nemotron 3.5 Transcribe offers advanced multilingual transcription capabilities.
- The model includes features like speaker attribution and audio question answering.
- It is available on Hugging Face and ModelScope, showing strong performance on ASR leaderboards.

## Why it matters

The launch of Nemotron 3.5 Transcribe signifies a significant advancement in AI-driven transcription technology, catering to the growing demand for multilingual support in various industries.

- **Product managers:** Product managers should note the model's capabilities for enhancing user experience in applications requiring transcription and translation, potentially opening new market opportunities.
- **Developers:** Developers can leverage the advanced features of Nemotron 3.5 to build more sophisticated applications that require accurate and context-aware transcription services.
- **Students and job seekers:** Students and job-seekers can benefit from understanding and utilizing this technology, as proficiency in AI tools like Nemotron 3.5 can enhance their skill set in a competitive job market.

## Sources

- [NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt](https://huggingface.co/blog/nvidia/nemotron-transcribe-granary) (Hugging Face Blog, 2026-10-28)

## 中文

### NVIDIA推出Nemotron 3.5 Transcribe模型，支持先进的多语言转录

NVIDIA推出了Nemotron 3.5 Transcribe模型，增强了多语言转录的能力。该新模型具有扬声器归属、翻译和音频问答等先进功能，使其成为多种应用的多功能工具。它现已在Hugging Face和ModelScope等平台上可用，并在多个自动语音识别（ASR）排行榜上表现出色，显示出其市场竞争优势。

**要点：**

- Nemotron 3.5 Transcribe提供先进的多语言转录能力。
- 该模型包括扬声器归属和音频问答等功能。
- 它在Hugging Face和ModelScope上可用，并在ASR排行榜上表现强劲。

**为什么重要：** Nemotron 3.5 Transcribe的推出标志着AI驱动的转录技术的重大进步，满足了各行业对多语言支持日益增长的需求。

---
Sipply: Sip AI News Simply. https://www.sipply.dev