# NVIDIA releases Nemotron 3.5 Transcribe, a 30B-A4B open-weight speech model

> Original title: NVIDIA Nemotron 3.5 Transcribe has landed: a 30B-A4B open-weight model that turns up to an hour of recorded speech into searchable transc...

- Source: ModelScope
- Published: 2026-10-28T15:08:19.000Z
- Bad Influence: https://badinfluence.news/items/li7axlegqyjgl3uqdms4glaxa
- Original: https://x.com/ModelScope2022/status/2115460660792361039

## Summary

ModelScope announces NVIDIA's Nemotron 3.5 Transcribe, a 30B-A4B open-weight model that transcribes up to an hour of speech with speaker labels, translations, and audio answers. The post says it transcribes 40 languages, translates 31 languages to and from English, and supports speaker attribution in 13 languages for recordings with up to eight speakers. It runs on a single GPU and is released under the openmdw-1.1 license.

## Why it matters

The post lists the model's language coverage, speaker attribution limits, and self-hosting setup, which helps readers judge whether it fits their transcription workflow.

## Post

NVIDIA Nemotron 3.5 Transcribe has landed: a 30B-A4B open-weight model that turns up to an hour of recorded speech into searchable transcripts, speaker labels, translations, and answers.
🤖 https://modelscope.ai/collections/nv-community/Nemotron-35-Transcribe

🏆 Leading transcription and speaker attribution: Ranks first among open-weight models on the Hugging Face English Open ASR Leaderboard, and first on both David AI’s multilingual diarization benchmark and VoiceArena’s 14-system comparison.
🌍 One checkpoint, multiple speech tasks: Transcribes 40 languages, translates 31 languages to and from English, and supports speaker attribution in 13 languages for recordings with up to eight speakers.
🎯 Guide the output with natural language: Prompt for domain terms, transcript conventions, translations, speaker labels, or questions about the recording. Language support differs by task; audio Q&A is trained in English.
🔧 Adapt it to your domain: Granary v2 and NeMo Speech fine-tuning tools extend prompt-level control to training. In the medical case study, fine-tuning reduced held-out WER by 45.8% over the best prompt-only baseline.
⚡ Built for self-hosted batch transcription: Runs on a single GPU, from DGX Spark to Blackwell data-center systems.
📜 License: openmdw-1.1

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Ftweet_video_thumb%2FHVubyPVXIAAIiLY.jpg&mode=thumb&exp=1793404800&sig=e912f770224a114e)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVub9UQXAAAbT_1.jpg&mode=thumb&exp=1793404800&sig=72cb9e661a68f4b8)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVub9UPXUAAp4uz.jpg&mode=thumb&exp=1793404800&sig=082b624b8a0418f8)

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHVub9UXXkAAIJx0.jpg&mode=thumb&exp=1793404800&sig=6ce6ce027281d7a7)