# NVIDIA — NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt

- Company: NVIDIA (nvidia.com)
- Announced: 2026-10-28T14:58:17+00:00
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/nvidia/nemotron-transcribe-granary
- Record: https://forck.live/items/28778-nvidia-nemotron-3-5-transcribe-and-granary-v2-intelligent-multilingual
- Open weights: yes
- Models affected: Nemotron 3.5 Transcribe, Granary v2

NVIDIA released Nemotron 3.5 Transcribe, an open-weight, promptable speech model that handles transcription, speaker attribution, translation and audio question answering in one checkpoint, alongside the open Granary v2 data pipeline. The company says the model transcribes 40 languages, translates 31 of them to or from English, and attributes speakers in 13, handling recordings up to an hour long and up to eight speakers. NVIDIA reports it ranks first among open-weight models on the Hugging Face Open ASR Leaderboard for English at 5.33% average WER, and ties for first among open-weight models on Artificial Analysis's AA-WER index at 2.8% with about 4B active parameters. It pairs a speech encoder with a hybrid Mamba–Transformer mixture-of-experts language model, so only about 4B of its 30B parameters are active per token, and it runs on a single NVIDIA GPU. Developers can steer output with natural language prompts, and NVIDIA says fine-tuning with Granary v2 data and NeMo Speech tools cut word error rate on held-out speakers by 45.8% relative to the best prompt in a medical case study. The model is available on Hugging Face and ModelScope, and NVIDIA advises spot-checking names, speaker changes and answers against the recording.

## Evidence

Verbatim from https://huggingface.co/blog/nvidia/nemotron-transcribe-granary:

> One open model for multilingual transcription, speaker attribution, translation, and audio Q&A, with top leaderboard results, plus the open Granary v2 data pipeline and fine-tuning recipes to adapt it.
> 
> A transcript can capture every spoken word and still leave users or applications wondering who said what, how to translate it, or how to format domain-specific jargon. Multilingual calls, fast-paced meetings, and medical dictation each need different output: a translation, speaker labels, or correctly spelled medical terms.
> 
> NVIDIA Nemotron 3.5 Transcribe is an open-weight, promptable model that turns recorded speech into useful text, now available on Hugging Face and ModelScope . It brings transcription, speaker attribution (diarization), translation, and audio question answering into one checkpoint: it transcribes 40 languages, translates 31 of them to or from English, and attributes speakers in 13. It handles recordings up to an hour long and labels up to eight speakers. Developers can guide output with natural language, choose where their audio is processed, and adapt recognition to domain vocabulary and accents.

---

Record: https://forck.live/items/28778-nvidia-nemotron-3-5-transcribe-and-granary-v2-intelligent-multilingual
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md