NVIDIA releases open-weight Nemotron 3.5 Transcribe with multilingual transcription and speaker attribution
NVIDIA has launched Nemotron 3.5 Transcribe, an open-weight, promptable model for multilingual transcription, speaker attribution, translation, and audio question-answering. It supports 40 languages for transcription, translates 31 into or from English, and attributes up to eight speakers in 13 languages. The model handles recordings up to an hour long and can be fine-tuned for domain-specific…
What you can do with it
AI at Work →Transcribe meetings with NVIDIA Nemotron 3.5 Transcribe
Single model handles transcription, speaker attribution and translation.
- Who for
- marketers
- Cost
- Price not stated
- Effort
- minutes
Use it for
- Transcribe meetings
- Label speakers
- Translate audio
Watch out Check the details on the maker's page first
Key points from the news
- Nemotron 3.5 Transcribe supports 40 languages for transcription, 31 for translation, and speaker attribution in 13 languages, handling up to 8 speakers per recording
- Leads on Hugging Face Open ASR Leaderboard (5.33% WER for English) and David AI’s 21-language diarization benchmark (18.26% DER), outperforming proprietary APIs in accuracy-to-parameter efficiency
- Granary v2 data pipeline and fine-tuning tools cut WER by 45.8% in a medical domain case study, with 463,062 hours of multilingual speech data across 48 languages
Granary v2, part of the Nemotron speech collection, provides 463,062 hours of multilingual speech data across 48 languages, up from 25 in its previous version. The pipeline includes reusable curation tools for aligning transcripts, task labels, and metadata, enabling developers to fine-tune the model for specialized domains. A medical case study demonstrated a 45.8% relative reduction in word error rate (WER) when fine-tuning on held-out speakers, cutting errors from 22.44% to 12.17%. The model is available on Hugging Face and ModelScope, with hosted endpoints offered by Baseten, DeepInfra, and Simplismart. NVIDIA also provides tutorials for fine-tuning, deployment, and agent-driven workflows.
Model page: Nemotron 3 Diarization →
The story so far
3 episodes →- NVIDIA releases open-weight Nemotron 3.5 Transcribe with multilingual transcription and speaker attributionthis story
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
Hugging Face · 28 October 2026
Loading the full article…
This text was published by Hugging Face. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
7sources- Nvidia's open Nemotron 3.5 Transcribe combines transcription, translation, and speaker recognitionPress · The Decoder ·
- NVIDIA Launches Open-Weight Speech Model and 463,062-Hour Audio DatasetPress · Unite.AI ·
- Nvidia debuts Nemotron 3.5 Transcribe, an open-weight model for multilingual audio transcription and translation, and Granary v2, its open-source speech datasetPress · siliconangle.com ·
- Thin, Light and Built for Everything: NVIDIA RTX Spark Windows Laptops Gain New Models, Agent Tools and GamesPrimary source · NVIDIA Blog ·
- NVIDIA RTX Spark Laptops Expand With New AI Models, Creator Tools and GamesPress · tech.yahoo.com ·
- Voice AI in vogue: Nvidia releases new open transcription modelPress · techcrunch.com ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Ggml-org/llama.cpp merges PR #31283 adding video input for LFM3 models · 2 src
- Deepseek V4.1 Flash: 1,286 tokens/sec · 1 src
- Diffuspace/Clover-35B-A3B-Preview released · 1 src
- inclusionAI releases Ling-3.1-flash-1019 with 1M-token window and 560B parameters · 3 src
- Researchers propose Scoped semantic invariance to improve LLM consistency · 2 src
Comments
via GitHub Discussions