NVIDIA releases Nemotron 3.5 Transcribe model and Granary v2 pipeline

NVIDIA released Nemotron 3.5 Transcribe, an open-weight promptable speech model combining transcription, speaker diarization, translation and audio Q&A in one checkpoint. It transcribes 40 languages, translates 31 to or from English and diarizes 13, handling recordings up to an hour with eight speakers. It ranks first among open-weight models on Hugging Face's English ASR leaderboard, alongside the Granary v2 data pipeline and NeMo fine-tuning recipes for domain adaptation.

• DOJ queries Nvidia's $13B Hugging Face deal2026-10-28
• Nvidia CEO demos Microduck robots, preorders exceed 20,0002026-10-23
• NVIDIA releases Nemotron-3.5-Bolt-E4B small model2026-10-23
• Train Microduck to walk in Isaac Lab 3.0 and deploy to real robot2026-10-21
• inclusionAI releases 126B audio-language model Ming-3.0-audio-flash2026-10-20