Nvidia releases Nemotron 3.5 Transcribe, an open transcription model for 40 languages
Nvidia released Nemotron 3.5 Transcribe, a free open-weight model transcribing audio in up to 40 languages, alongside version 2 of its Granary speech dataset.
By GennnAi··1 min read
Nvidia says the model translates 31 languages to and from English, handles hour-long recordings and separates up to eight speakers. It targets business meetings and medical transcription, with tools to customize industry jargon. At 30 billion parameters, it runs on a single chip, but works on recorded audio, not livestreams. Nvidia claims it beats rivals on benchmarks, including Hugging Face's Open ASR Leaderboard.
Source: TechCrunch, published on October 28, 2026.