Key facts
- Nemotron 3.5 Transcribe supports up to 40 languages.
- The model can translate 31 languages to and from English.
- Nemotron 3.5 can process recordings up to an hour long.
- It can distinguish up to eight speakers.
- The model has 30 billion parameters and can run on a single chip.
Nvidia released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes audio in up to 40 languages, on Wednesday, October 28, 2026. The company also launched version 2 of Granary, its open-source speech dataset. Nemotron 3.5 can translate 31 languages to and from English, handle recordings up to an hour long, and distinguish up to eight speakers. Nvidia claims the model, with 30 billion parameters, can run on a single chip and outperforms rivals on benchmarks like Hugging Face’s Open ASR Leaderboard. The tools are aimed at developers building business meeting and medical transcription applications.