Nvidia on Wednesday, October 28 released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes audio in up to 40 languages. It also released version 2 of Granary, its open source speech dataset.

Nvidia says Nemotron 3.5 can translate 31 languages to and from English, handle recordings up to an hour long, and tell up to eight speakers apart. It claims the model beats rivals on benchmarks including Hugging Face's Open ASR Leaderboard, and targets developers building apps for business meetings and medical transcription.

One drawback is that Transcribe works with recorded audio, not livestreams. At 30 billion parameters, Nvidia says it can run on a single chip, from the Jetson AGX Thor robotics controller and DGX Spark to Blackwell datacenter chips.