Voice AI in vogue: Nvidia releases new open transcription model

Nvidia released Nemotron 3.5 Transcribe, a free, open-weight model that can transcribe up to 40 languages, including 31 languages that can be translated to and from English. The model can handle recordings up to an hour long and can tell up to eight speakers apart. It can run on a single chip, including the Jetson AGX Thor robotics controller, DGX Spark chip, and Blackwell datacenter chips. It is targeted at developers building apps for business meetings and medical transcription.