Nvidia releases open transcription model Nemotron 3.5 Transcribe

Nvidia released Nemotron 3.5 Transcribe, a free open-weight model that transcribes audio in up to 40 languages. The 30-billion-parameter model translates 31 languages to and from English, distinguishes up to eight speakers and handles recordings up to an hour long, but does not support live streams.

• Transcribes speech in up to 40 languages and translates 31 languages to and from English
• Tells apart up to eight speakers and handles recordings up to an hour long
• 30 billion parameters, runs on a single chip from Jetson AGX Thor to Blackwell
• Ships alongside version 2 of the open Granary speech dataset