Nvidia releases free open model that transcribes 40 languages

Nvidia has released Nemotron 3.5 Transcribe, a free, open-weight speech-to-text model covering up to 40 languages. It can translate 31 languages to and from English, handle hour-long recordings and distinguish up to eight speakers. The 30-billion-parameter model runs on a single chip but works only on recorded audio, not live streams, targeting meeting and medical transcription.