Nvidia releases Nemotron 3.5 Transcribe, open transcription model

nvidia released nemotron 3.5 transcribe, a free open-weight model that transcribes audio in up to 40 languages. it claims to beat rivals on benchmarks, including hugging faces open asr leaderboard, and can translate 31 languages to and from english, handle recordings up to an hour long, and tell up to eight speakers apart. the model targets developers building apps for business meetings and medical transcription. nemotron 3.5 can run on a single chip, from the jetson agx thor robotics controller and dgx spark chip powering new laptops, to blackwell datacenter chips.