Nvidia has released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes recorded audio in up to 40 languages. The company also released version 2 of Granary, its open-source speech dataset.
Nvidia says the model can translate 31 languages to and from English, process recordings up to an hour long, and distinguish up to eight speakers. The company claims it outperforms rivals on benchmarks, including Hugging Face’s Open ASR Leaderboard.
The tools are aimed at developers building applications for business meetings and medical transcription. Nvidia says developers can use the model, the updated Granary dataset and tools such as NeMo Speech to customize applications to recognize industry jargon in each language.
One limitation is that Nemotron 3.5 Transcribe works with recordings, not live audio streams. Nvidia says the 30 billion-parameter model can run on a single chip, including its Jetson AGX Thor robotics controller, DGX Spark chip and Blackwell data center chips.
The release joins Nvidia’s open-weight voice models, including Parakeet, which has 1.1 billion parameters. Other recent voice releases include Mistral’s Voxtral 3, ElevenLabs’ Realtime and Salesforce’s Launa-Omni.
Comments
0No comments yet. Be the first to comment.