Nvidia has released Nemotron 3.5 Transcribe, a free, open-weight model that transcribes audio in up to 40 languages. The company also published version 2 of Granary, its open source speech dataset. According to Nvidia, Nemotron 3.5 can translate 31 languages to and from English, handle recordings up to an hour long, and distinguish up to eight speakers. The company claims the model beats rivals on benchmarks, including Hugging Face’s Open ASR Leaderboard.

The tools are aimed at developers building applications for business meetings and medical transcription, two established workplace use cases for AI. Nvidia says developers can combine the model with the updated Granary dataset and tools such as its NeMo Speech model to customize apps to recognize industry-specific jargon in each language.

One stated limitation is that Transcribe works with recorded audio, not livestreams. Nvidia promises that the 30-billion-parameter model can run on a single chip, from the Jetson AGX Thor robotics controller and DGX Spark chip powering new laptops to Blackwell datacenter chips. It joins Nvidia‘s open-weight voice models, including the much smaller Parakeet, which has 1.1 billion parameters.

The release lands during a busy period for AI voice models: Mistral shipped Voxtral 3 earlier this month, ElevenLabs launched Realtime for instant speech in voice agents, and Salesforce released Launa-Omni.