Voice AI in vogue: Nvidia releases new open transcription model

Nvidia released Nemotron 3.5 Transcribe on Wednesday, a free, open-weight 30-billion-parameter speech transcription model that handles audio in up to 40 languages and translates 31 languages to and from English, alongside version 2 of its open-source Granary speech dataset. Nvidia claims the model, which can distinguish up to eight speakers and process recordings up to an hour long, beats rivals on benchmarks including Hugging Face's Open ASR Leaderboard, and says it runs on a single chip ranging from the Jetson AGX Thor robotics controller and DGX Spark to Blackwell datacenter chips. The release targets developers building business-meeting and medical transcription apps, though Transcribe works only with recorded audio, not live streams.

Nvidia on Wednesday released Nemotron 3.5 Transcribe https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B , a free, open-weight model that transcribes audio in up to 40 languages. It also released version 2 of Granary, its open-source speech dataset. Nvidia boasts that Nemotron 3.5 can translate 31 languages to and from English, handle recordings up to an hour long, and tell up to eight speakers apart. It claims to beat rivals on benchmarks, including Hugging Face’s Open ASR Leaderboard https://huggingface.co/spaces/hf-audio/open asr leaderboard . These tools target developers building apps for business meetings and medical transcription, two of AI’s most established footholds in the workplace. Nvidia says developers can use the model, the updated Granary dataset, and tools like its NeMo Speech model to customize apps to recognize an industry’s jargon in each language. One drawback: Transcribe works with recorded audio, not live streams. Still, the company promises Transcribe, at 30 billion parameters, can run on a single chip, from the Jetson AGX Thor robotics controller and DGX Spark chip powering new laptops https://techcrunch.com/2026/10/07/microsoft-releases-new-nvidia-chip-ai-pcs-with-revamped-windows-11/ , to Blackwell datacenter chips. It joins Nvidia’s open-weight voice models, including the super small yet powerful Parakeet https://build.nvidia.com/nvidia/parakeet-1 1b-rnnt-multilingual-asr/modelcard 1.1 billion parameters . Nvidia’s latest voice entry comes during busy period of AI voice releases: Mistral shipped Voxtral 3 https://x.com/MistralAI/status/2112574615318876178 earlier this month; ElevenLabs launched Realtime for instant speech in voice agents; and Salesforce released Launa-Omni, https://www.salesforce.com/blog/launa-omni/ its voice model.