Nvidia Releases Open Transcription Model Nemotron 3.5 Transcribe

Nvidia has introduced Nemotron 3.5 Transcribe, a free, open-weight model that transcribes audio in up to 40 languages. The company also released version 2 of Granary, its open source speech dataset.

According to Nvidia, the model can translate 31 languages to and from English, handle recordings up to an hour long, and distinguish up to eight speakers. Nvidia claims it outperforms rivals on benchmarks, including Hugging Face's Open ASR Leaderboard.

The tools are aimed at developers building apps for business meetings and medical transcription, two established workplace uses for AI. Nvidia says developers can combine the model, the updated Granary dataset, and tools like its NeMo Speech model to tailor apps to recognize industry jargon in each language. One limitation: Transcribe works with recorded audio, not livestreams.

At 30 billion parameters, the company says Transcribe can run on a single chip, from the Jetson AGX Thor robotics controller and the DGX Spark chip powering new laptops to Blackwell datacenter chips. It joins Nvidia's open-weight voice models, including the smaller Parakeet at 1.1 billion parameters.

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

Source: TechCrunch