Nvidia 發佈 Nemotron 3.5 Transcribe 開放權重音訊轉錄模型
Voice AI in vogue: Nvidia releases new open transcription model
Nvidia 發佈 Nemotron 3.5 Transcribe 開放權重模型，可轉錄最多 40 種語言的音訊，並推出開源語音數據集 Granary version 2。Nvidia 表示，模型可將 31 種語言與英文互相翻譯、處理最長一小時的錄音，並分辨最多 8 位説話者。Nvidia 稱這個 30 billion parameters 模型可在單一晶片上運行，但只支援錄音、不支援即時串流。
In Brief
Posted:
8:00 AM PDT · October 28, 2026
Nvidia on Wednesday released Nemotron 3.5 Transcribe, 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.
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, to Blackwell datacenter chips. It joins Nvidia’s open-weight voice models, including the super small yet powerful Parakeet (1.1 billion parameters).
Nvidia’s latest voice entry comes during busy period of AI voice releases: Mistral shipped Voxtral 3 earlier this month; ElevenLabs launched Realtime for instant speech in voice agents; and Salesforce released Launa-Omni, its voice model.
來源：TechCrunch · AI · techcrunch.com