Nvidia 发布 Nemotron 3.5 Transcribe 开放权重语音转录模型
Voice AI in vogue: Nvidia releases new open transcription model
Nvidia 发布开放权重转录模型 Nemotron 3.5 Transcribe，支持最多 40 种语言，并推出开源语音数据集 Granary v2。公司称，该模型可在英语与 31 种语言之间双向翻译，处理最长 1 小时录音、区分最多 8 位说话者，并在 Hugging Face Open ASR Leaderboard 等基准上超过竞争对手。
开放权重与单芯片运行范围，结合语言支持、录音时长和基准信息，为会议及医疗转录场景的模型选型提供具体参考。
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.
来源：TechCrunch · techcrunch.com