英伟达发布开源语音转写模型 Nemotron 3.5 Transcribe
Voice AI in vogue: Nvidia releases new open transcription model
英伟达发布开源语音转写模型 Nemotron 3.5 Transcribe，支持 40 种语言转写，含 30 亿参数，可在 Jetson AGX Thor 和 DGX Spark 芯片上运行。该模型能翻译 31 种语言、区分 8 个说话人，并在 Hugging Face Open ASR Leaderboard 基准测试中超越竞品，但仅支持录制音频。
同一件事另外 3 家也报道了
- TechCrunch · AI··首发·当前阅读
英伟达发布开源语音转写模型 Nemotron 3.5 Transcribe
- The Decoder··+50 分钟
- MarkTechPost··+13 小时 41 分
NVIDIA 发布 Nemotron 3.5 Transcribe 开源语音模型，支持 40 种语言转写
新增信息：活跃参数约4B；离线运行
- IT之家 · AI··+16 小时 31 分
按发布时间排列 · 事件后续出现时自动追加 · 由模型根据各家标题与摘要比对
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 livestreams.
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 a 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 · AI · techcrunch.com