Voice AI in vogue: Nvidia releases new open transcription model

TechCrunch AI 约 6 分钟读完

Nvidia just released a free speech-to-text model that can transcribe up to 40 languages, but it only works on recordings, not live audio, so it’s a big step for meeting and medical transcription tools while still leaving real-time use to rivals like ElevenLabs.

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.

Topics

AI , In Brief , nvidia , TC

November 4

Boston

Buy One Pass, Get a Second Free

Cover more ground at TechCrunch’s ultimate founder bootcamp of the year by bringing your co-founder or partner for free

Book before the BOGO deal expires

Register Now

Newsletters

See More

Subscribe for the industry’s biggest tech news

Related

Enterprise

Microsoft hits 10 quarters of record-breaking revenue in a row

Julie Bort

6 hours ago

AI

General Compute raises $100 million Series A, countering the neocloud disaster narrative

Tim Fernholz

2 days ago

AI

Nvidia backs Indian startup helping companies run AI models with fewer GPUs

Jagmeet Singh

2 days ago

Latest in AI

Enterprise

Microsoft just shared Azure’s actual revenue in dollars: $33.2 billion

Aditya Mehta

5 hours ago

AI

Google expands AI Search ads globally as core ad growth slows

Lauren Forristal

5 hours ago

AI

Microsoft recorded $10 billion in revenue from OpenAI

Rebecca Bellan

6 hours ago

原文标题 Voice AI in vogue: Nvidia releases new open transcription model
引用来源 TechCrunch AI
本地存档 2026-10-29 11:35
引用格式 Julie Bort. Voice AI in vogue: Nvidia releases new open transcription model. 2026-10-28. https://www.ai007.site/news/62760

本文内容由 ai007 从公开渠道聚合,版权归原作者所有。若原文已删除或变更, 以原文站为准;本站存档仅为便于查阅而保留。