本文へ移動
AI NEWS JOURNAL
TechCrunch · AIAI NEWS / JOURNAL

注目の音声AI:NVIDIAが新しいオープンな文字起こしモデルを公開

Nvidiaは、最大40言語を文字起こしできる無料の音声認識モデルを発表しましたが、これは録音データにのみ対応しており、リアルタイムの音声には対応していません。そのため、会議や医療分野の文字起こしツールにとっては大きな進展ですが、リアルタイムでの利用については、ElevenLabsなどの競合に依然として譲る形となっています。

翻訳サービスが停止中のため原文を表示しています。

Julie Bort

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.

Buy One Pass, Get a Second FreeCover more ground at TechCrunch’s ultimate founder bootcamp of the year by bringing your co-founder or partner for freeBook before the BOGO deal expires

Newsletters

Subscribe for the industry’s biggest tech news

Hardware

Amazon debuts the Alexa Photo Frame and Echo Time smart clock, plus other upgraded devices

Amanda Silberling

26 minutes ago

Apps

Meta has a new AI pet app called Waddle World

Ivan Mehta

1 hour ago

Gaming

Free Fire returns to India as Garena launches localized version four years after ban

Jagmeet Singh

1 hour ago

Latest in AI

In Brief

Voice AI in vogue: Nvidia releases new open transcription model

Julie Bort

40 seconds ago

TechCrunch Founder Summit 2026

7 days until TechCrunch Founder Summit: Save up to $100 on your pass before doors open

TechCrunch Events

2 hours ago

AI

VCs will make billions on Anthropic’s IPO, but Amazon is set to make much (much) more

Marina Temkin

14 hours ago

出典

原文を読む ↗

関連テーマ

← すべてのニュースへ