Nvidia releases open-weight Nemotron 3.5 Transcribe speech-to-text model
Editorial responsibility
- No named human review is recorded for this page.
- Source reporting is collected, normalized, translated or condensed automatically when needed.
- Automatically published source-backed update
Nvidia released Nemotron 3.5 Transcribe, a free, open-weight speech-to-text model that transcribes audio in up to 40 languages and translates 31 languages to and from English. The 30-billion-parameter model can handle recordings up to an hour long, distinguish up to eight speakers, and run on a single chip, from the Jetson AGX Thor robotics controller and DGX Spark chip to Blackwell datacenter chips. Nvidia also released version 2 of its open-source Granary speech dataset. The tools target developers building business meeting and medical transcription apps, and Nvidia says developers can customize them to recognize industry jargon in each language. A drawback is that Transcribe works with recorded audio, not live streams, leaving real-time use to rivals such as ElevenLabs, which launched Realtime for instant speech in voice agents. The release comes amid a busy period of AI voice launches, including Mistral's Voxtral 3 and Salesforce's Launa-Omni.
Source report
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.
Capabilities and Performance
Nvidia boasts that Nemotron 3.5 can:
- Translate 31 languages to and from English
- Handle recordings up to an hour long
- Tell up to eight speakers apart
The company claims the model beats rivals on benchmarks, including Hugging Face's Open ASR Leaderboard.
Target Use Cases
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.
Hardware Compatibility
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).
A Busy Period for AI Voice Releases
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
- Salesforce released Launa-Omni, its voice model
Source
TechCrunchNeutral / independent
Part of this Story
Nvidia releases open-weight Nemotron 3.5 Transcribe speech model supporting 40 languages