logo
About Contact

NVIDIA Advances Multilingual AI Capabilities with New Open-Source Speech Model and Transcription Tool

AI News

NVIDIA Advances Multilingual AI Capabilities with New Open-Source Speech Model and Transcription Tool

NVIDIA Expands Open-Source Push with Multilingual Speech Model, Massive Audio Dataset

Techstrong

NVIDIA Expands Open-Source Push with Multilingual Speech Model, Massive Audio Dataset

NVIDIA releases Nemotron 3.5 Transcribe and Granary v2, an open-weight multilingual speech model supporting 40 languages, speaker labels, and translation.

NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters

MarkTechPost

NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters

NVIDIA has released Nemotron 3.5 Transcribe, an open-weights speech LLM built for transcription. One model handles 40 languages and recordings up to 1 hour. A text instruction picks the output...

Coverage dates

First reported:

First saved on ClustZ:

Coverage updated:

We use cookies to improve your experience and analyze site traffic. By clicking "Accept", you agree to our use of cookies. See our Privacy Policy.