Nemotron 3.5 Transcribe: NVIDIA’s free model for recordings in 40 languages
The open model transcribes recordings of up to an hour, tells up to eight speakers apart and translates 31 languages. It doesn’t handle live audio.
Nemotron
NVIDIA’s family of open models, including speech recognition.
- Category
- Audio & voice
- Made by
- NVIDIA
- Official site
- www.nvidia.com