Nemotron 3.5 Transcribe
Collection
Open-weight offline ASR model supporting 40 languages, 1-hr audio, and 64k context. Hybrid MoE (~4.3B active). Available in BF16, FP8, and NVFP4. • 7 items • Updated • 12
Nemotron Speech
Open, state-of-the-art, production‑ready enterprise speech models from the NVIDIA Speech research team for ASR, TTS, Speaker Diarization and S2S
-
-
Magpietts Demo
🐠39Nvidia Text-to-Speech with MagpieTTS.
-
nvidia/nemotron-3.5-asr-streaming-0.6b
Automatic Speech Recognition • 0.6B • Updated • 691k • • 1.25k -
nvidia/nemotron-speech-streaming-en-0.6b
Automatic Speech Recognition • 0.6B • Updated • 97.4k • 649 -
nvidia/magpie_tts_multilingual_357m
Text-to-Speech • 0.3B • Updated • 14.5k • 239 -
nvidia/parakeet-unified-en-0.6b
Automatic Speech Recognition • Updated • 6.21k • 75 -
nvidia/personaplex-7b-v1
Audio-to-Audio • 8B • Updated • 132k • • 2.93k -
nvidia/Granary
Viewer • Updated • 113M • 6.23k • 237 -
nvidia/NVIDIA-NemotronLabs-VoiceChat-11B
11B • Updated • 4.83k • 549 -
nvidia/Granary-v2
Updated • 3.21k • 35