NVIDIA
Explore
Models
Blueprints
GPUs
Docs
⌘KCtrl+K
Terms of Use
Privacy Policy
Your Privacy Choices
Contact

Copyright © 2026 NVIDIA Corporation

Models

Deploy and scale models on your GPU infrastructure of choice with NVIDIA NIM inference microservices
Optimized by NVIDIALaunch from Hugging FaceBeta
Sorting by Most Recent

nvidiaBackground Noise Removal

Removes unwanted noises from audio improving speech intelligibility.

Nvidia MaxineSpeech-to-speechDigital HumanSpeech Enhancement

nvidiaaudio2face-3d

Converts streamed audio to facial blendshapes for realtime lipsyncing and facial performances.

Speech-to-AnimationDigital HumansAudio-to-FaceNVIDIA NIM

nvidiastudiovoice

Enhance speech by correcting common audio degradations to create studio quality speech output.

Nvidia MaxineSpeech-to-speechDigital HumanRun-on-RTXSpeech Enhancement

nvidiallama-3.1-nemotron-70b-reward

Leaderboard topping reward model supporting RLHF for better alignment with human preferences.

Text-to-textReward ModelRLHF

nvidiaeyecontact

Estimate gaze angles of a person in a video and redirect to make it frontal.

telepresenceNvidia MaxineDigital Human

nvidiavista-3d

VISTA-3D is a specialized interactive foundation model for segmenting and anotating human anatomies.

Interactive AnnotationImage SegmentationNon-Commercial Use OnlyMedical Imaging