Nemotron OCR v2 is a state-of-the-art multilingual text recognition model designed for robust end-to-end optical character recognition (OCR) on complex real-world images.

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top ...

Removes unwanted noises from audio improving speech intelligibility. Background Noise Removal (BNR) is an audio background noise removal model from NVIDIA. BNR removes unwanted noises from audio, ...

Mistral Large 4 is a multimodal Mixture-of-Experts model from Mistral AI that accepts text and images and generates text for instruction following, reasoning, coding, and agentic workflows. It has ...

Mistral Large 4 from Mistral AI, a 1T-total / 52B-active granular MoE for text and image input with reasoning, function calling and structured outputs, served in NVFP4 with DSpark speculative decoding ...

document parsing supported language - english text and table extraction Get API Key ExperienceExperience Model CardModel Card DeployDeploy API ReferenceAPI Reference Accelerated by DGX Cloud TryTry ...

Sorry, your browser does not support inline SVG. Sorry, your browser does not support inline SVG. Are all models free to use? All models on build.nvidia.com are free ...

Robust Speech Recognition via Large-Scale Weak Supervision.

Natural and expressive voices in 23 languages. For voice agents and brand ambassadors. Chatterbox Speech Generation TTS multilingual Text-to-Speech Get API Key ExperienceExperience Model CardModel ...

Sorry, your browser does not support inline SVG.

Use NVIDIA Sync Cluster Assistant to connect your nodes. It is the recommended path: it handles the cabling checks, interface configuration, and passwordless SSH for you. If Cluster Assistant ...