# Video and Audio Solutions NVIDIA’s AI-powered SDKs for building GPU-accelerated multimedia processing applications provide real-time solutions for enhancing, modifying, and optimizing audio and video quality. Packaged into two core live streaming and video conferencing products— [NVIDIA Broadcast Engine](https://developer.nvidia.com/broadcast-engine) and [NVIDIA Maxine™](https://developer.nvidia.com/maxine)—these SDKS enable developers to improve live streaming, content creation, and video conferencing applications and platforms. ### Face and Body Tracking The [AR SDK](https://developer.nvidia.com/broadcast-engine/ar-sdk) allows developers to enable real-time 3D tracking of a person’s face and body using a standard web camera, creating fun and engaging augmented reality (AR) effects. [Get Started with AR SDK](https://developer.nvidia.com/broadcast-engine/ar-sdk) ### Audio Enhancements With the [Audio Effects SDK](https://developer.nvidia.com/broadcast-engine/audio-effects-sdk), developers can utilize AI to remove distracting background noise, isolating human speech in audio from incoming and/or outgoing audio feeds. [Get Started with Audio Effects SDK](https://developer.nvidia.com/broadcast-engine/audio-effects-sdk) ### Super Resolution and Virtual Backgrounds The [Video Effects SDK](https://developer.nvidia.com/broadcast-engine/video-effects-sdk) allows developers to utilize AI to upscale video resolution in real time and provide virtual backgrounds, optimize the viewing experience. [Get Started with Video Effects SDK](https://developer.nvidia.com/broadcast-engine/video-effects-sdk) ### Video and Image Analytics The [DeepStream SDK](https://developer.nvidia.com/deepstream-sdk) delivers a complete streaming analytics toolkit for AI-based multi-sensor processing and video and image understanding. [Get Started with Deepstream SDK](https://developer.nvidia.com/deepstream-sdk) ### Conversational AI The [Riva SDK](https://developer.nvidia.com/riva) is an application framework for multimodal conversational AI services that delivers real-time performance on GPUs. [Get Started with Riva SDK](https://developer.nvidia.com/riva) ### Facial Animation from Voice The [Audio2Face SDK](https://www.nvidia.com/en-us/design-visualization/omniverse/audio2face/) is an AI-powered application that generates expressive facial animation from just an audio source. [Get Started with Audio2face SDK](https://www.nvidia.com/en-us/design-visualization/omniverse/audio2face/) ### Live Streaming for Windows Machines [NVIDIA Broadcast Engine](https://developer.nvidia.com/broadcast-engine) is a suite of SDKs that provides AI-powered features for broadcasting, content creation, and video conferencing to developers utilizing AI on local Windows machines. [Learn More](https://developer.nvidia.com/broadcast-engine) ### Platform for Cloud-Based Video Conferencing [NVIDIA Maxine](https://developer.nvidia.com/maxine) is a fully accelerated platform SDK for building and deploying AI-powered video conferencing features using state-of-the-art models in the cloud. [Learn More](https://developer.nvidia.com/maxine) ## Display and Output Technologies View a collection of products for creating optimized GPU-accelerated applications for any type of display. These products enable developers to improve the delivery and synchronization of their visual applications. [Learn More](https://developer.nvidia.com/display-and-output-solutions) ## Core Video Technologies Explore the hardware-accelerated technology that serves as the foundation for all video solutions. Taking advantage of the latest NVIDIA architecture, this technology frees up the GPU and CPU for other operations, providing more computational power for developers to create their applications. ### Video Encode and Decode The [Video Codec SDK](https://developer.nvidia.com/nvidia-video-codec-sdk) is a comprehensive set of APIs, including high-performance tools, samples, and documentation for hardware-accelerated video encode and decode on Windows and Linux. [Learn More](https://developer.nvidia.com/nvidia-video-codec-sdk) ### Graphics and Compute The [Vulkan API](https://developer.nvidia.com/vulkan) is a new-generation graphics and compute open-standard API that provides high-efficiency, cross-platform access to modern GPUs. [Learn More](https://developer.nvidia.com/vulkan) ### Accurate Flow Vectors The [Optical Flow SDK](https://developer.nvidia.com/opticalflow-sdk) uses sophisticated algorithms to yield highly accurate flow vectors, which are robust to frame-to-frame intensity variations and can track true object motion. [Learn More](https://developer.nvidia.com/opticalflow-sdk) ### High-Performance Data Transfer The [Rivermax SDK](https://developer.nvidia.com/networking/rivermax) enables direct data transfers to and from the GPU, delivering best-in-class throughput and latency with minimal CPU utilization for streaming workloads. [Learn More](https://developer.nvidia.com/networking/rivermax) ### Accelerated Game Asset Loading and Decompression [NVIDIA RTX™ IO](https://www.nvidia.com/en-us/geforce/news/rtx-io-gpu-accelerated-storage-technology/) enables rapid GPU-based loading and game asset decompression, accelerating IO performance by up to 100X compared to hard drives and traditional storage APIs. [Learn More](https://www.nvidia.com/en-us/geforce/news/rtx-io-gpu-accelerated-storage-technology/) ### Low-Latency IO and GPU/CPU Synchronization [GPUDirect® for Video](https://developer.nvidia.com/gpudirectforvideo) allows third-party hardware to efficiently communicate with NVIDIA GPUs and minimize historical latency issues by synchronizing IO devices with the GPU and CPU. [Learn More](https://developer.nvidia.com/gpudirectforvideo) ### Direct Transfer Between GPU and Storage [GPUDirect Storage](https://developer.nvidia.com/gpudirect-storage) enables a direct data path for direct memory access (DMA) transfers between GPU memory and storage, which avoids a bounce buffer through the CPU. [Learn More](https://developer.nvidia.com/gpudirect-storage) ### Neural Network Trainer The [Data Loading Library](https://developer.nvidia.com/dali) reduces latency and training time by overlapping training and pre-processing when decoding and augmenting images, videos, and speech. [Learn More](https://developer.nvidia.com/dali) ### Accelerated Video and Image Processing The [Performance Primitives](https://developer.nvidia.com/npp) library provides GPU-accelerated image, video, and signal processing functions that perform up to 30X faster than CPU-only implementations. [Learn More](https://developer.nvidia.com/npp) ### Low-Latency Image Decoding The [nvJPEG](https://developer.nvidia.com/nvjpeg) libraries provide low-latency decoding, encoding, and transcoding for common JPEG formats used in computer vision applications, such as image classification/segmentation and object detection. [Learn More](https://developer.nvidia.com/nvjpeg)