NVIDIA Broadcast Alternatives

NoiseTorch is a cross-platform audio processor and real-time noise filter designed to suppress ambient sound from audio streams. It functions as a virtual microphone noise suppressor and routing tool, capturing system audio sources and directing filtered signals into virtual input or output devices. The application uses a recurrent neural network to distinguish between human speech and ambient noise. It provides a virtual denoising microphone that removes background noise from a selected input, alongside tools for filtering audio output streams. The system includes capabilities for audio dev

This project is a macOS system camera driver and software plugin that exposes software video streams as hardware-recognized camera inputs. It functions as an OBS virtual camera plugin, allowing the live output of OBS to be utilized as a webcam device within other applications. The tool enables the routing of composited video from a production suite into video conferencing applications such as Zoom or Google Meet. This allows for the streaming of processed scenes instead of a raw webcam feed. The system integrates with macOS using a kernel-level device driver and shared-memory buffer transfer

This project is an OBS-based streaming software and live broadcast engine designed for capturing and transmitting real-time audio and video content to online platforms. It functions as a content distribution tool and a cross-platform desktop application that manages the encoding and transmission of multimedia streams from a computer. The software utilizes an OBS-based engine to handle desktop content capture, including screen activity, application windows, and webcam feeds. It provides the necessary infrastructure to manage complex broadcast layouts and scenes for live audiences. The system

Avatarify-python is a real-time face animation tool that uses a PyTorch-based neural network to map facial movements from a live camera feed onto a static image. It creates photorealistic animated avatars that mimic a user's movements for use in video software. The project includes a remote GPU inference client that offloads heavy computational workloads to a remote server, allowing high-performance animations to run on low-spec hardware. It also features a virtual webcam driver to route synthetic video streams into video conferencing applications as a standard camera device. The system prov

DeepFilterNet is a deep learning noise suppression framework and real-time audio filter designed to isolate speech and remove background noise from audio signals. It functions as a speech enhancement tool and audio processing middleware that cleans microphone input and speaker output for communication applications. The system operates as an audio server interceptor, delivering noise-suppressed streams between hardware devices and software applications. It provides capabilities for microphone signal cleaning and audio output filtering, including the creation of virtual noise-suppressed microph

StreamFX-Public is a collection of OBS Studio plugins and software components designed for broadcast enhancement. It provides a suite of visual effects, filters, hardware-accelerated encoders, and professional video encoding tools to expand the capabilities of the host application. The project distinguishes itself through the support of professional mezzanine video codecs, including DNxHR, ProRes, and Cineform, for high-fidelity post-production editing. It also implements hardware-accelerated recording via GPU cores and AMD AMF to reduce CPU overhead during live broadcasts. The toolset cover

EasyEffects is a real-time audio processor and system-wide effects manager designed for PipeWire audio streams. It functions as a comprehensive suite for applying filters, equalizers, and limiters to both input and output audio across the entire system. The project distinguishes itself through its use of deep learning for neural network noise suppression and voice isolation, as well as its ability to simulate physical acoustic environments using impulse-response convolution. It includes a sophisticated preset management system that allows users to associate specific audio configurations with

DeepFaceLive is a desktop application designed for real-time facial replacement and animation within live video streams. By utilizing deep learning models, the software performs high-speed identity mapping and facial feature analysis to transform video content as it is captured. The engine relies on GPU-accelerated inference to execute these complex image manipulation tasks at interactive frame rates. The application distinguishes itself through a modular video processing pipeline that chains specialized tasks to maintain high throughput and low latency. It features a virtual camera streaming

BackgroundMattingV2 is a deep learning background matting tool and real-time image segmentation framework. It provides a system for isolating foreground subjects from high-resolution images and video feeds in real time. The project includes a deep learning model trainer for optimizing matting models through base convergence and end-to-end refinement. It also functions as a cross-runtime model exporter, converting trained neural networks into interchangeable formats for deployment across different software environments and hardware runtimes. The framework supports streaming processed webcam f

This project is a GPU-accelerated speech engine and AI voice cloning tool. It functions as a text-to-speech synthesizer and voice-to-voice converter that replicates specific human voices to generate synthetic speech. The system creates digital voice profiles by analyzing short audio samples or capturing live microphone input. These profiles enable the transformation of existing audio recordings into a target speaker's voice or the synthesis of new audio from written text. The engine supports subtitle-based speech generation for batch processing and automated dubbing workflows. A web-based au

waifu2x-ncnn-vulkan is an AI super-resolution tool and image processor that uses deep learning to increase image resolution and remove visual noise. It is an NCNN-based implementation designed for efficient neural network inference on local hardware. The project utilizes the Vulkan API to provide GPU-accelerated image scaling and noise reduction across diverse graphics hardware. It employs tiled image processing to prevent GPU memory overflow and multi-threaded model loading to reduce initial startup latency. The software covers functional domains including AI image upscaling for maintaining