Awesome GitHub RepositoriesFrame Extractors

Bodymovin is a motion graphics pipeline tool and plugin that exports After Effects animations into JSON files for native rendering on web and mobile platforms. It serves as a cross-platform animation bridge, converting complex vector motion designs into a portable Lottie format for use across different operating systems and frameworks. The project enables high-performance web animation by rendering motion graphics using SVG, Canvas, or HTML. It ensures consistent playback across diverse environments by converting dynamic expressions into static keyframes during the export process. The toolse

Graphite is a node-based visual design environment that integrates vector illustration, raster image processing, and motion graphics generation into a single platform. It utilizes a functional reactive pipeline and a data-flow execution model to propagate state changes through a graph of interconnected nodes, allowing users to construct complex, automated design workflows. The platform distinguishes itself through a context-aware evaluation engine that injects runtime metadata—such as coordinate data and loop indices—directly into the node graph. This enables the creation of procedural geomet

Wav2Lip is a deep learning lip sync model and neural talking head framework designed to synchronize the lip movements in a video to match a provided audio file. It functions as a computer vision lip synchronizer and speech-to-lip generator that maps speech patterns to visual mouth movements to produce realistic talking head videos. The system utilizes a framework for training and evaluating models that align audio and video frames. This includes the ability to train lip-sync models and visual discriminators using speech-to-lip datasets and evaluating the resulting synchronization accuracy thr

ImageGlass is a lightweight image viewer and editor designed for Windows environments. It provides a unified interface for displaying a wide range of file types, including raw camera files, vector graphics, and web formats, while offering tools for basic image transformation and metadata inspection. The application distinguishes itself through deep integration with the host operating system, including the ability to synchronize its internal viewing order with the file explorer's sorting state. It supports complex media by providing playback controls for multi-frame and animated files, allowin

This project is an end-to-end text-to-speech engine and deep learning voice synthesizer. It functions as a neural speech synthesis framework that converts written text directly into audio waveforms using a single neural network. The system implements an adversarial framework and a conditional variational autoencoder to generate high-fidelity artificial speech. It utilizes a generative adversarial network to ensure synthesized audio is indistinguishable from real human speech. The toolkit provides capabilities for neural speech synthesis, text-to-audio generation, and the training of custom v

Hotwire Turbo is a server-driven navigation and HTML streaming framework that intercepts link clicks and form submissions to fetch pages in the background and replace content without full browser reloads. It provides a Turbo Frame component that scopes page regions into independent contexts, enabling partial page updates where only a specific area of the page navigates or loads content. The framework includes a page cache and morph system that stores recently visited pages for instant restoration and applies minimal DOM changes on refresh, preserving scroll position and element state. The fra

Dejavu is a Python audio fingerprinting library and recognition engine. It functions as a digital audio signature tool used to analyze sound waves and create unique identifiers for the purposes of audio search and retrieval. The project enables automatic music identification by matching live audio feeds or recorded clips against a database of fingerprints. It covers audio content matching and digital audio archiving to identify original source recordings from a stored collection. The system incorporates capabilities for generating audio fingerprints, identifying audio tracks, and recognizing

Ardour 是一个数字音频工作站（DAW）、多轨音频混音器和 MIDI 音序器。它作为一个非线性音频编辑器和用于运行第三方效果器和乐器的插件宿主。 该系统为后期制作音频配乐提供了专门的功能，包括视频帧同步，以及用于实时触发片段和模式的现场表演音序功能。它还支持通过控制界面映射和硬件控制器配置进行触控混音。 该软件涵盖了广泛的音频制作需求，包括多轨录音、MIDI 音序与编曲、专业混音以及多声道音频导出。其处理框架包括行业标准的插件支持和矩阵式信号路由系统。

VITS-fast-fine-tuning 是一个使用小型音频数据集将语音合成模型适配到特定目标音色的流水线。它充当快速说话人适配工具和多语言语音合成器，能够生成跨不同语言的口语音频。 该系统提供了一个用于多对多语音转换的框架，在保留原始语言内容的同时转换说话人的身份。它允许通过使用音频片段或视频源微调预训练模型来适配文本转语音的音色。 该项目涵盖端到端语音合成和音频处理，利用对抗性波形生成和单调对齐搜索来产生高保真音频。它结合了随机持续时间预测器来管理说话节奏的变化，并支持预训练模型迁移。

Chafa is a terminal graphics library that converts images and animated GIFs into character art for display in terminal emulators. It supports multiple output formats including ANSI escape sequences, Sixel graphics, and Unicode block characters, making it a versatile tool for rendering images directly within the terminal environment. The library is built as a shared C library with official bindings for Python and JavaScript, allowing developers to integrate terminal image rendering capabilities into applications across different programming environments. Chafa handles the full pipeline from im

GPAC is an open-source multimedia framework built around a pluggable filter graph pipeline, where modular processing units called filters connect into a directed graph to handle media workflows. At its core, the framework centers all media packaging and manipulation on the ISO Base Media File Format (ISOBMFF), with specialized tools for reading, writing, fragmenting, and encrypting MP4 and related containers. It also provides a declarative scene graph composition system for describing interactive multimedia scenes using MPEG-4 BIFS, X3D, SVG, or VRML syntax, alongside a hardware-accelerated re

Intro Skipper is a media server plugin and automated playback utility designed to identify and bypass television opening sequences. It functions as an automated content sequence skipper that detects repeated introduction segments in video files to improve viewing efficiency. The tool employs audio fingerprinting to analyze audio patterns during playback, comparing waveforms against known templates to trigger skip events. It allows for the management of playback preferences across multiple client devices to determine how these opening sequences are handled. The project covers automated media