Radar

Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles.

Enter text and upload a reference audio to create a synthesized speech that matches the speaker's voice and chosen style. Supports English and Chinese.

Upload a source image and audio file to create a video of the image's face moving and speaking as if it were saying the audio. You can also use reference videos to enhance the animation.

MiniMax M2.1, a SOTA model for real-world dev & agents.

ACE-Step: A Step Towards Music Generation Foundation Model

Code for a proof of concept for OMR (Optical Mark Recognition) using opensource tools

基于AI的图片/视频硬字幕去除、文本水印去除，无损分辨率生成去字幕、去水印后的图片/视频文件。无需申请第三方API，本地实现。AI-based tool for removing hard-coded subtitles and text-like watermarks from videos or Pictures.

完全本地的AI小说视频生成工作流，每个人都能成为导演！

A random walk voice style cloning application for Kokoro text to speech

Calligrapher: Freestyle Text Image Customization

ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloads, seamless closed LLM integration, and offline-first RAG knowledge bases, ARGO becomes a DeepResearch powerhouse for autonomous thinking, task planning, and 100% of your data stays locally. Support Win/Mac/Docker.

Open-source, accurate and easy-to-use video speech recognition & clipping tool, LLM based AI clipping intergrated.

Tesseract Open Source OCR Engine (main repository)

A Windows app to debloat and optimize your PC

The desktop app for ComfyUI (Windows & macOS)

Contribute to cocktailpeanut/kohya_ss development by creating an account on GitHub.

[ICCV'25 Best Paper Candidate] Official Implementations for Paper: Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows.

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

A complete browser-based reverse engineering platform built on Rizin, running entirely client-side via WebAssembly.