Projects and exercises for the latest Deep Learning ND program https://www.udacity.com/course/deep-learning-nanodegree--nd101

Sync local Codex Desktop conversation history back to the current provider

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

A disperser vst/clap plugin that made with `i_am_dsp`

Next waveshaper plugin (VST3/CLAP), written in Rust

REAPER C/C++ extension SDK

Personal conclusion for reaper .RPP file key mapping rules and value meanings

Formula Recognition & Office Editing Math Workspace | Handwriting & PDF to LaTeX/Markdown, powered by MathCraft OCR & MathLive

Skills for Real Engineers. Straight from my .agents directory.

Fish's custom settings and tools about claude code, codex, oh-my-pi etc

b站自动录播+歌切+上传脚本，支持docker部署

Say goodbye to the complex, verbose, and laggy interaction mode of IDA Pro MCP

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

A native Android audio player that combines multi-source streaming, local control, rich lyrics, and self-hosted sync. / ✨ 一个把多源在线播放、本地管理、歌词体验和自建同步做进原生 Android 的音频播放器 🎵

Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.

Weighs the soul of incoming HTTP requests to stop AI crawlers

C++ polyphonic pitch/time library (GitHub mirror)

A C++ library for time-stretching and pitch-shifting audio with high quality in realtime or offline.

reverse engineering Gemini's SynthID detection

"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026 Conference Paper)

AI Vtuber是一个由 【ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达/千问/kimi/ollama】 驱动的虚拟主播【Live2D/UE/xuniren】，可以在 【Bilibili/抖音/快手/微信视频号/拼多多/斗鱼/YouTube/twitch/TikTok】 直播中与观众实时互动 或 直接在本地进行聊…

Real-time audio translation, captures system audio + mic, runs ASR (Whisper/SenseVoice), translates via LLM API with streaming display. Perfect for VTubers, livestreamers, and watching foreign cont…

cs598lmz

HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

a base AI SVS Model Training Dataset and support files for the Greek language, used to train "A-MAIN -DS MODE-"

public male singing voice dataset

stb single-file public domain libraries for C/C++

Python Audio Effects