Starred repositories
小皮AI直播机器人 硬件+私有服务器解决方案 (XiaoPi)是一个将直播弹幕与AI硬件语音交互结合的解决方案。它能够： - 📺 实时接收直播间弹幕消息 - 🤖 使用大语言模型(LLM)生成智能回复 - 🔊 将回复转换为语音(TTS) - 📡 发送到ESP32等硬件设备进行播放 - 🎯 支持串行化处理，避免弹幕堆积
This is a folk of og ComfyUI-WanVideoWrapper by kijai but it works on mac
Open-source framework for conversational voice AI agents
Turn boring papers into fun comics with the help of Gemini!
General purpose 3D and 2D game engine using Go (golang) and Vulkan with built in editor
GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning
6B parameter image gen that actually runs fast on your Mac. 14 seconds. No cloud. No GPU rental.
real time face swap and one-click video deepfake with only a single image
LAION research paper dataset visual explorer 🔬 🧑🔬 👩🔬
Go (Golang) client for Deepseek API. Deepseek Go supports DeepSeek-V3, DeepSeek-R1 and more
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.
Rust multi‑backend OCR/VLM engine (DeepSeek‑OCR, PaddleOCR‑VL, DotsOCR) with DSQ quantization and an OpenAI‑compatible server & CLI – run locally without Python.
一键监控今日头条、百度热搜、微博、抖音、知乎、B站等35个平台，智能关键词筛选，自动生成热点分析报告。支持企业微信、飞书、钉钉、Telegram推送，30秒网页部署，1分钟手机通知，无需编程基础。还有文字和图片版api可调用
🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.
Go 学习、Go 进阶、Go 实用工具类、Go DDD 项目落地、Go-kit 、Go-Micro 、Go 推送平台、微服务实践
Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)
Lightweight ComfyUI wrapper for IndexTTS 2 (voice cloning + emotion control). The nodes call the original IndexTTS2 inference and keep behavior faithful to the repo.
ComfyUI custom node for the VibeVoice TTS. Expressive, long-form, multi-speaker conversational audio
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"