Stars
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
💬 DialogX dialog box component library, easy to use, more customizable, more scalable, easy to achieve a variety of dialog boxes. DialogX对话框组件库，更加方便易用，可自定义程度更高，扩展性更强，轻松实现各种对话框、菜单和提示效果，更有Material Yo…
ESP32 BLE HID Keyboard, Abs Mouse, and Two-Way Communication Library Esp32蓝牙HID键盘鼠标触摸屏双向通信库
blackketter / ESP32-BLE-Combo
Forked from T-vK/ESP32-BLE-KeyboardBluetooth LE Keyboard library for the ESP32 (Arduino IDE compatible)
Bluetooth LE Gamepad library for the ESP32
🖼️ Image Toolbox is a powerful app for advanced image manipulation. It offers dozens of features, from basic tools like crop and draw to filters, OCR, and a wide range of image processing options
Real-time speech recognition and voice activity detection (VAD) using next-gen Kaldi with ncnn without Internet connection. Support iOS, Android, Linux, macOS, Windows, Raspberry Pi, VisionFive2, L…
The official Java library for the OpenAI API
Jetpack Media3 support libraries for media use cases, including ExoPlayer, an extensible media player for Android
Edge-TTS for Android is a text-to-speech service that uses the Edge-TTS API to convert text to speech.
🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT多轮对话能力，还可能是首个支持脑机交互的开源智能音箱项目。
这是一个Android系统TTS应用，内置微软演示接口，可自定义HTTP请求，可导入其他本地TTS引擎，以及根据中文双引号的简单旁白/对话识别朗读 ，还有自动重试，备用配置，文本替换等更多功能。
🚀 The fast, Pythonic way to build MCP servers and clients
A Repository for Single- and Multi-modal Speaker Verification, Speaker Recognition and Speaker Diarization
本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
HAL for the CH583/CH582/CH581 family of microcontrollers. BLE 5.3, RISC-V Qingke V4.
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
real time face swap and one-click video deepfake with only a single image
An Open Source YouTube app for privacy