一个开箱即用的、跨平台的影视聚合播放站

Turn detection for full-duplex dialogue communication

Open-source framework for conversational voice AI agents.

🚀 全网效果最好的移动端【实时对话数字人】。 支持本地部署、多模态交互（语音、文本、表情），响应速度低于 1.5 秒，适用于直播、教学、客服、金融、政务等对隐私与实时性要求极高的场景。开箱即用，开发者友好。

SRS is a simple, high-efficiency, real-time media server supporting RTMP, WebRTC, HLS, HTTP-FLV, HTTP-TS, SRT, MPEG-DASH, and GB28181.

一行代码实现Android屏幕采集并编码H264

每个人都能用的数字人

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

科技爱好者周刊，每周五发布

Bring portraits to life!

一个超轻量级、可以在移动端实时运行的数字人模型

[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

Start building LLM-empowered multi-agent applications in an easier way.

MiniCPM-o 2.6: A GPT-4o Level MLLM for Vision, Speech and Multimodal Live Streaming on Your Phone

游戏种子合集

Try to do Acoustic Echo Cancellation on Android with AEC modules from Speex and WebRTC.

Android Voice Activity Detection (VAD) library. Supports WebRTC VAD GMM, Silero VAD DNN, Yamnet VAD DNN models.

Android Serial Port Assistant - Android 串口助手

ADB in your browser

在原版的基础上修改了显示 VLESS 配置信息转换为订阅内容。使用该脚本，你可以方便地将 VLESS 配置信息使用在线配置转换到 Clash 或 Singbox 等工具中。

every websites have been tested and fixed, all can be running in localhost. After clone the repository enter the website's folder, simply start a local HTTP server such as live-server to run the we…

肖像大师 中文版 comfyui-portrait-master

[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers

Live2D Virtual Human for Chatting based on Unity

使用AudioTrack和Jlayer播放AES加密的MP3音频流（非文件）

A demo implementation of Unity Entity Component System with NavMesh

An simple and optimized grid pathfinding

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…