1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Build your own AI friend

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.

Robust Speech Recognition via Large-Scale Weak Supervision

一套移动端高性能高可用的动态化跨端开发框架

Visual Studio Code

🍀 HuLa是一款基于Tauri+Vue3的桌面即时通讯应用程序（不仅仅是即时通讯）

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

Make websites accessible for AI agents

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

使用Python PyQt制作的Scrcpy GUI版本

Python for Windows (pywin32) Extensions

前端低代码框架，通过 JSON 配置就能生成各种页面。

An enterprise-class low-code technology stack with scale-out design / 一套面向扩展设计的企业级低代码技术体系

Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.

写的更少, 性能更好 -> 为开发人员打造的低代码开发平台。mybatis-plus关联查询，关联无SQL，性能高10倍，前后端代码本地可视化生成，flowable工作流，spring cloud微服务等全方位赋能！

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

visual basic 6.0

The most advanced responsive front-end framework in the world. Quickly create prototypes and production code for sites that work on any kind of device.