思源笔记 A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.

High-Quality Voice Cloning TTS for 600+ Languages

一个基于 Sherpa-ONNX 的高性能语音识别服务，支持实时VAD（语音活动检测）、多语言语音识别和声纹识别功能。

工作流开发框架FlowGram is a node-based flow building engine that helps developers quickly create workflows in either fixed layout or free connection layout modes

美团TTS

Claude Code Snapshot for Research. All original source code is the property of Anthropic.

VTable is not just a high-performance multidimensional data analysis table, but also a grid artist that creates art between rows and columns.

ginfast前端

A Vue 3 admin dashboard template using Vite + TypeScript + Element Plus | vue3 admin | vue-admin — focused on user experience and visual design.

用纯C语言实现的Qwen3-TTS推理引擎：无需Python依赖Pure C inference engine for Qwen3-TTS text-to-speech. No Python, no PyTorch — just C and BLAS. Supports 0.6B and 1.7B models, 9 voices, 10 languages.

Fast and accurate automatic speech recognition (ASR) for edge devices

欢迎使用EasyMrcp！ EasyMrcp使用java编写，目前提供了多种不同的asr和tts的集成，做到真正简单使用ASR和TTS。 现已推出最新架构2.0，已全面放弃原mrcp协议，取而代之的是简化实现的完全异步架构，部分功能正在完善中.......

AIFutureTrade

一个用于CLI Proxy API 批量账号管理的工具（暂时只支持codex）：Cliproxy Account Cleaner

Multi-dimensional table solution developed based on Vue 3 ｜ vue3实现的多维表格解决方案

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …

现代化、原生体验的数据库管理工具，支持 MySQL、PostgreSQL、SQLite 等数据库，采用 Go 后端 + Wails + React 前端构建，启动快、体积小、性能强。

RTCPilot is an open-source WebRTC SFU (Selective Forwarding Unit) implemented in modern C++. support win11/linux/macos

Voice Agent = Voice Interaction + Large Language Model Agent It is not an ordinary voice assistant, but an AI that can understand you, think, and proactively help you complete tasks.

蚂蚁集团开源Ming-omni-tts：一个模型搞定语音+音乐+音效，粤语控制准确率93%Ming-omni-tts: Simple and Efficient Unified Generation of Speech, Music, and Sound with Precise Control

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state m…

流程图 Make beautiful isometric infrastructure diagrams

The open-source voice synthesis studio powered by Qwen3-TTS.

Streaming speech recognition running natively and in the browser. A pure Rust implementation of Mistral's Voxtral Mini 4B Realtime model using the Burn ML framework.

A native desktop GUI for Claude Code — chat, code, and manage projects visually. Built with Electron + Next.js.

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …

Speech recognition API service powered by FunASR and Qwen-ASR, supporting 52 languages, compatible with OpenAI API and Alibaba Cloud Speech API. 基于 FunASR 与 Qwen3-ASR 的语音识别 API 服务，支持 52 种语言，兼容 Open…

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

🍭 Lobe UI - an open-source UI component library for building AIGC web apps