Lists (2)
Starred repositories
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.......
Open source cross-platform implementation of MRCP protocol
使用FreeSWITCH接受用户手机呼叫，通过UniMRCP Server集成讯飞开放平台（xfyun）插件将用户语音进行语音识别（ASR），并根据自定义业务逻辑调用语音合成（TTS），构建简单的端到端语音呼叫中心。
The MRCPv2 protocol is designed to allow client devices to control media processing resources, such as speech recognition engines. MRCP4J provides a Java API that encapsulates the MRCPv2 protocol a…
Native and Compact Structured Latents for 3D Generation
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
基于lobe-chat，增加了绘图、音乐、视频等创作面板，支持midjourney、dall-e-3，flux，suno，luma，runway，kling(快手可灵)，豆包画图，用户注册登录，充值消费，模型及价格管理，聊天、绘图、音乐、视频创作记录管理，通知公告等
🧩 / 🏪 Plugin Index - This is the plugin index for LobeChat. It accesses index.json from this repository to display a list of available plugins for LobeChat to the user.
🤖 / 🏪 Agent Index - This is the agent index for LobeChat. It accesses index.json from this repository to display a list of available agents for LobeChat to the agent market.
🤯 LobeHub - an open-source, modern design AI Agent Workspace. Supports multiple AI providers, Knowledge Base (file upload / RAG ), one click install MCP Marketplace and Artifacts / Thinking. One-cl…
🍒 This is the mobile version of Cherry Studio.
Free, local, open-source GUI app for Gemini CLI, Claude Code, Codex, Qwen Code, Goose Cli, Auggie, and more — Enhanced Chat UI, WebUI, Multi-Agent & Multi-LLM, MCP Integration | 🌟 Star if you like it!
一个简单的WPS插件，将代码复制到对应路径即可将DeepSeek等主流工具插入到WPS中
一键将 Markdown 和网页 AI 对话（ChatGPT/DeepSeek等）完美粘贴到 Word、WPS 和 Excel 的效率工具 | One-click paste Markdown and AI responses (ChatGPT/DeepSeek) into Word, WPS, and Excel perfectly.
Make Office/WPS more powerful and easier to use with AI, similar to Office Copilot and WordGPT.
Office AI intelligent agent plugin based on Visual Studio+VSTO+VB.net (compatible with WPS). Persist in releasing two versions per week, with long-term updates and accompanying video addresses http…
DeepSeek-powered WPS add-in delivers smart document automation and AI-driven productivity enhancements within your office workflow.
线上语音/线上会议 中文->英文 中文说话转英文语音给对方 中英文同声传译 线上语音同声传译 线上会议同声传译
EarTrumpet - Volume Control for Windows
Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)
🔥🔥🔥AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.
MedSAM2: Segment Anything in 3D Medical Images and Videos
Medical SAM 2: Segment 3D Medical Images Via Segment Anything Model 2
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.
A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.