Multimodal real-time interactive products

综合介绍 Gemini Cursor 是一个基于 Google 的 Gemini 2.0 Flash（实验性）模型的桌面智能助手。它能够通过多模态 API 实现视觉、听觉和语音交互，提供实时低延迟的用...

综合介绍 xiaozhi-esp32-server 是一个为 小智AI聊天机器人（xiaozhi-esp32）提供后端服务的工具。它用 Python 编写，基于 WebSocket 协议，帮助用户快速...

综合介绍 Baichuan-Audio 是由百川智能（baichuan-inc）开发的一个开源项目，托管于 GitHub 上，专注于端到端的语音交互技术。该项目提供了一个完整的音频处理框架，能够将语音...

综合介绍 MoshiVis 是 Kyutai Labs 开发的一个开源项目，托管在 GitHub 上。它基于 Moshi 语音-文本模型（7B 参数），新增了约 2.06 亿个适配参数和冻结的 Pal...

General Introduction VideoMind is an open source multimodal AI tool focused on inference, Q&A and summary generation for long videos. It was developed by Ye Liu of the Hong Kong Polytechnic University and a team from Show Lab at the National University of Singapore. The tool mimics human understanding of video...

General Introduction OpenAvatarChat is an open source project developed by the HumanAIGC-Engineering team and hosted on GitHub. It is a modular digital human conversation tool that allows users to run on a single PC...

综合介绍 Stepsailor 是一个专为开发者打造的工具，核心是一个 AI 命令栏。开发者可以用它让自己的软件产品听懂用户的话，比如用户说“添加新任务”，软件就自动执行。它通过简单的 SDK 集成到...

General Introduction RealtimeVoiceChat is an open source project focused on real-time, natural conversations with artificial intelligence via voice. Users use a microphone to input their voice, and the system captures the audio through a browser, quickly converts it to text, and a large-scale language model (LLM) generates back...