gpt-4o前两天发布会有了视频聊天版本，再模仿前两天谷歌发布会的多模态AI项目Project Astra，粗略挫了个视觉聊天模型。现在能跟他自由交谈，它会根据摄像头拍到的画面与使用者的语言进行反映，并实时声音输出。目前英语效果是最好的，中文也算能支持。演示程序未加速未剪辑，视觉反映过程比较快，但是文转声会有延迟。 在Github项目DIY-Astra的基础上进行改进，现在可以做到拿着摄像头自由聊天。 目前感觉Gemini 1.5 Flash效果不错，不敢想象以后手机、甚至个人穿戴设备都被这些低功耗AI模型改造一遍的时代。 DIY-Astra地址：https://github.com/Doriandarko/DIY-Astra
☆43May 23, 2024Updated 2 years ago
Alternatives and similar repositories for Free_Astra
Users that are interested in Free_Astra are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Real time faster whisper gradio☆25Aug 17, 2025Updated 10 months ago
- 大模型推理框架加速，让 LLM 飞起来☆24May 10, 2024Updated 2 years ago
- Examples for QinYan GLMs☆13Sep 3, 2024Updated last year
- 永久免费高速，秒回复的免费ChatGPT API，支持文本转语言，文本翻译和文件翻译，高速流式对话，国内免代理。零成本使用Openai。无限制畅快聊天。☆32Mar 22, 2024Updated 2 years ago
- AI驱动，自然语言为输入，chat的方式，激发文本转换、图片生成、智能阅读、音视频生成等生产效率。Utools插件链接：https://u.tools/plugins/detail/AI%20Transform%20Box/?c=lsabf3sl7c☆32Aug 19, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Chat AI (↓↓Scroll to see more↓↓)☆15Sep 3, 2024Updated last year
- Make audio books in one click! Let Genshin characters read novels for you!☆29Aug 2, 2024Updated last year
- ☆15Mar 11, 2026Updated 3 months ago
- 一个将豆包 ASR 能力封装为 OpenAI 兼容接口的小项目，支持 Docker 启动，并提供一份可配合 Spokenly 使用的参考修正提示词，实现和 Typeless 类似的语音修正效果。☆40Feb 28, 2026Updated 3 months ago
- docker容器本地自签证书反代iyuu使用例☆15Jan 16, 2024Updated 2 years ago
- ChatGPT on WeChat项目插件使用jina reader和ChatGPT总结网页链接内容，支持总结公众号、小红书、知乎等分享卡片链接☆118Dec 28, 2024Updated last year
- A python plugin for Chatgpt On Wechat☆16Jul 1, 2024Updated last year
- 使用vue写的一个简单的日历☆11Dec 8, 2017Updated 8 years ago
- ☆12Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Face++ 是一款基于 Android 平台开发的创新性 AI 面相分析应用。它巧妙地将中国传统面相学理论（如“三庭五眼”和“十二宫”）与现代人工智能技术相结合，为用户提供一份专业、详尽且富有洞察力的面相分析报告☆22Jul 14, 2025Updated 11 months ago
- 财联社☆14May 18, 2021Updated 5 years ago
- ☆11Feb 4, 2023Updated 3 years ago
- 一款用于chatgpt-on-wechat的简易的提示词保护插件。☆13Apr 20, 2024Updated 2 years ago
- A Tampermonkey script for a fully-featured text-to-speech tool using the OpenAI TTS API.一个使用openai tts api的朗读工具的油猴脚本，功能完善。☆12Dec 12, 2023Updated 2 years ago
- Demo application using cordova and ionic.☆19Jan 12, 2015Updated 11 years ago
- Simplify Google Gemini 1.5 Pro's authentication☆15Apr 11, 2024Updated 2 years ago
- dow新协议接口☆21Jun 2, 2025Updated last year
- 基于FFmpeg推流到Nginx(nginx-rtmp-module)的一个简易推流的web管理系统☆23Oct 19, 2022Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Lite-MCP-Client是一个基于命令行的轻量级MCP客户端工具☆16Apr 1, 2025Updated last year
- vite-vue3-eslint-stylelint-demo 代码自动格式化☆13Jun 5, 2023Updated 3 years ago
- 基于pdfium的pdf/ofd双引擎解析渲染引擎☆13Oct 15, 2024Updated last year
- ☆27Mar 18, 2026Updated 3 months ago
- Just a simple Android app that uses Rokid's CXR-M SDK to upload/sideload an APK onto your Rokid glasses over Wi-Fi. It might be hard to g…☆54Apr 9, 2026Updated 2 months ago
- Happy Hacking With Claude!!!☆25Oct 27, 2025Updated 7 months ago
- 基于golang go语言（beego框架）下的ONLYOFFICE Document Server二次开发。 主要功能为文档的上传、预览、覆盖、回调等功能。☆10Oct 20, 2023Updated 2 years ago
- ☆15Oct 16, 2024Updated last year
- Deep Learning Visualization Tools Using PyTorch☆11Feb 2, 2021Updated 5 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Simple demo project with OpenAI's API and TTS☆15Mar 2, 2023Updated 3 years ago
- ☆14Apr 26, 2025Updated last year
- AI驱动的虚拟数字人直播系统，支持2D/3D数字人、TTS、ASR、唇形同步、推流、互动等模块化开发。☆25May 13, 2025Updated last year
- Integrated ChatGPT API and Used Voice As A Medium To Communicate☆20Feb 12, 2023Updated 3 years ago
- Accelerating GOT-OCRv2 with VLLM☆10Nov 15, 2024Updated last year
- 在监控画质下实现对 校园自行车的重识别，包含REID模型识别，向量数据库检索，UI展示☆11Feb 13, 2024Updated 2 years ago
- 一个开源的多模态 AI 搜索项目，结合 大语言模型（LLM）+ 多源搜索引擎 + 多 Agent 架构，打造新一代的智能问答式搜索体验☆17Mar 26, 2025Updated last year