
The full gallery
Tech stack
18 projects


A shared music room for friends. Everyone hears the same track at the same second, one person holds the aux, and anyone can take it off them.
@theeasyway6 · X

Reads articles aloud in your browser with podcast-quality voices.
DmitryDolgopolo · HN
ReadAloud – on-device, podcast-quality text-to-speech in the browser

Listen to music together in shared rooms with chat, skip voting, and AI-powered song requests.
vodmaker · V2EX
做了个在线听音乐的另一种可能 平时听歌,不管是工作还是休息,习惯基本都是:打开 App ,进入歌单,然后开始播放。 我最近在想,听歌是不是还能有另一种方式? 参考 KTV 的点歌模式,我做了一个多人在线听歌的小产品——听歌 Next 。 大家可以进入同一个房间,一起听同一首歌,也可以各自点歌,把想听的歌曲加入播放队列。播放进度会在房间内同步,还支持聊天和投票切歌。 另外做了一个自然语言点歌功能,不需要准确输入歌名,可以直接说: - 来几首适合下班路上听的歌 - 想听一些周杰伦早期的慢歌 - 放几首适合写代码的轻音乐 系统会根据描述推荐歌曲,再批量加入播放队列。 目前还是早期版本,欢迎大家来试用,也欢迎反馈问题和建议: 试用地址: https://tingge-production.up.railway.app/

Conduct AI-powered voice, chat, and video interviews with automated transcripts and insights.
Aural — 开源 AI 面试平台,支持语音、聊天和视频面试,提供自适应追问、结构化评分、面试练习与自托管 - [查看仓库](https://github.com/1146345502/aural-oss)

Play white noise, rain sounds, and nature ambience to help you sleep better.
@AI_fengkuang · X
My first website built with Codex — a white noise sleep aid site to help adults get better rest.

Build audio synthesizers using visual node-based workflows in your browser.
Synthesizer Flow — 浏览器端模块化合成器,通过可视化节点和连线搭建音频工作流,支持实时声音合成、MIDI 音序及 AI Agent 辅助修改工程

A radio for the back row. Slow indie and acoustic songs for empty classrooms, rainy corridors, and the last bell — flip to Hip Hop mode for something louder.
@Varuntiwari_ · X

Listen to an internet radio station where an AI DJ picks songs and announces them live.
@pinku1 · X
Personal internet radio: Agentic AI DJ - Open Source

Convert audio and video files to text with speaker labels and timestamps, no signup required.
zxhywork · V2EX
SayScribe AI - 音频转文字的在线工具 花了几周搞了一个基于 OpenAI Whisper 的 AI 转录工具 **[SayScribe]( https://sayscribe.org)**,目前 5 个工具全部免费,每天 3 次无需注册。上线前请 SEO 专家做了一轮诊断,踩了不少坑,分享出来给同样在做工具站的 V 友参考。 --- ## 做了什么 核心工具是 **[Audio to Text Converter]( https://sayscribe.org)**(主页),上传音频/视频文件,AI 自动转成带 speaker labels 和时间戳的文字稿。选这个词的原因是:Google 第一页有个 DR 只有 10 的小站排第三,KD 才 20.2 ,链接预算只要 15-35 个引用域就能进前十——典型的弱盘面蓝海。 然后在主页基础上拆了 4 个子工具,每个打一个独立搜索词: - **[MP3 to Text]( https://sayscribe.org/mp3-to-text)** — 只转 MP3 。KD 41.7 比主页难一些,但

Generate AI voices, sound effects, and music from text prompts in multiple languages.

Watch calm visuals and listen to slow, ambient audio in a meditative browser experience.
@ace_space_1 · X