
RenewandReset — Free meditation moments
Free meditation app with customizable soundscapes from 5 minutes to 1 hour.
@TwoMinutesAI · X
The full gallery
Tech stack
26 projects

Free meditation app with customizable soundscapes from 5 minutes to 1 hour.
@TwoMinutesAI · X

Forge creatures in a 3D game with GPU-simulated water physics.
@rand_monsterlab · X
A monster walks into a GPU-simulated pond. Reactive SPH water in the browser with @threejs + WebGPU. Every movement sends ripples through Coming soon. Follow @rand_monsterlab: #ThreeJS #WebGPU #VibeCoding #IndieGame #Monster

Transcribe audio files to text instantly with AI, no signup required.
音频转文字工具 — AI 音频转文字,快速、精准、安全的转写服务

Create music, beats, and instrumentals from text using AI.
CreateYourMusic AI — AI 音乐生成器,把文字描述、歌词或诗句变成带人声、旋律和编曲的完整歌曲,支持多风格生成和 MP3/WAV 下载

Get music recommendations by picking five favorite albums and finding listeners with similar taste.
BubbleRings · HN
I used AI to build a music recommender system that itself uses no AI in its operation. I have been promoting the system in communities that can sometimes be considerably anti-AI. But people usually assume that it is AI because, well, it's a recommender system. Anyways, after a 30-year break, I rebuilt it and got it working the way I always wanted! It basically uses the same 10 lines of code, (for which I was granted now-expired US patent #5749081), but with a good interface around it instead of

Turn songs you love into a two-sided digital keepsake with an optional memory place and up to twelve Polaroid-style photographs. MXT8 stores metadata, not music audio.
@Alan_John_Riley · X

Upload a sky photo for AI-powered cloud identification and educational weather information.
在线云朵识别 — 上传天空照片,用 AI 即时完成云识别与云分类,了解积云、层云、卷云等常见云型及典型天气、出现高度与形成过程,适合学生、摄影爱好者与天气科普学习。

Generate personalized birthday songs with AI using names and memories.
CelebrateYou — AI 音乐生成器

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

Make music with webcam hand gestures—chords, harmony, theremin pitch, no signup needed.
lisheng3698 · V2EX
我把摄像头变成了乐器:从手势识别到 Web Audio,分享 5 个真正踩过的坑 最近做了一个有点不一样的浏览器小项目:用摄像头识别双手动作,再把手的位置和姿势映射成和弦、音高、音量和音色。 不需要安装软件,也不需要麦克风。打开网页、允许摄像头后,就可以隔空演奏。 项目地址:[GestureSynth.me]( https://gesturesynth.me/) 建议使用最新版 Chrome 或 Edge 。摄像头画面只在本地处理,不会上传。 ## 真正难的不是“识别到手” 最开始我以为,只要 MediaPipe 能返回手部关键点,剩下的事情就是把坐标转换成音符。 实际做下来发现:**识别出一只手很容易,让它变成一个“能演奏”的控制器才难。** 摄像头每一帧都会返回一组手部关键点,但这些坐标会轻微抖动,偶尔还会丢失。如果直接把原始坐标连接到音高或者音量,听起来会非常不稳定。 最后形成的处理链路大致是: ```text 摄像头 → 手部关键点识别 → 提取手掌位置、距离和手势 → 平滑、死区和状态保持 → 映

Generate full-length songs with vocals or instrumentals from text prompts.
Moono AI 帮你写歌 — AI 音乐生成器
