Creative Tools1 month ago
AhaPrompt - AI Prompts for Images, Video & Audio — Every Model, One Library
Copy curated prompts for AI image, video, and audio generation.
weijunext · HN
Free, curated prompts for AI image, video and music
The full gallery
Tech stack
32 projects
Copy curated prompts for AI image, video, and audio generation.
weijunext · HN
Free, curated prompts for AI image, video and music
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
Generate personalized AI songs for birthdays, weddings, and celebrations.
kronosense_support · Product Hunt
Singy Turn any celebration into a personalized AI song
Make editable music with AI-generated Strudel patterns, directly in your browser.
@ferdousbhai · X
Vibe coding for music production is here. Open source, runs entirely in your browser. With AI music, typically you get audio you can't edit directly with fine-grain control. But with a Web Audio framework like strudel, the AI writes live-coding patterns and the code is the music.
Generate personalized birthday songs with AI using names and memories.
CelebrateYou — AI 音乐生成器
Describe a song idea and Boppy generates complete lyrics and music tracks with AI in minutes.
@GamerHashCom · X
It's 3 AM. You're mass-producing spaghetti code with an AI copilot and your lo-fi playlist died two hours ago. "3 AM Code" fixes one of those problems. AI-generated on in about 60 seconds, powered by GPUs from the GamerHash AI network. Vibe coding deserved a vibe anthem.
Enter a presence-based digital ecosystem with AI agents, music, and shared community experience.
@EllistriponX · X
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