The full gallery
Tech stack
19 projects
Play and create music from audio clips, hummed melodies, or voice input.
@HappyMonkeyAI · X
Been building so many cool things recently, like Riffly 🎸Hear something cool? Play it in seconds. 📷Drop in a clip, hum a melody, or use your mic. 📷
Remove background noise, hum, echo, and hiss from audio and video files.
nadermx · HN
NoiseRemover.ai – Remove background noise from audio
Master WAV tracks online in under a minute, then build reverb impulse responses, bass one-shots, drum samples and more with BitKrunch's browser-based audio DSP toolkit. No install
@mstrdbybitkr · X
Create AI voices, convert text to speech, and clone existing voices.
Seed Audio — AI 语音生成与在线音乐创作工具
Speech to text dictation and multi-engine speed benchmarking. Compare OpenAI GPT-Transcribe, Deepgram Nova-3, NVIDIA Parakeet, and Fish Audio with local IndexedDB privacy.
@alvaisy · X
finished voice to text small web app for my own itch. it's opensource. use openrotuer key. and use it with 4 models.
Edit, compress, convert, and merge video and audio files in your browser.
zhw2590582 · V2EX
最近对网站进行了重构，做成了免费的视频工具站：[ArtPlayer Tools]( https://artplayer.org/tools/) 主要是围绕着 ffmpeg.wasm 和 mediabunny 实现的一些可以直接在浏览器里用的视频/音频工具，常用的有： - 视频压缩：[Compress Video]( https://artplayer.org/compress-video/) - 视频裁剪：[Crop Video]( https://artplayer.org/crop-video/) - 视频合并：[Merge Video]( https://artplayer.org/merge-video/) - 视频尺寸调整：[Resize Video]( https://artplayer.org/resize-video/) - 视频旋转：[Rotate Video]( https://artplayer.org/rotate-video/) - 视频调速：[Change Video Speed]( https://artplayer.org/change-video-speed/) - 添加文字到视频：[Add Text to Video]( https://artplayer.org/add-text-to-video/) - 添加水印：[Watermark Video]( https://artplayer.org/watermark-video/) - 提取字幕：[Subtitle Editor]( https://artplayer.org/subtitle-editor/) - HLS 转 MP4：[HLS to MP4]( https://artplayer.org/hls-to-mp4/) - 音频可视化：[Audio Visualizer]( https://artplayer.org/audio-visualizer/) 大部分工具都是本地处理，文件不会上传到服务器。最开始是因为自己偶尔要处理一些视频，开剪辑软件又有点重，在线工具又担心隐私，所以就慢慢做成了一个站。 目前还在持续完善，体验肯定还有不少粗糙的地方，比如不同浏览器的兼容、移动端操作、长视频性能之类的。 网站： [ArtPlayer Tools]( https:
Practice whistling with real-time pitch feedback and progressive exercises.
x1shir · V2EX
HowToWhistle：像唱 KTV 一样练习吹口哨 一直想提高吹口哨技巧，搜了一圈发现网上的教程都是文字和视频，练的时候根本不知道自己吹得对不对。 想到可以像 KTV 一样，有个音轨对比，于是干脆自己搓了一个练习网站：[https://howtowhistle.org/]( https://howtowhistle.org/) 核心思路是用浏览器的麦克风做实时音高检测，你对着麦克风吹，页面会显示你当前的音高和目标音的偏差，类似 KTV 唱歌时的实时评分。功能大概有： - 实时音高反馈，能看到自己吹的是哪个音、偏高还是偏低 - 从单音长音开始的渐进式练习，到音阶、再到简单旋律 - 纯前端实现，声音不上传，无需注册 目前还比较简陋，欢迎大家试玩和提建议。
Search podcast content by exact word and timestamp, save clips, and track brand mentions.
lawnmaster18 · HN
Vuci – make the spoken word searchable
Pay to shout. Rank is your bid. The louder you pay, the higher you rank.
@peakdHQ · X
Just launched let the party continue 🥳
Compress LLM prompts and documents to reduce token usage and API costs.
@marcusyul · X
THEY JUST GAVE AWAY 100 MILLION FREE TOKENS SO YOU CAN STOP BURNING THROUGH YOUR CLAUDE CODE BUDGET. if you code with AI you already know: the session fills up, starts failing, and on top of that you're overpaying there's a tool that fixes this: it shrinks the context before the model even sees it same model, same response, a fraction of the cost in a real session: from $154 to $43. a 72% drop and right now: → extend your Fable sessions in Claude Code → 100M free tokens to try it out you don't switch models you don't touch your code you just stop paying to repeat yourself link below ⬇️
