Here's a fully local, open-source RAM-optimized dictation app.
This is a dev post classified by Jev as Mobile & desktop (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Here's a fully local, open-source RAM-optimized dictation app. Nothing ground breaking, I've used the best models everyone else uses but I focused the stack spending as little RAM when models are loaded. One neat trick is that I split long recordings on silences. Mostly for my use, but feel free to contribute or fork :)
Posted by Mihovil Ilakovac (2k followers) 3 days ago · 2 likes · 115 views · view the original post on X. Kept by the Dev Radar as Mobile & desktop.
More dev work like this
- Added Steamworks SDK to my game, feels so unreal to see the steam overlay! 😊 — @JanMellstrom
- I built Hacker News directly into Hermes Desktop. — @HermesWatcher
- 1.0beta2更新，修正退出音频播放后服务不退出的bug，增加守护进程，增加手动调节音量灯条指示。不破坏系统文件，兼容原系统服务指示灯，项目地址… — @eastwoodnet
- I raised a PR into Electron itself to save ~400ms off window launch time on Windows. — @LukeParkerDev
- GPUI Kit v0.6.2 is out! — @rustaceans_rs
- 🛠️iPhone Duo Workshops 🛠️ — @lindadong
- Here, damn. — @lindadong
- How do you simulate thousands of enemies on a mobile screen? 📲 — @unitygames
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 12.2k posts from 4.7k X accounts over the last 21 days, 1.4k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-19 18:06 UTC. Full method.