InOpen IntelligencebyDr. Fadi Shaar·1d agoSpeak Instead of Type: How Hex Brings Private, Local Voice Dictation to Every AppAn open-source, on-device voice dictation tool for Mac, Windows, and Linux that lets you speak into any application without sending…A response icon1A response icon1
Arda Baysallar·2d agoI wanted subtitles for my own life. I built the app in two days.A phone app that catches me up in German, an AI coding agent, and the afternoon it got humbled.
Shruti Sridhar·Oct 29What If Your Notes App Learned Your Handwriting?A plan for handwriting recognition that adapts to you: what data it needs, how I’d build it, and how I’d test it.A response icon1A response icon1
Shivay Lamba·Oct 29Running Qualcomm GenieX on a Mac with Apple SiliconA practical guide to trying GenieX through its CPU-only Docker image
PielouNW·Oct 26How to build an offline transcription app with WhisperAt NobodyWho, we’ve spent the last months shipping new features, like Speech-to-Text or Voice Activity Detection, to complete our local AI…
YouShin kim·Oct 21Meta AI — Muse Glimmer 30B: 온디바이스 에이전틱 AI를 위한 고성능 오픈소스 언어 모델 아키텍처1. 한눈에 보는 핵심 요약 (Executive Summary)
Valentin Telegin·Oct 21How a 270M-parameter model on your phone turns a dictated note into contactsFine-tuning Gemma 3 270M on synthetic speech for an on-device birthday app: a second per note, no cloud.
InProAndroidDevbyKevin Desai·Oct 20Shipping a 584 MB Gemma model through Google PlayI was working on my Pokemon collection tracking Kotlin Multiplatform app (PokeCollect) and added a feature that uses on device LLMs to…A response icon1A response icon1
InProAndroidDevbyKatie Barnett·Oct 20AI, Meet App: Android AppFunctionsImplement the brand new API which allows your Android apps to behave just like an on-device MCP server.
Rahul Ahir·Oct 16Google’s Embedding Model Just Learned to Transcribe | Nobody Taught ItAn hour of audio in 13 seconds is the headline. The trick behind it is the part worth stealing.A response icon1A response icon1
