FnScribe – Open-source, offline dictation for macOS
I built FnScribe because I'm pretty privacy concious and wanted a wispr flow-like app that kept everything local and on device. Currently works for Mac (sillicon and intel). It's dead simple. Hold the fn key, speak and release. I use a quantized Wisper small.en model for transcription. It inserts the text into the active application. There's also a hands-free model for longer dictation. Audio transcription is kept in memory. There's no account or transcription history. Clipboard contents are restored after it inserts it. GPLv3, Mac-only, English only..still in alpha. Hope you enjoy it! Would…
In plain words
FnScribe is a privacy-focused dictation tool for macOS that transcribes speech locally using an offline Whisper model. Users hold the function key and speak to insert text into any application, or use hands-free mode for longer passages. It runs from the menu bar, keeps no transcription history or accounts, and restores clipboard contents after insertion. Available for Apple Silicon and Intel Macs running macOS 13 or later, it is open-source under GPLv3 and currently in alpha.
written from the facts on this page · September 2026
From the sources
Contribute to AlgorithmicResearchGroup/fnscribe development by creating an account on GitHub.
Hold a shortcut, speak, and release—or use hands-free mode for longer thoughts. FnScribe transcribes your voice locally and inserts the result into the app you are using. It lives in the menu bar and stays out of the way until you need it. FnScribe requires an Apple Silicon or 64-bit Intel Mac running macOS 13 Ventura or later. The default push-to-talk shortcut is the fn /Globe key. To change it, click the menu-bar microphone, click the shortcut button, and press a new key combination. For hands-free dictation, press fn + Space once to start and again to stop. You can also turn a push-to-talk recording into hands-free mode by pressing Space while continuing to hold fn . Press Escape at any…from github.com
In the maker’s words, at launch
I built FnScribe because I'm pretty privacy concious and wanted a wispr flow-like app that kept everything local and on device. Currently works for Mac (sillicon and intel). It's dead simple. Hold the fn key, speak and release. I use a quantized Wisper small.en model for transcription. It inserts the text into the active application. There's also a hands-free model for longer dictation. Audio transcription is kept in memory. There's no account or transcription history. Clipboard contents are restored after it inserts it. GPLv3, Mac-only, English only..still in alpha. Hope you enjoy it! Would love some feedback.
Does the same job
all alternatives →
MegaphoneJul 2026 · megaphone.kuber.studio · ▲102Open-source Mac dictation App that's 100% on-device
- QSQwen Scribe – local transcription and dictation for Apple SiliconJul 2026 · github.com · ▲97
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 2d ago · opentrailpaper.com
Launched alongside, August 2026
the whole month →- TL
Life & fun · 10d ago · louisabraham.github.io
- SA
Hello HN! I found that picking out plausible but diverse skin tones for my digital art and game development projects was kind of difficult, and I got curious about if there was a way to define a color space that made it easy. I've built a color picker and procedural generation algorithm based on the space as well as a bunch of other fun js features and demos throughout the page that use the equations. If you find it interesting, I have lots of explanations of how I built it and what properties the space has. The methodology might be a bit shaky, but hopefully the result is as helpful for…
Life & fun · Aug 2026 · toneyalexander.github.io
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com