Fly Labs
Ask FlyBot

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 love some feedback.

Hacker NewsToolDesign & CreativeSource
0Sign in to voteCopy link

FL score

62

out of 100

Verdict

VALIDATE

medium confidence

Competition

No competitor data yet

Trend

No signal yet

Local-first dictation for macOS that trades convenience for privacy, solving a real problem for a small but defined audience.

The pain

Users who care about privacy avoid cloud dictation tools because audio files get sent to external servers. Whisper's release created an opportunity to build local alternatives, but most implementations still require technical setup or don't match the UX of commercial tools like Whisper.

The gap

There's no polished, one-click dictation tool for privacy-conscious Mac users. Whisper exists but requires command-line setup. Commercial tools like Otter.ai and Google Docs dictation require cloud uploads. FnScribe fills this specific gap with a simple fn-key interface.

Build angle

This works best as a niche tool for privacy advocates, developers, and writers who already distrust cloud services. The business model is unclear (open-source, GPLv3), which limits revenue potential but builds trust. Consider: freemium desktop app with optional paid features (custom models, batch processing, export tools), or position as infrastructure for privacy-focused apps.

Strengths

  • Solves a real, articulated problem for a defined audience
  • Simple UX (fn-key hold) matches user expectations from commercial tools
  • Technical execution is sound (quantized model, memory-only storage, clipboard restoration)
  • Open-source builds credibility with privacy-conscious users
  • Low resource requirements (quantized small model) means broad Mac compatibility
  • Already built and in use by creator

Risks

  • Market size is small, privacy-conscious dictation users are a niche within a niche
  • No monetization strategy defined; open-source GPLv3 limits commercial paths
  • macOS-only severely limits addressable market (15% of desktop users)
  • English-only excludes non-English speakers and international markets
  • Whisper model quality lags behind commercial tools; transcription errors will frustrate users
  • Maintenance burden on solo creator; no clear path to sustainable development
  • Competing against free cloud alternatives (Google Docs, Apple Dictation) that have better accuracy
  • Alpha status means stability and feature completeness are unproven

Questions about this idea?

FlyBot reads the scoring and gives you a second opinion on “FnScribe – Open-source, offline dictation for macOS”.

Open FlyBot