sebsto

sebsto / wispr

Public

Privacy-first voice dictation for macOS — powered by on-device Whisper AI. No cloud, no tracking.

wispr.stormacq.com accessibility local-first macos menubar-app privacy
35
6
100% credibility
Found Mar 11, 2026 at 30 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Swift
AI Summary

Wispr is a menu bar voice dictation app for Mac that transcribes speech to text on-device and inserts it anywhere using a global hotkey.

How It Works

1
🖥️ Discover Wispr

You find this handy menu bar tool for turning your voice into text right on your Mac.

2
📥 Install and launch

Download the app, drag it to your Applications folder, and it appears in your menu bar ready to go.

3
🔒 Quick setup

Grant microphone access to listen and typing permission to insert words wherever your cursor is.

4
🧠 Grab a voice brain

It automatically downloads a fast speech-to-text model so everything works offline on your Mac.

5
🗣️ Try your first dictation

Press Option+Space, speak a sentence, release the key, and watch the words appear like magic.

✨ Dictate anywhere anytime

Now you can instantly turn speech into text in any app with one hotkey—effortless and private.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 30 to 35 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is wispr?

Wispr is a privacy-first voice dictation app for macOS, built in Swift with SwiftUI. Hit a global hotkey to start recording, speak, release to transcribe on-device using Whisper AI or Parakeet models, and insert text anywhere via accessibility APIs—no cloud, no tracking. Download and switch models like Tiny or Large-v3 right from the app, with settings for hotkeys, audio devices, and language (auto-detect or specific).

Why is it gaining traction?

As a Wispr Flow alternative on GitHub, it ditches cloud dependencies for fully local processing, appealing to datenschutz-focused users tired of subscriptions (Wispr Flow kosten) or Windows/Android ports. Menu-bar integration with real-time overlay, model management, and launch-at-login make dictation seamless in any app. On-device speed beats laggy web services, especially offline.

Who should use this?

Mac power users like writers, devs dictating code comments, or researchers needing quick notes without privacy leaks. Ideal for German speakers (Wispr Flow Deutsch vibes) or anyone evaluating Wispr AI locally before cloud trials. Skip if you need Windows/Android (no Wispr Flow Android GitHub here) or enterprise-scale.

Verdict

Solid early prototype at 26 stars and 1.0% credibility—comprehensive tests and onboarding shine, but low adoption signals immaturity; docs are README-only. Try for offline dictation wins, but watch for updates before daily driver.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.