Installation Guide

macOS

NexScribe requires macOS 13 (Ventura) or later. It runs on both Apple Silicon and Intel Macs.

  1. 1. Download the .dmg from the download section or the link above.
  2. 2. Drag NexScribe to Applications. Open it from your Applications folder.
  3. 3. Grant Microphone permission. macOS will prompt you on first launch. NexScribe needs this to hear your voice.
  4. 4. Grant Accessibility permission. Required for typing transcribed text into other applications. Go to System Settings → Privacy & Security → Accessibility.
  5. 5. Grant Input Monitoring permission. Required for global hotkey detection. System Settings → Privacy & Security → Input Monitoring.

Quick Start

Once permissions are granted:

1. Hold Fn (or your configured hotkey)
2. Speak naturally
3. Release the key — text appears at your cursor

The first transcription may take a few seconds while the Whisper model loads into memory. Subsequent transcriptions are near-instant.

Troubleshooting

"NexScribe can't be opened because it is from an unidentified developer"

If you see this Gatekeeper warning, right-click (or Control-click) the app in Finder and select "Open". You'll see an option to open it anyway. This only needs to be done once.

Permissions not working after update

macOS may revoke permissions when the app is updated or re-signed. Go to System Settings → Privacy & Security and re-enable NexScribe for Accessibility and Input Monitoring.

Slow first transcription

The Whisper model takes 20-30 seconds to load into GPU memory on first use. After that, transcriptions are near-instant. The model stays loaded while NexScribe is running.