joe waine's site — Visual Studio Code
◇ index.js × ◇ about.md × ◇ blog.json × ◇ contact.json × ◇ photo.json × ◇ snake.js × ◇ chess.js × ◇ svg-filters.js × ◇ lotusvoice.py ×
☰ ⌕ ⎇ ⚙
Explorer
▼ joe-waine-site
▶ node_modules
▶ .git

// lotusvoice

LotusVoice

Push-to-talk dictation for macOS. Hold a key, speak, release — your words appear wherever your cursor is.

Download LotusVoice.dmg v1.0.0 · macOS only · ~16 MB

How it works

  1. Hold Right Option — recording starts, menu bar turns red
  2. Speak — audio is captured via your microphone
  3. Release — audio is transcribed locally with Whisper AI
  4. Text is pasted — automatically inserted wherever your cursor is

Everything runs locally on your machine. No audio is sent to the cloud.

Install

  1. Open LotusVoice.dmg
  2. Double-click Install Dependencies — this installs sox (audio recording) and whisper-cpp (transcription) via Homebrew
  3. Drag LotusVoice.app to your Applications folder
  4. Launch LotusVoice — grant Accessibility and Microphone permissions when prompted

Requirements

  • macOS 12+
  • Homebrew (the install script handles the rest)
  • Accessibility permission (for global hotkey)
  • Microphone permission

Features

  • Lives in your menu bar — no window clutter
  • Transcription history saved as daily markdown files in ~/.voice-history/
  • Filters out Whisper hallucinations on silence
  • Ignores accidental key taps (< 0.5s)
⎇ main ↻ 0 ⚠ 0
Ln 1, Col 1 UTF-8 JavaScript