Should you build your own Wispr Flow?

Build me a system-wide AI dictation tool like Wispr Flow for macOS. Requirements:

- A background app with a global hotkey (hold-to-talk fn key or a chosen shortcut).
  While held: record the mic. On release: transcribe and paste.
- Double-tap the hotkey for a hands-free session that records with nothing held ·
  one more tap stops it. Auto-stop after 5 minutes so a forgotten session cannot
  record all afternoon.
- Esc cancels: drop the recording, or kill a transcription already running. Watch
  it passively so Esc still reaches the app I am typing in.
- Transcribe with whisper.cpp locally (small or medium model), or the Groq/OpenAI
  Whisper API if a key exists in .env · pick per a config flag.
- Pipe the raw transcript through an LLM (key in .env) with a short prompt that
  removes filler words, fixes punctuation, and matches casing to dictation style.
- Insert the result at the current cursor position in whatever app has focus
  (simulate keystrokes or use the pasteboard + Cmd-V approach). Leave the transcript
  on the clipboard so I can paste it again, with a config flag to restore my
  previous clipboard instead.
- Show a tiny floating pill while recording so I know it's live and which mode I'm in.
- Menu bar toggle for on/off, launch at login, and a settings file for the hotkey.
- No accounts, no telemetry, works offline with the local model.
- README with the Accessibility/Input Monitoring permissions I need to grant.