Can AI replace Superwhisper?

Build me a push-to-talk dictation tool for macOS to replace Superwhisper. Requirements:

- A global hotkey (default: hold right Option) records my mic while held, stops on
  release. A small Swift menu bar app or a Hammerspoon script, pick the simpler to
  ship.
- Record with ffmpeg (avfoundation) to a temp wav, transcribe locally with whisper.cpp
  (small.en by default, model path in a config file). Works fully offline, no cloud
  speech APIs.
- Paste the result into whatever field has focus (simulate Cmd+V via CGEvent or
  osascript, then restore my previous clipboard).
- Optional cleanup mode on a second hotkey: send the transcript to an LLM (key in
  .env) to fix punctuation and drop filler words, then paste. If no key is set, this
  mode just does a plain paste.
- Menu bar icon shows idle/recording/transcribing; clicking it lists the last 10
  transcripts with copy buttons.
- Append every transcript to ~/Dictation/YYYY-MM.md with a timestamp, and delete the
  audio after transcription. No accounts, no telemetry.
- Out of scope: per-app presets and custom vocabulary tuning. One good general mode.
- README: mic + accessibility permissions to grant, how to download the whisper
  model, and a note that the first run will trigger macOS permission prompts.