Vale construir sua versão de Descript?

Build me a text-based clip cutter to replace Descript for simple edits. Requirements:

- A local web app: Node + Express with a plain JS frontend, binds to localhost.
- I drop an audio/video file into ./media/; the app transcribes it with whisperX
  for word-level timestamps, or the OpenAI Whisper API if a key is in .env.
- The transcript renders as clickable words. I select and delete words or whole
  sentences; deleted spans go into a cut list I can undo from.
- Render: build one ffmpeg trim/concat command that removes the cut spans from
  the original and writes ./output/<name>-cut.mp4 (or .mp3 for audio-only).
- Pad each cut by about 80 ms so words are not clipped mid-syllable.
- Save each project as JSON next to the media file (transcript + cut list) so an
  edit can be reopened later.
- No accounts, no telemetry; everything stays on my machine except the optional
  Whisper API call.
- Out of scope: multitrack timeline, overdub or AI voices, filler-word
  auto-removal, cloud anything. This is a cutter, not an editor.
- README: installing ffmpeg and whisperX, and a warning that local
  transcription of long video is slow on CPU.