implemented 15,12,18 didn't check 18

FEATURES.md

@@ -6,13 +6,13 @@ Features are grouped by priority. Check off items as they are implemented.
 
 ## 🔴 Highest Impact Next — Conversion and retention
 
-- [ ] [#015] **Word text correction** — allow editing the transcript text of a word without affecting its timing. Whisper gets homophones/proper nouns wrong constantly. Pure frontend state change; no backend needed.
+- [x] [#015] **Word text correction** — double-click any word to edit its text in-place. Preserves timing and confidence. Pure frontend state change. (2026-05-04)
 
 - [ ] [#013] **Re-transcribe selection** — if Whisper gets a section wrong, let the user select a word range and re-run transcription on just that segment (optionally with a different model or language).
 
-- [ ] [#012] **Low-confidence word highlighting** — WhisperX already returns `confidence` per word. Words below a threshold (e.g. < 0.6) should be visually underlined or tinted so the user knows where to double-check.
+- [x] [#012] **Low-confidence word highlighting** — words with `confidence < 0.6` (configurable in Settings) get an orange dotted underline. Hover shows exact confidence %. (2026-05-04)
 
-- [ ] [#018] **Audio normalization / loudness targeting** — single "Normalize" button that targets a LUFS level (-14 for YouTube, -16 for Spotify). Backend: `ffmpeg -af loudnorm`. Very high value for podcasters, ~2–3 hours of work.
+- [x] [#018] **Audio normalization / loudness targeting** — "Normalize" button in Export panel with LUFS target selector (-14 YouTube, -16 Spotify, -23 Broadcast). Backend: FFmpeg two-pass `loudnorm`. (2026-05-04)
 
 - [ ] [#024] **Export to transcript text / SRT only** — some users just want a clean `.txt` or `.srt` of the edited transcript without rendering video.