- [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)
- [x] [#013] **Re-transcribe selection** — select any word range in the transcript and click "Re-transcribe" to re-run Whisper on just that segment. Backend extracts audio via FFmpeg, transcribes with offset-adjusted timestamps. (2026-05-04)
- [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)
- [x] [#024] **Export to transcript text / SRT only** — "Export Transcript Only" section in Export panel with format selector (plain text or SRT). Uses `POST /export/transcript` backend endpoint. Respects word cuts. (2026-05-04)
- [x] [#016] **Named timeline markers** — colored marker pins on the waveform canvas. Add at current playback position with label/color picker in Markers panel. Editable labels, deletable. Persisted in project file. (2026-05-04)
- [x] [#020] **Video zoom / punch-in** — scale and position the video (crop, zoom, pan). Used constantly on talking-head videos for emphasis. Backend: FFmpeg crop/scale post-process. Frontend: sliders in Export dialog. (2026-05-05)
- [x] [#019] **Background music track** — a second audio track for background music with volume ducking. Uses FFmpeg amix + sidechaincompress for auto-ducking. Configurable in Background Music panel. (2026-05-05)
- [ ] [#014] **Optional VibeVoice-ASR-HF transcription backend (future)** — evaluate as an alternate transcription mode for long-form, speaker-attributed transcripts. Keep WhisperX as the default for word-level timestamp editing.
- [ ] [#048] **AI Show Notes** — generate title, description, soundbites, keywords from transcript + markers. `POST /ai/show-notes`. Copy to clipboard or save to file.
- [ ] [#049] **AI Find Fluff** — AI marks rambles, intros, off-topic chatter for deletion. Extends existing filler detection. `POST /ai/find-fluff`. AIPanel tab showing suggested cut ranges.
- [ ] [#050] **AI Smooth Cuts** — remove jump cuts between deleted segments using crossfade/blend during re-encode. Export option toggle.
- [ ] [#051] **AI B-roll** — generate footage from a text prompt to fill visual gaps in the timeline. Uses local SD or API. New "B-roll" section in AIPanel.
- [ ] [#052] **Smart Layouts** — auto-switch video layout between speakers based on who's talking. Detects active speaker from diarization + volume, applies crop/pad to focus on current speaker during export.
- [ ] [#053] **Per-track audio levels** — individual gain per speaker track. Extend `GainRange` model with `track_id`, apply per-stream via FFmpeg.
- [ ] [#054] **Intro/Outro templates** — save segment ranges as reusable templates, apply with one click on export.
- [ ] [#055] **Built-in free music library** — 5–10 CC0/royalty-free short loops shipped in `frontend/public/resources/music/`. BackgroundMusicPanel gets a "Built-in" tab with play/preview.
- [ ] [#056] **Stock media browser** — new `MediaLibraryPanel` that browses local `resources/media/` for images, video, audio with thumbnails. Frontend-only via Tauri `readDir`. Drag-to-add for bg removal images, append clips, or music.
- [ ] [#057] **Sample content downloader** — "Get Sample Video" button on empty state downloads a short public-domain test video + pre-made transcription JSON for trying the app without your own media.
These aren't features to build — they're things to make more visible in the UI and README:
- **100% offline / no account required** — CapCut requires login and sends data to servers. Descript is cloud-first. TalkEdit never leaves the machine.
- **Local AI models** — Ollama support means no API costs and no data leaving the device.
- **Word-level precision** — editing by deleting words (not dragging razor cuts) is faster for talking-head content than any timeline-based editor.
- **Works on long files** — virtualized transcript + chunked waveform handles 1hr+ content that bogs down CapCut.
