Conal Mullan ffa515a23d Add SadTalker NarratorPiP integration patterns and improvements ...

- Add comprehensive docs/sadtalker.md with NarratorPiP workflow
- Document critical patterns: 16:9 image prep, --preprocess full
- Add auto-timeout calculation based on audio duration
- Add --retrieve flag for job recovery after client timeout
- Update NarratorPiP component with objectFit: contain
- Track learnings in BACKLOG.md for future improvements

Key insight: Always use --preprocess full to preserve image
dimensions for video overlays. Let users crop their own images
for best face framing.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-12 02:31:07 +00:00

..

__init__.py

Initial release of claude-code-video-toolkit

2025-12-09 20:38:32 +00:00

addmusic.py

Add addmusic tool for background music on existing videos (v0.5.0)

2025-12-28 20:26:43 +00:00

config.py

Add dewatermark and locate_watermark tools (v0.7.0)

2025-12-30 20:22:16 +00:00

dewatermark.py

Add sora preset for OpenAI Sora watermark removal

2025-12-30 20:25:15 +00:00

image_edit.py

Add AI image editing tools (qwen-edit, upscale) (#1)

2026-01-05 15:23:46 +00:00

locate_watermark.py

Add sora preset for OpenAI Sora watermark removal

2025-12-30 20:25:15 +00:00

music.py

Initial release of claude-code-video-toolkit

2025-12-09 20:38:32 +00:00

notebooklm_brand.py

Add notebooklm_brand tool for NotebookLM video post-processing

2025-12-29 10:10:26 +00:00

redub.py

Add eleven_v3 (alpha) model option to TTS tools

2025-12-29 10:17:01 +00:00

requirements.txt

Add dewatermark and locate_watermark tools (v0.7.0)

2025-12-30 20:22:16 +00:00

sadtalker.py

Add SadTalker NarratorPiP integration patterns and improvements

2026-01-12 02:31:07 +00:00

sfx.py

Initial release of claude-code-video-toolkit

2025-12-09 20:38:32 +00:00

upscale.py

Add AI image editing tools (qwen-edit, upscale) (#1)

2026-01-05 15:23:46 +00:00

voiceover.py

Add eleven_v3 (alpha) model option to TTS tools

2025-12-29 10:17:01 +00:00