**video-talkcraft** is the narration-video installment of the [video-shotcraft](https://github.com/Vincentwei1021/video-shotcraft) series: an AI agent skill that turns Claude Code or Codex into a motion-design studio for talking videos. Hand it a narration script and a finished voiceover, and it aligns word-level timestamps locally, storyboards every semantic beat into a SHOTBOOK, then renders a high-quality explainer with [Remotion](https://www.remotion.dev/) — kinetic type, evidence screenshots, camera moves, plain-cut subtitles, and film-grade SFX, all locked to the voice.

The methodology docs and recipe cards are written in Chinese — the toolkit is built Chinese-narration-first (mixed Chinese/English narration is fully supported). Agents read them natively.

🖼️ [**Browse all 78 motion previews in the live Gallery »**](https://vincentwei1021.github.io/video-talkcraft/)

✨ Highlights

• Word-level voiceover sync — scripts/timestamps_cpu.py aligns your script to the audio (FireRedASR2-CTC int8 by default, faster-whisper as the zero-download fallback). Benchmarked against a GPU forced aligner on a 110s mixed-language narration: median per-character offset 20–40 ms, worst case 200 ms, zero false QA flags. Every motion beat anchors to the exact word.
• 78 motion recipe cards — each with intent, parameters, known pitfalls, and a runnable HTML preview — browse them all in the online Gallery or locally wit