---
title: "Video-talkcraft Turns Claude Code Into a Frame-Perfect Video Director"
subtitle: "A new open-source agent skill hands Claude Code and Codex a full motion-design studio for voiceover explainer videos with word-level sync and Remotion rendering."
url: "https://alphasignal.ai/news/video-talkcraft-turns-claude-code-into-a-frame-perfect-video-director"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-09-02T07:25:02.000Z"
updated: "2026-09-02T07:36:58.631Z"
type: "Repo"
topics:
  - "Video"
  - "Development"
subtopics:
  - "Video Generation"
  - "Code Agents"
upvotes: 335
source_url: "https://github.com/Vincentwei1021/video-talkcraft"
comments: 0
truncated: true
---

# Video-talkcraft Turns Claude Code Into a Frame-Perfect Video Director

> A new open-source agent skill hands Claude Code and Codex a full motion-design studio for voiceover explainer videos with word-level sync and Remotion rendering.

Video-talkcraft is an open-source agent skill for Claude Code and Codex that produces voiceover-driven explainer videos through [Remotion](https://www.remotion.dev/). Hand it a script and a finished audio file, and it aligns word-level timestamps, writes a shot-by-shot storyboard, and renders the final piece with kinetic captions, camera moves, transitions, and sound effects locked to the narration.

## Sync, not slideshow

Most AI video tools stitch stock footage together or animate a slide deck. Video-talkcraft targets something narrower: narrated explainers where every motion beat lands on a specific syllable. The agent reads a methodology document, selects from 78 motion recipe cards, writes Remotion code, and runs a triple-QA loop before delivering the output.

## What ships in the repo

* **78 motion recipe cards.** Each card includes intent, parameters, known pitfalls, self-contained Remotion TSX source, and a runnable HTML preview. A gallery page shows all 78 previews at once.
* **Word-level voiceover alignment.** A CPU script aligns narration to audio using FireRedASR2-CTC int8 by default, with faster-whisper as a fallback that skips manual downloads. On a 110-second Chinese-English mixed voiceover, character-level deviation clocked in at a median of 20–40ms, worst case 200ms, with zero false positives in QA.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Vincentwei1021/video-talkcraft](https://github.com/Vincentwei1021/video-talkcraft)
- [video-talkcraft online gallery](https://vincentwei1021.github.io/video-talkcraft/)
- [Remotion](https://www.remotion.dev/)