isabellagreco1997

Script To Video — Communication skill for Claude Code

Communication community

Turn a script into a narrated, word-synced explainer video (16:9 YouTube or 9:16 Reels/Shorts).

How to install Script To Video

This entry records only its repository, not the path inside it, so there is no exact command to give. Open isabellagreco1997/script-to-video and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Script To Video does

Turn a script into a narrated, word-synced explainer video (16:9 YouTube or 9:16 Reels/Shorts). Free local Kokoro voice, licensed web images, clips, browser-rendered motion. Python CLI + Claude Code skill.

Alternatives in Communication

HolaOS — Open-source agentic workspace enterprises can make their own 10.9k ★
YouTube Shorts Research: Claude SEO — YouTube Shorts Research: Claude SEO skill 5k ★
Claude Skill Social Post — A Claude Code skill by Hao (駱君昊) that learns your Facebook voice and auto-posts to FB / IG / Threads / X with 625 ★

README

script-to-video

**Turn a script into a narrated, word-synced explainer video.** Free local voice (Kokoro), images and articles from the web with licences recorded, clips, and browser-rendered motion graphics. 16:9 for YouTube or 9:16 for Reels, Shorts and TikTok. No After Effects, no cloud, no API keys.

It also ships as a **Claude Code skill** (`SKILL.md`): drop the folder in `~/.claude/skills/` and Claude plans the shots, fetches the pictures, and builds the video from your script.

How does a door work · 16:9 · 1:49
Wikipedia images + article screenshots + diagrams, male Kokoro voice

The story of Dark Souls · 9:16 · 0:58
trailer clips + article captures + a counter, same voice

How it works

script.txt ──voice──▶ narration.wav ──align──▶ words.json
                                                  │
assets (web images, article shots, clips) ────────┼──▶ build.py (shot list, anchored to phrases)
                                                  ▼
                              timeline.js ──render──▶ frames ──encode──▶ video.mp4 (+ sfx, music)
                                                                └──audit──▶ contact sheets

Voice: Kokoro TTS, sentence by sentence with natural gaps. Any recorded narration works too.
Align: whisper word timestamps. Every shot is anchored to a phrase, so re-recording the voice never breaks the sync.
Assets: images the relevant Wikipedia articles actually use (licensed, with a manifest and an attributions file), article screenshots scrolled to the paragraph, video clips cut into frames, made cards and diagrams.
Timeline: a tiny Pyth