faceless-explainer

Convert text into narrated motion-explainer videos with illustrated assets and HTML frame compositions.

Updated Jul 22, 2026
One-click install
npx skills add https://github.com/Chau165/local_skill --skill faceless-explainer-chau165
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: faceless-explainer
Source: https://github.com/Chau165/local_skill/tree/main/codex/skills/faceless-explainer
Command: npx skills add https://github.com/Chau165/local_skill --skill faceless-explainer-chau165

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? Turning an article, notes, or a script into a coherent explainer video requires coordinating storyboarding, narration, asset production, animation, and rendering — this Skill orchestrates that entire pipeline as a gated, step-by-step workflow. ## Core Features & Use Cases - Text-to-Video Pipeline: Transforms arbitrary text into a frame-by-frame storyboard, script, and final rendered MP4 via HyperFrames, with no website capture required. - World-First Visual Design: Builds a persistent illustrated world with characters, props, and environments from concrete nouns in the source text, producing original cartoon/cutout assets instead of slide-like cards. - Audio & Caption Automation: Generates TTS narration with word timings, retrieves background music, fetches SFX, syncs frame durations, and builds timed captions deterministically. - Use Case: Paste a blog post explaining compound interest and receive a narrated, illustrated motion-explainer MP4 with a continuous visual world, captions, and background music. ## Quick Start Turn this article about how compound interest works into a narrated cartoon explainer video with illustrations and captions.

Frequently Asked Questions about faceless-explainer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn an article into an explainer video?

Provide the article text and the Skill runs a gated pipeline: brief setup, design preset selection, storyboard and script drafting, audio generation, illustrated asset production, per-frame HTML composition, and final MP4 rendering via HyperFrames.

How to make a faceless video without recording a website?

This workflow is faceless by design — visuals are invented or generated downstream from the text rather than captured from a site. Concrete nouns in the source become illustrated characters, props, and environments in a continuous world.

Does the explainer video support narration and background music?

Yes, it generates TTS narration with word-level timings via HeyGen or the offline Kokoro engine, and retrieves background music matched to the storyboard's mood. Setting music to none with no script marks the project fully silent.

Can I use my own brand colors and fonts in the video?

Yes, add brand colors and fonts to tokens.json and the build-frame script remixes a chosen design preset onto them, mapping colors by role and swapping font families while preserving the preset's structure.

Why does assembly fail when background music is still generating?

Assembly refuses to build when audio_meta.json carries bgm_pending, because it cannot distinguish a still-generating track from an intentionally silent film. Wait for the track, re-run the audio step, or pass --allow-pending-bgm for a deliberate silent preview.