faceless-explainer

Convert text into faceless explainer videos with invented visuals and narration.

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/celeroncoder/skills --skill faceless-explainer-celeroncoder
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: faceless-explainer
Source: https://github.com/celeroncoder/skills/tree/main/faceless-explainer
Command: npx skills add https://github.com/celeroncoder/skills --skill faceless-explainer-celeroncoder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve? Turning an article, notes, or a topic brief into a polished explainer video normally requires sourcing footage, designing scenes, recording narration, and assembling a timeline by hand. This Skill orchestrates that entire pipeline in HyperFrames, inventing every visual (typography, diagrams, data-viz) from the text itself since there is no website or footage to capture. ## Core Features & Use Cases - End-to-end orchestrated workflow: Seven gated steps from brief setup through storyboard, script, audio (TTS narration, BGM, SFX), frame building, and final MP4 render. - Design system presets: Adopts a shipped frame preset and deterministically remixes it onto brand colors and fonts via the build-frame script. - Parallel frame production: Dispatches one sub-agent per storyboard frame to build HTML compositions, then assembles captions, transitions, and audio tracks into the final video. - Use Case: Paste a blog post explaining compound interest and receive a narrated, captioned 1080p explainer video with animated diagrams and background music. ## Quick Start Turn this article about compound interest into a 60-second narrated explainer video with captions and background music.

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 builds a storyboard and script, generates narration and background music, designs each frame with invented visuals like typography and diagrams, then renders a final MP4. You approve the plan and the final preview at gated review steps.

What is a faceless explainer video?▼

A faceless explainer is a video where every visual is invented per scene rather than captured from a website or footage. Visuals use typography, abstract graphics, diagrams, and data visualizations paced to a voiceover script.

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

Yes. Add brand colors and fonts to the project's tokens.json and the build-frame script remixes a design preset onto them, mapping colors by role and swapping font families. Without brand tokens, the preset's complete default palette is used.

Does the video support narration and background music?▼

Yes. The audio step generates TTS narration with word-level timings via HeyGen or the offline Kokoro engine, retrieves BGM matching the storyboard's music mood, and fetches per-frame sound effects. Setting music to none with no script marks the project fully silent.

When should I not use the faceless explainer workflow?▼

Do not use it for videos built from an existing website or product, such as promos or site tours; those route to the product-launch-video workflow instead. It is specifically for explaining a topic from text with no capturable assets.