faceless-explainer

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

Updated Aug 25, 2026
One-click install
npx skills add https://github.com/Sergiotsk/Interstellar --skill faceless-explainer-sergiotsk
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: faceless-explainer
Source: https://github.com/Sergiotsk/Interstellar/tree/main/.agents/skills/faceless-explainer
Command: npx skills add https://github.com/Sergiotsk/Interstellar --skill faceless-explainer-sergiotsk

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 scripting, design, voiceover, and video editing skills. This Skill orchestrates that entire pipeline in HyperFrames, producing a rendered MP4 from plain text with no website or footage to capture. ## Core Features & Use Cases - Text-to-Video Pipeline: Runs a gated seven-step workflow from brief setup through storyboard, script, audio, frame building, and final MP4 render. - Invented Visuals: Generates typography, abstract graphics, diagrams, and data visualizations per scene since there are no captured assets. - Narration and Audio: Produces TTS voiceover with word timings, retrieves background music, and fetches sound effects via the HeyGen audio engine. - Use Case: Paste an article explaining compound interest and receive a storyboarded, narrated, captioned explainer video rendered to renders/video.mp4. ## Quick Start Turn this article about compound interest into a 60-second faceless explainer video with a male narrator.

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 synthetic capture package, drafts a storyboard and narration script, generates voiceover and music, then builds each frame as an HTML composition and renders a final MP4 through HyperFrames.

What is a faceless explainer video?▼

A faceless explainer is a video with no captured footage or real asset inventory; every visual is invented per scene using typography, abstract graphics, diagrams, and data visualizations. It suits topic explainers, how-tos, and listicles.

Can I choose the narration voice for the video?▼

Yes, pass a voice preference in your request and the workflow resolves a matching voice id from the HeyGen or Kokoro provider. Without a preference it falls back to a remembered voice or the pipeline default.

Does this workflow support videos without narration or music?▼

Yes, setting music to none in the storyboard frontmatter with no script file marks the project fully silent, so no TTS, BGM, or SFX is generated. Music none with a script keeps narration but disables only the music bed.

When should I use a product launch video workflow instead?▼

Use a captured-asset workflow when the video promotes or tours an existing website or product, since that route captures real screens and assets. This skill is only for explaining a topic from text with invented visuals.