ascii-video

Convert video, audio, images, and text into colored ASCII character video outputs.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/MarbleSodas/Mavis --skill ascii-video-marblesodas
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/MarbleSodas/Mavis/tree/main/skills/creative/ascii-video
Command: npx skills add https://github.com/MarbleSodas/Mavis --skill ascii-video-marblesodas

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Users need a way to transform video and audio into visually compelling, shareable ASCII art motion—without manual, frame-by-frame crafting.

Core Features & Use Cases

  • Video-to-ASCII rendering: convert video (and images) into colored ASCII MP4/GIF outputs using multi-grid rendering and palette mapping.
  • Audio-reactive ASCII visuals: drive motion, color, and effects from audio features (FFT bands, beat detection, energy and timbre metrics).
  • Generative and hybrid modes: create procedural ASCII animation, or combine video with audio-reactive overlays and timed text/TTS.

Quick Start

Ask an agent to use the ascii-video skill to convert your uploaded video into a 1080p 24fps colored ASCII MP4 using the audio-reactive hybrid mode when audio is present.

Frequently Asked Questions about ascii-video

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

FAQPage Schema
How do I convert video into colored ASCII art animation?

To convert video into colored ASCII art animation, the skill applies a six-stage pipeline including multi-grid rendering, adaptive brightness normalization, and ffmpeg encoding to generate single-file MP4 or GIF outputs.

Can I create audio-reactive ASCII visualizers from music?

Yes, you can create audio-reactive ASCII visualizers by driving motion, color, and effects from extracted audio features including FFT bands, beat detection, energy, and timbre metrics.

Does this video rendering pipeline require manual frame-by-frame editing?

No, colored ASCII video rendering requires no manual frame-by-frame crafting because the pipeline automates scene rendering, adaptive brightness normalization, and ffmpeg encoding into deterministic single-file Python generation.

What is the best way to generate procedural ASCII animation with timed text overlays?

The best way to generate procedural ASCII animation with timed text overlays is using the hybrid mode, which combines video with audio-reactive overlays and timed text or TTS narration.

Are there limitations when using ffmpeg encoding for ASCII video rendering?

A key limitation of ffmpeg encoding for ASCII video rendering is that outputs are bound to deterministic, single-file Python generation, meaning complex multi-grid rendering and shader feedback require precise pipeline staging.

Do I need Python to use this ascii-video skill?

Yes, you need Python because the skill relies on deterministic single-file Python generation to execute the multi-grid rendering, tonemap, shader, and ffmpeg encoding pipeline.