ascii-video

Convert video and audio into colored ASCII character animations encoded as MP4 or GIF.

Updated May 15, 2026
One-click install
npx skills add https://github.com/cabezno/bmb-encover-agent --skill ascii-video-cabezno
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/cabezno/bmb-encover-agent/tree/main/skills/creative/ascii-video
Command: npx skills add https://github.com/cabezno/bmb-encover-agent --skill ascii-video-cabezno

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill removes the friction of building a full ASCII animation pipeline by generating real MP4/GIF output with colored character frames from video, audio, images, or text.

Core Features & Use Cases

  • Video/audio-to-ASCII rendering pipeline: converts input into colored ASCII character video (MP4/GIF or image sequence) with a configurable multi-grid look.
  • Audio-reactive visual synthesis: drives scene visuals using per-frame audio features (FFT bands, beat detection, energy/flux/centroid).
  • Generative + hybrid + lyric/TTS modes: renders procedural ASCII animations, blends video+audio reactivity, overlays timed lyrics, and supports narrated output.
  • Cinematic post-processing: applies a shader chain (CRT/glitch/bloom/vignette/grain/color grading) plus temporal feedback for recursive trails.

Quick Start

Use the skill to render an audio-reactive ASCII MP4 from a local file by running it with a request like: "Create a 2-minute audio-reactive colored ASCII video from song.mp3 at 1080p 24fps."

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 to ASCII animation with colored characters?

Audio-reactive ASCII visuals are synthesized by driving scene graphics using per-frame audio features like FFT bands, beat detection, energy, flux, and spectral centroid extracted from the input audio file.

What is the best way to create an audio-reactive ASCII music visualizer?

Audio-reactive ASCII visuals are synthesized by driving scene graphics using per-frame audio features like FFT bands, beat detection, energy, flux, and spectral centroid extracted from the input audio file.

Does ffmpeg support adding shader effects like CRT or glitch to ASCII video?

Yes, the pipeline supports generative and hybrid modes that blend video and audio reactivity, overlay timed text or lyrics, and include optional TTS narration rendered directly into the output file.

Can I add timed text overlays and TTS narration to generative ASCII art?

Yes, the pipeline supports generative and hybrid modes that blend video and audio reactivity, overlay timed text or lyrics, and include optional TTS narration rendered directly into the output file.

What resolution and frame rate should I target for colored ASCII video rendering?

Colored ASCII video rendering supports configurable outputs like 1080p at 24fps, balancing MP4 encoding efficiency with the multi-grid character density needed for clear visual fidelity.