ascii-video

Convert video and audio into colored ASCII video frames with shaders.

11|Updated May 17, 2026
One-click install
npx skills add https://github.com/StarryCod/cogitum --skill ascii-video-starrycod
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/StarryCod/cogitum/tree/main/cogitum/data/skills/creative/ascii-video
Command: npx skills add https://github.com/StarryCod/cogitum --skill ascii-video-starrycod

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Create visually striking colored ASCII representations of video and audio, enabling retro, text-art style outputs for storytelling, data visualization, and creative expression.

Core Features & Use Cases

  • Multi-mode rendering: Video-to-ASCII, Audio-reactive visuals, Generative ASCII art, Hybrid video+audio, and TTS-narrated overlays.
  • Multi-grid composition: Simultaneous use of several character grids at different sizes to produce rich, textured frames.
  • Colorful palettes and shaders: Per-frame hue mapping, tone mapping, and post-processing shaders for cinematic aesthetics.
  • Production-grade workflow: Input handling, frame-by-frame rendering, and output in MP4 or GIF formats with optional narration.
  • Use Case: Transform a music video into an ASCII art piece with beat-synced visuals and a spoken narration overlay.

Quick Start

Start by feeding a video into the pipeline and render an ASCII video output with color, grids, and shader effects.

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 colored ASCII art animations?

You can convert video to colored ASCII art using a multi-grid rendering pipeline with per-frame hue mapping and post-processing shaders. The workflow processes input video frame-by-frame and outputs the result as an MP4 or GIF file.

Can I generate audio-reactive ASCII visuals from a music track?

Yes, you can generate audio-reactive ASCII visuals by feeding audio input into the rendering pipeline. The system supports audio-reactive modes that drive textual art grids in sync with the audio track.

What do I need to render ASCII video with ffmpeg and Python?

To render ASCII video, you need Python 3.10 or higher, ffmpeg, and a monospace font installed in your environment. These dependencies are required to handle input processing and frame-by-frame textual rendering.

Does the ASCII video renderer support text-to-speech narration overlays?

Yes, the ASCII video renderer supports optional text-to-speech narration overlays. You can add TTS audio to your MP4 or GIF output to create narrated visualizations for storytelling or accessibility-friendly contexts.

What is the best way to create multi-grid ASCII frames for retro art?

The best way to create multi-grid ASCII frames is using simultaneous character grids at different sizes to produce rich, textured frames. This approach combines colorful palettes and tone mapping shaders for cinematic retro aesthetics.

Why use post-processing shaders for ASCII video generation?

Post-processing shaders apply per-frame hue mapping and tone mapping to ASCII video generation, enhancing the cinematic aesthetics of the textual frames. This ensures colored ASCII output maintains rich visual depth and texture.