ascii-video

Convert video, audio, images, or generative parameters into full-color ASCII character video.

247|22|Updated Dec 11, 2024
One-click install
npx skills add https://github.com/graniet/kheish --skill ascii-video-graniet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/graniet/kheish/tree/main/skills/creative/ascii-video
Command: npx skills add https://github.com/graniet/kheish --skill ascii-video-graniet

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Creating video content from non-video sources or converting existing footage into a distinctive retro-terminal aesthetic traditionally requires complex manual compositing or specialized GPU hardware. This skill eliminates that barrier by providing a complete CPU-based pipeline that transforms video, audio, images, or mathematical functions into full-color ASCII character animations.

Core Features & Use Cases

  • Multi-Modal Input: Accepts video files, audio tracks, static images, or pure generative parameters to produce MP4, GIF, or PNG sequences.
  • Cinematic ASCII Rendering: Produces 1080p 24fps video with full RGB color per character cell using a 6-stage pipeline and 38 composable post-processing shaders.
  • Audio-Reactive Visuals: Analyzes FFT bands, beats, and spectral features to drive generative visuals, music visualizers, or karaoke-style text overlays with beat-synced glitch and particle effects.

Quick Start

Use the ascii-video skill to convert the uploaded music file 'track.mp3' into a 3-minute audio-reactive ASCII music visualizer with beat-triggered particles and a cyberpunk color palette.

Frequently Asked Questions about ascii-video

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

FAQPage Schema
How do I convert a video to ASCII art without a GPU?

You can convert video to ASCII art entirely on CPU by running a Python 3.10+ pipeline that uses NumPy, SciPy, and ffmpeg to render full-color character animations and encode them into MP4 output. This process applies a 6-stage rendering pipeline with parallel encoding to generate 1080p 24fps video without requiring GPU acceleration.

Can I create audio-reactive music visualizers using ASCII characters?

Yes, you can create audio-reactive ASCII music visualizers by analyzing FFT bands, beats, and spectral features from audio tracks to drive generative visuals. The pipeline applies beat-synced glitch and particle effects using 38 composable post-processing shaders to produce encoded MP4 or GIF deliverables.

What do I need to generate ASCII video from images or generative parameters?

To generate ASCII video from images or generative parameters, you need Python 3.10+, NumPy, Pillow, SciPy, and ffmpeg installed in your environment. The pipeline processes these multi-modal inputs through adaptive tone mapping and cinematic ASCII rendering to output MP4, GIF, or PNG sequences.

Does ffmpeg support parallel encoding for ASCII video generation?

Yes, ffmpeg supports parallel encoding for ASCII video generation through the deterministic 6-stage rendering pipeline. This pipeline leverages CPU-based parallel processing alongside adaptive tone mapping and 38 composable shader effects to produce 1080p 24fps full-color ASCII character video output.

What is the best way to make a karaoke video with ASCII text overlays?

The best way to make an ASCII karaoke video is to process audio tracks through an FFT and beat analysis pipeline that drives beat-synced text overlays. This CPU-based pipeline applies generative ASCII rendering with composable shader effects to output full-color MP4 or GIF deliverables.