ascii-video

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

Updated Apr 11, 2026
One-click install
npx skills add https://github.com/musical-basics/hermes-build-2 --skill ascii-video-musical-basics
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/musical-basics/hermes-build-2/tree/main/skills/creative/ascii-video
Command: npx skills add https://github.com/musical-basics/hermes-build-2 --skill ascii-video-musical-basics

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Turn audio, video, images, or generative parameters into high-fidelity, full-color ASCII character video so creators can produce cinematic, shareable outputs without manual frame-by-frame art or GPU dependencies.

Core Features & Use Cases

  • Video-to-ASCII conversion that preserves source color and detail for MP4, GIF, or image-sequence outputs.
  • Audio-reactive visualizers and generative animations with beat-detection, multi-band FFT, and bdecay-driven effects.
  • Multi-density grid rendering, pre-rasterized character bitmaps, OKLAB/OKLCH color interpolation, adaptive percentile tonemapping, ShaderChain post-processing, and temporal FeedbackBuffer recursion.
  • TTS-narrated testimonial rendering, lyrics/SRT overlays, and hardware-adaptive quality profiles for draft → production workflows.

Quick Start

Render a 30-second audio-reactive colored ASCII MP4 from an input audio file using the skill's default production pipeline.

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 while preserving the original color?

Video-to-ASCII conversion preserves source color and detail by applying OKLAB color mapping and adaptive percentile tonemapping, outputting high-fidelity full-color ASCII characters as MP4, GIF, or image sequences.

Can I create audio-reactive ASCII music visualizers from an audio file?

Audio-reactive ASCII music visualizers are generated from audio files using beat-detection, multi-band FFT, and bdecay-driven effects to produce cinematic colored character animations.

Do I need a GPU to render full-color ASCII videos?

No GPU dependencies are required to render full-color ASCII videos. The pipeline runs on Python 3.10+ with NumPy, Pillow, optional SciPy or OpenCV, and encodes output via ffmpeg.

What is the best way to add timed lyrics overlays to an ASCII video?

Timed lyrics or SRT overlays are applied directly within the ASCII video pipeline, syncing text with multi-density grid rendering and ShaderChain post-processing for cinematic outputs.

Can I generate TTS-narrated ASCII videos for short-form content?

TTS-narrated testimonial rendering is supported using optional ElevenLabs integration, combining generated speech with ASCII character video for short-form or cinematic outputs.

What output formats are supported when exporting ASCII video animations?

ASCII video animations export as MP4, GIF, or image sequences. Encoding is handled by ffmpeg, utilizing adaptive quality profiles for draft to production workflows.