ascii-video

Convert video, audio, images, or prompts into colored ASCII video files.

Updated May 1, 2026

Search Tags:#video #visualization #ffmpeg #ascii #shader #tonemap #multigrid

Ready to run

npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill ascii-video-xiaoquqi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ascii-video
Source: https://github.com/xiaoquqi/hermes-agent-skills/tree/main/creative/ascii-video
Command: npx skills add https://github.com/xiaoquqi/hermes-agent-skills --skill ascii-video-xiaoquqi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

ASCII video generation from diverse inputs—video, audio, images, or generative prompts—without manual frame-by-frame work.

Core Features & Use Cases

Production pipeline to convert inputs into colored ASCII video (MP4, GIF, image sequence)
Supports multiple modes: Video-to-ASCII, Audio-reactive visuals, Generative ASCII art, Hybrid with audio, Text/lyrics overlays, TTS narration
Multi-grid composition, tone-mapping, shader pipeline, and temporal feedback for rich visuals
Real-world use: artifacts, matrix-style visuals, data visualization, retro-style video.

Quick Start

Run the ASCII-video pipeline by selecting a mode, supplying input data, and rendering to an MP4, GIF, or image sequence.

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 without manual frame-by-frame editing?▼

You can convert video to colored ASCII art by running an automated production pipeline that processes inputs directly into an MP4, GIF, or image sequence. This avoids manual frame-by-frame work by utilizing a shader pipeline and tone-mapping for rich visual output.

Can I generate audio-reactive ASCII visuals from an audio file?▼

Yes, you can generate audio-reactive ASCII visuals by selecting an audio-reactive mode. The pipeline processes audio inputs to create dynamic visuals, supporting hybrid modes that combine audio with text or lyrics overlays for synchronized storytelling.

Does generating ASCII video require ffmpeg and Python installed on my system?▼

Yes, generating ASCII video requires Python 3.10+, NumPy, Pillow, SciPy, and ffmpeg on your PATH. A monospace font is also necessary to ensure the ASCII characters render correctly in the final video output.

What is the best way to create multi-grid ASCII video compositions for data visualization?▼

The best way to create multi-grid ASCII video compositions is to use the pipeline's built-in multi-grid composition feature. This approach applies temporal feedback and tone-mapping to produce complex, retro-style data visualization artifacts.

Can I use generative prompts to create matrix-style ASCII video artifacts?▼

Yes, you can use generative prompts to create matrix-style ASCII video artifacts. The pipeline supports generative ASCII art modes, utilizing shader pipelines and temporal feedback to transform text prompts into dynamic visual outputs.

What are the limitations of using ASCII video for media-art projects?▼

Limitations of ASCII video include dependency on a monospace font for correct character rendering and requiring specific environmental setups like ffmpeg on PATH. Complex visual outputs depend on tone-mapping and shader pipeline configurations.