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."