What problem does it solve?
Users need a fast way to convert videos, audio-reactive inputs, or text/lyrics into engaging, non-trivial animated ASCII output without writing the whole renderer and rendering pipeline from scratch.
Core Features & Use Cases
- What it renders: Converts video/audio/images/text into colored ASCII animation, producing MP4/GIF/image-sequence style output.
- Audio-reactive modes: Drives visuals from FFT bands, beat detection, and energy features for music visualizers and hybrid overlays.
- Generative and hybrid production: Supports fully procedural ASCII animation and video+audio blended scenes, including lyrics/text timing and optional TTS narration.
- Full creative pipeline: Builds the end-to-end pipeline including grid/font rendering, effect/shader composition, tonemapping for ASCII-on-black brightness, and ffmpeg encoding.
Quick Start
Use the ascii-video skill to render an MP4 from an input video by asking: "Convert 'my_clip.mp4' into a colored ASCII video at 1080p, 24fps."