What problem does it solve?
It removes the effort of manually creating animated ASCII art by providing a complete end-to-end pipeline that converts video, audio, images, or text into production-ready colored ASCII video output.
Core Features & Use Cases
- Media-to-ASCII Production Pipeline: converts input into colored ASCII frames and encodes MP4/GIF or image sequences, including video-to-ASCII and generative modes.
- Audio-Reactive Visuals: analyzes audio (FFT bands, RMS, centroid, flux, beat detection) to drive beats and spectral energy into music visualizers.
- Rich Visual Effects System: supports multi-grid composition (multiple character densities), adaptive tonemapping, shader chains (CRT/glitch/bloom/etc.), and temporal feedback for trails and recursion.
- Text & Narrative Rendering: overlays timed lyrics (SRT) and optional TTS narration (ElevenLabs) with dedicated text rendering modes.
Quick Start
Use the ascii-video skill to render an audio-reactive ASCII music visualizer from the attached file 'track.mp3' into an MP4 video.