What problem does it solve?
Convert audio, images, video, or generative algorithms into high-quality, colored ASCII character video without needing a GPU, removing the manual work of designing multi-scale character renderers, color harmonies, and encode pipelines.
Core Features & Use Cases
- Multi-mode pipeline: video-to-ASCII conversion, audio-reactive visualizers, generative animations, hybrid video+audio overlays, timed lyrics, and TTS-narrated sequences.
- Production-grade renderer: multi-density grids, pre-rasterized font bitmaps, 24-bit per-cell color via OKLAB/OKLCH workflows, composable shader chain, feedback buffers, and ffmpeg-based parallel encoding.
- Practical optimizations and tooling: hardware detection and quality profiles, adaptive tone-mapping, palette validation, particle systems, masking, and extensive references for effects, composition, and troubleshooting.
- Use Case: create a narrated testimonial video that overlays typewriter text, audio-reactive particles, and a cinematic shader stack, rendering to MP4 with synchronized TTS and background music.
Quick Start
Render a 30-second audio-reactive ASCII video from song.mp3 to MP4 at 1920x1080 using the production quality profile.