Skip to content
v0.2.1MIT

Finished videos with expressive voices, made from code: script, emotional narration checked by speech recognition, word-timed captions, React/TypeScript scenes (2D and 3D), original music, GPU render, export check and a share-ready MP4.

aria-video

Aria's video generation. Write scenes as React/TypeScript compositions (2D motion graphics, karaoke captions, 3D with lights, materials, Text3D and bloom), cue them on narration words from captions.json, score original music with Tone, mix to -14 LUFS, render on the GPU, check the export (clipped text, safe areas, contrast, loudness, blotching) and encode share copies. Use for making or fixing any Aria video, shorts/reels/TikTok 9:16, 16:9 films, explainers, promos, story videos, motion graphics or 3D scenes rendered from code.

Read SKILL.md at the source

Pinned to revision ffe2a54fb66f, so it is the text this page describes rather than whatever the author pushed since.

Files

Every link opens the file at its source, pinned to the revision this page describes.