Alisa0808/vox-director

What it solves

Vox Director automates the creation of editorial-style "paper-collage" explainer and advertisement videos. It eliminates the manual effort of scripting, designing keyframes, animating, and adding audio, allowing users to turn a single topic into a finished video with minimal human input.

How it works

The project operates as an agent skill that integrates with coding agents (like Claude Code or Codex) and the Atlas Cloud API. It follows a structured pipeline driven by a beats.json file:

1. Beat Mapping: A narrative arc is selected and a beat map is created for user approval.
2. Style Bake-off: Multiple visual themes are rendered for the user to choose from.
3. Keyframe Generation: High-detail collage posters are generated for each beat using text-to-image models.
4. Motion: These posters are animated using image-to-video models or a local keyframe engine for precise element-level motion.
5. Audio: Narration and background music are generated using TTS and music models.
6. Assembly: ffmpeg is used to concatenate clips, balance audio (ducking), and burn in captions and watermarks.

Who it’s for

It is designed for creators and developers who use AI coding agents and want to produce high-quality, stylized educational or promotional video content without needing professional motion graphics software.

Highlights

• End-to-end Automation: Handles everything from the initial script to the final .mp4 file.
• Collage-First Approach: Focuses on creating rich, detailed static posters first to ensure the visual DNA (torn paper, halftone dots) is preserved before animation.
• Human-in-the-loop: Includes two critical decision gates (beat map and style selection) to ensure the final output matches the user's vision.
• Flexible Animation: Supports both general AI-driven animation and a local engine for pixel-exact motion of specific elements.