# Vox Director

Agent skill that turns one topic into a Vox-style paper-collage explainer with Atlas Cloud and ffmpeg.

A Claude Code or Codex skill: the agent drafts a beat map, runs a style bake-off, generates collage posters and motion, adds narration and music, and assembles final.mp4. Every model call goes through the Atlas Cloud API; the look lives in editable prompt guides.

- Capabilities: adaptable, operable
- Vertical: video-streaming
- Shape: skill
- Form factor: skill
- Execution model: hybrid
- Provenance: unknown (recorded, never ranked)
- Repo: https://github.com/Alisa0808/vox-director (MIT), 1700 stars, last commit 2026-08-11
- Last activity: 2026-08-11
- Page: apps/alisa0808--vox-director.html
- JSON: apps/alisa0808--vox-director.json

## Use it when

- I want a 60-second explainer in the Vox collage look for a topic, produced while I approve two checkpoints
- I have a product photo or a talking-head clip and want it restyled into a collage ad

## Gotchas

- Single provider: everything runs through Atlas Cloud and costs credits per stage
- Model IDs drift; the skill fetches the live model list before each run
- Real people and brands are routed to Kling, which is pricier and has content filters

## Editions

- Free: Free, open source
  - source: https://github.com/Alisa0808/vox-director
  - installable: git clone https://github.com/Alisa0808/vox-director.git ~/.claude/skills/vox-director

## Adaptable: make it yours

Effort: config-only (8 things to edit)

Export ATLASCLOUD_API_KEY, then change the look by editing references/prompt-guide.md (theme presets and prompt structures), the narrative arcs in references/beat-layer.md, and the voice roster in references/voices.md. Per-project beats.json is the working file; examples/ has starters.

- Env vars: ATLASCLOUD_API_KEY
- Config files: beats.json, examples/
- Prompt files: SKILL.md, references/prompt-guide.md, references/beat-layer.md, references/voices.md, references/models-and-gotchas.md
- Accounts you'll need: Atlas Cloud

## Operable: what an agent can drive

Operability: native. Interface: cli at https://github.com/Alisa0808/vox-director/blob/main/SKILL.md (published by the builder, local).

### Reach (complete coverage)

- Write a beat map from a topic: reachable. README pipeline stage 1; beats.json per project; Gate 1 approval
- Style bake-off across themes: reachable. README stage 2; 9 theme presets in references/prompt-guide.md
- Generate collage keyframe posters: reachable. README stage 3 with nano-banana-2
- Animate posters into motion: reachable. README stage 4; gemini-omni-flash or Kling for real people
- Narration and background music: reachable. README stage 5; xai/tts and minimax/music
- Assemble with captions, ducking, watermark: reachable. README stage 6; ffmpeg concat and Pillow overlays
- Re-style an existing talking-head video (A-roll): reachable. README: ASR-segmented, gemini-omni-flash/video-edit with seedance fallback
- Anchor a still photo in the collage (C-roll): reachable. README: nano-banana-2/edit; optional voice cloning
- Element-level piece-by-piece motion: reachable. README: optional local keyframe engine in references/local-engine.md

## Code stack

- Languages: Python
- Frameworks: ffmpeg, Pillow
- Package manager: pip
- Database: none
- Hosting target: local

## Model stack

- Providers: Atlas Cloud
- Models: google/nano-banana-2/text-to-image, google/gemini-omni-flash/image-to-video, kwaivgi/kling-video-o3-pro/image-to-video, xai/tts-v1, bytedance/seed-audio-1.0, minimax/music-2.6
- Keys you need (names only): ATLASCLOUD_API_KEY
- Prompts live in: SKILL.md, references/prompt-guide.md, references/beat-layer.md, references/voices.md
- Tools: scripts/ one per pipeline stage

## Skills

pure: Repo is a single voice-direction skill: SKILL.md plus reference prompt files and helper scripts, no app of its own.
- Paths: SKILL.md, references/, vox-director.skill

## Evidence and confidence

- formFactor: README: agent skill; Claude Code auto-discovers it, AGENTS.md for other agents (confidence 0.95)
- executionModel: README: one script per stage in fixed order; models generate images, motion, voice, music (confidence 0.9)
- operability: README: usable by any coding agent; the skill is the only interface (confidence 0.9)
- effort: README install: export ATLASCLOUD_API_KEY; 'What's in the box' lists the prompt files (confidence 0.9)
- editions: README license: MIT (confidence 0.95)
- active: GitHub pushedAt 2026-08-11
- reach:  (confidence 0.85)

## Open questions

- Operable fit held at 2 because the software is prompts plus scripts around one third-party API; the Curator may judge it a thin wrapper or a real product on the strength of 1.7k stars
- Provenance: single-author agent-skill experiment; no statement on how the scripts were written

## Sources

- https://github.com/Alisa0808/vox-director (sourcing:video-streaming:curated)
