vox-director
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Badge for your README
Markdown
[](/listings/alisa0808--vox-director)HTML
<a href="/listings/alisa0808--vox-director"><img src="/api/listings/alisa0808--vox-director/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
This is an **agent skill** — it works with any coding agent that can read a workflow and run scripts (Claude Code, Codex, …). Claude Code auto-discovers it as a skill; other agents read [`AGENTS.md`](AGENTS.md) → [`SKILL.md`](SKILL.md).
**Option A — from this repo:**
git clone https://github.com/Alisa0808/vox-director.git ~/.claude/skills/vox-director
**Option B — from the packaged skill:** download [`vox-director.skill`](vox-director.skill) and install it via your Claude skills UI.
Then set your Atlas Cloud API key (get one at [atlascloud.ai/console/api-keys](https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=vox_director)):
export ATLASCLOUD_API_KEY="sk-..."
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
SKILL.md · Manifest · 331 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- ---
- name: vox-director
- description: >
- Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end
- on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over,
- music, captions, all automated. Use this whenever the user wants a "Vox style" video,
- a paper/torn-paper collage animation, a "motion collage", a narrated explainer or short
- ad built from AI-generated collage posters, a scrapbook-style tribute, or wants to turn
- a topic / product / person into a punchy narrated collage video — even if they don't say
- the word "Vox". Also use when reproducing Stav Zilber / rom1trs / Higgsfield-style collage
- ad workflows.
- Three input modalities: a topic (B-roll), a talking-head video (A-roll mode), or a single
- photo of a person/product anchored into the collage (C-roll mode).
- Triggers: "vox video", "collage video", "motion collage", "paper collage
- explainer", "make a collage ad", "turn this topic into a collage video", "turn my
- photo/this product shot into a collage video".
- ---
- # Vox Director
- Turn a one-line topic into a finished **Vox-style paper-collage video**: a bold, punchy,
- narrated explainer/ad where each beat is a torn-paper collage poster that comes alive, with
- voice-over, music and captions. Runs on **one Atlas Cloud API key** + local **ffmpeg**.
- The look is the modern editorial paper-collage popularized by Vox explainers and creators
- like Stav Zilber / rom1trs: hand-cut paper cut-outs, torn edges, tape, halftone dots,
- newspaper clippings, bold flat color per beat, big cut-out headlines.
- ## The core idea (read this first)
- The Vox collage look and the collage motion are **two different steps**:
- 1. **The look is born in the IMAGE step.** Each beat is a finished collage *poster* made by a
- text-to-image model. All the collage DNA (torn paper, cut-outs, halftone, bold color,
- headline text) lives in that image. If the image isn't a rich collage, nothing downstream
- will save it.
- 2. **The motion is added after.** By default an AI video model animates the whole poster (the
- "living poster" path — simple, automated). For dramatic *piece-by-piece* assembly you cut
- the poster into parts and drive them with the local keyframe engine (advanced path).
- Everything hinges on the prompts. **Before writing any image or video prompt, read
- `references/prompt-guide.md`** — it has the exact prompt structures that make the difference
- between "a real Vox collage" and "a moving PowerPoint".
- ## Prerequisites (check, don't skip)
- - `echo "${ATLASCLOUD_API_KEY:+set}"` — if empty, tell the user to set it (get one at
- https://www.atlascloud.ai/console/api-keys) and stop.
- - `command -v ffmpeg ffprobe` — required for assembly (`brew install ffmpeg` on macOS).
- - `python3 -c "import PIL"` — Pillow, for captions/watermark overlays.
- ## Standard workflow (topic → film)
- This is the default, most-automated path. Every stage is one script, all driven by a single
- `beats.json` per project under `out/<project>/`.
- 1. **Topic → beat map.** First **read `references/beat-layer.md`** (the story layer) and pick a
- narrative `arc` that fits the topic (`timeline` for history, `pas`/`bab` for ads,
- `how_it_works` for explainers, `man_in_hole` for transformations, …). Then write
- `out/<project>/beats.json` following that arc: **beat-1 headline must be a ≤3s hook**; beat
- count per duration (30s→6–8, 60s→10–12); split each beat into **2 shots** (wide+detail) with
- **per-shot `camera_move` VARIED across adjacent beats** (never repeat; `static` on the payoff)
- and **rich `element_motion`** (see step 4). Each beat: `narration`, `title_cn`/`title_en`,
- `scene`, `bg`, `feel`, `hook`. This draft is the **first mandatory approval gate** — show the
- user the beat map before generating (the aspect-routing approximation in step 4 is the other
- one). Examples in `examples/`.
- 2. **Pick the visual style (hybrid — do this BEFORE keyframes).** Do not reuse one house style
- for every topic. Read `references/prompt-guide.md` (§5 theme presets); pick 3–4 **theme presets**
- (`styles.THEME_PRESETS`: `american-retro`, `swiss-modern`, `punk-zine`,
- `soviet-constructivist`, `wpa-propaganda`, `70s-groovy`, `chinese-ink`, `atomic-age`,
- `newsprint-editorial`) that fit
- the topic's era/culture/tone — **or compose a custom theme** by mixing the prompt-guide dimensions
- (medium/era/palette/type/finish) when none fit. Match the topic, **not** the language (an
- English film on Chinese history should look Chinese). A theme bundles the whole LOOK layer
- (idiom+palette+type+finish+mood+motion). Run a bake-off and let the user pick by eye — AI
- proposes, the library is the quality floor, the human decides. Set the pick as `"theme"`:
- `python3 scripts/style_bakeoff.py out/<project> american-retro,swiss-modern,punk-zine,atomic-age`
- Set the chosen name as `"collage_style"` in beats.json (keyframes.py reads it).
- 3. **Keyframes (the collage look).** `python3 scripts/keyframes.py out/<project>`
- Generates one collage poster per beat/shot with **google/nano-banana-2/text-to-image**,
- headline text baked in. Compose prompts with the 5-part structure in
- `references/prompt-guide.md`. Verify each poster looks like a *real layered collage*
- before animating — re-roll cheap ($0.08) here rather than paying to animate a weak image.
- 4. **Motion.** `python3 scripts/clips.py out/<project>`
- Animates each poster with **google/gemini-omni-flash/image-to-video**. Two independent axes
- (see `references/beat-layer.md` §3, tested on our stack):
- • **`camera_move`** — ONE move per shot. Safe/default: `{static, push_in, pull_out, pan, tilt,
- parallax}`. **Bold/experimental** `{orbit, dolly_zoom, roll, whip}` are **available, not
- banned** — they can warp the flat art, so pair with `constraints: loose` and **re-roll**.
- Any custom phrase also passes through.
- • **`element_motion`** — where the energy lives; **AI writes it per beat to fit that scene** (not a
- template). Make it RICH (several elements moving) — be bold. A **hero element flying across
- the frame** (paper bird/plane/coins) is a great **occasional** punch on a key beat, **not
- every shot** (a flyer in every frame reads as a formula).
- `motion_style` = amplitude `calm | punchy | max` (the theme sets a default). **`constraints`**
- = `strict` (default: defect guards on — flat-2D, one-way, no-morph; best for clean text-heavy
- explainers) or `loose` (let the model explore 3D/bold moves; re-roll the misses). **Headline
- text is hard-protected only on shots that have a title** (detail shots without a headline are
- free to go wild). For **real people / brand logos**, Omni & Seedance refuse — set
- `"video_model": "kwaivgi/kling-video-o3-pro/image-to-video"`.
- **Aspect routing** (`styles.resolve_video_aspect`, second approval gate): `clips.py` resolves
- `doc["aspect"]` against the chosen `video_model`'s own supported ratios — exact match wins;
- Omni is 16:9/9:16 only, Kling reference-to-video adds 1:1, Kling image-to-video/video-edit and
- Seedance just follow the input/ratio param. When there's no exact match it picks the nearest
- ratio but **stops and asks you to confirm** (set `"aspect_approx_confirmed": true` once you
- have) rather than silently reframing the film — every clip in one run shares the same resolved
- aspect so the finished film is never mixed.
- 5. **Voice + music.** `python3 scripts/audio.py out/<project>`
- One consistent narrator via **xai/tts-v1** + instrumental BGM via **minimax/music-2.6**.
- **Pick `voice_id` to fit the topic + language** (don't just keep the default) — see
- `references/voices.md` for the full roster (5 multilingual + ~66 native voices by language,
- with gender). Default `leo` (male, documentary). To narrate in a REAL person's own voice
- (the presenter of a C-roll photo, a brand voice), set `voice.clone_ref` to a local audio
- sample — narration switches to seed-audio voice cloning with a pinned-speaker,
- studio-clean template that keeps timing beat-stable (see gotchas: never hand seed-audio
- bare narration without that pin).
- 6. **Assemble.** `python3 scripts/assemble.py out/<project>`
- ffmpeg: normalize + concat all shots, lay the single narration ducked under the music,
- burn captions timed per beat, add the watermark. Output `out/<project>/final.mp4`.
- 7. **Verify.** You can't read an mp4 directly — extract frames to jpg and look:
- `ffmpeg -ss <t> -i final.mp4 -vf "scale=640:-1,format=yuvj420p" -frames:v 1 f.jpg`
- ### Cadence — how long shots should be
- A common mistake is one long shot per beat. On a 9:16 / social piece especially, a static
- 10s shot reads as dead air. Aim for a **cut every ~4–6 seconds**:
- - **Shots run 3–6s; never let a single shot exceed ~7s** — beyond that the AI motion has
- nowhere to go and it feels static.
- - **A beat's narration is ~8–10s, so give each beat 2 shots** (a *wide* establishing shot with
- the headline + a *detail* cut-in without it). The narration plays continuously across both;
- the visual cuts mid-sentence. This is the single biggest rhythm win.
- - So a ~60s film is typically **~6 beats × 2 shots × ~5s = 12 shots**, not 6 × 10s.
- - Reuse the wide keyframe as shot `a`; generate a tighter detail scene for shot `b`.
- `keyframes.py` skips any shot that already has a `keyframe_url`, so adding `b` shots and
- re-running only generates the new ones.
- Add a `shots` array to each beat (see schema). Give each shot its own short `scene` and
- `motion`; set `"title": true` only on the wide shot so the headline shows once per beat.
- ## A-roll mode (talking-head → collage)
- The standard workflow above is **B-roll**: a topic becomes AI-generated collage posters
- that get animated. **A-roll is the reverse case** — the user already has a real recorded
- talking-head video (a presenter speaking to camera) and wants it *itself* turned into the
- collage look, keeping their actual performance (face, lip movement, gestures) intact. There
- is no poster to generate; the "keyframe" is the presenter's own footage. Use A-roll when the
- user gives you a video file of themselves/a presenter talking, not a topic to write from
- scratch.
- 1. **Transcribe + auto-segment.** `python3 scripts/asr_beats.py <project_dir> <source.mp4>`
- Runs xai/stt-v1 on the source's own audio and cuts it into beats at sentence-ending
- punctuation or natural pause gaps (never exceeding ~9.5s, under Omni/Kling video-edit's
- 10s per-call cap). Writes `beats.json` with each beat's `start`/`end`/`text` — **this is
- the same mandatory approval gate as the B-roll beat map**: review it, set `"theme"` (run
- `style_bakeoff.py` the same way — the presenter's segment works fine as the bake-off
- source), and optionally fill in a `content_beats` string per beat (a sticker/stamp idea
- to layer in) before generating anything.
- 2. **Generate.** `python3 scripts/aroll_clips.py <project_dir> [only_ids]`
- Cuts each beat's time range out of the source, uploads it, and re-styles it with a
- **photographic paper-cutout sticker** treatment on the presenter — her real likeness,
- lip movement, eye-line and gestures follow the source frame-for-frame; only the
- silhouette edge and the world around her are paper-collage. Default model is
- `google/gemini-omni-flash/video-edit`; any beat it rejects automatically retries on
- `bytedance/seedance-2.0/reference-to-video` (set via `video_model`/`video_model_fallback`
- in beats.json). **Never ask the model to redraw or halftone-texture the face itself** —
- that gets rejected regardless of how the prompt is worded (tried both a strong and a
- softened phrasing; both failed). Uses the same aspect-routing confirm gate as `clips.py`.
- 3. **Assemble.** `python3 scripts/aroll_assemble.py <project_dir>`
- Muxes each generated clip with the *original* beat segment's own audio (never whatever
- audio the video model produced) so lip-sync is guaranteed regardless of which model
- handled that beat, normalizes every beat to one canvas, and concats into `final.mp4`.
- ## C-roll mode (one photo → collage)
- The third input modality — "cutout roll". A-roll re-styles a talking-head VIDEO; B-roll
- generates everything from a topic; **C-roll takes a single still PHOTO** (a selfie, an
- avatar card, a product shot) and anchors it inside the collage world: the subject is cut
- out as a PHOTOGRAPHIC sticker — never redrawn — and per-beat posters are generated around
- it with an image-EDIT model, then animated through the normal clip stage. Use C-roll when
- the user gives you one photo and a topic: a personal explainer fronted by their own face,
- or a collage ad built around a real product shot (validated on both, 2026-07-17).
- 1. **Beat map.** Same as B-roll (`references/beat-layer.md`, same approval gate), plus the
- C-roll fields in beats.json: `"mode": "croll"`, `"anchor_photo"`, `"croll_subject"`
- (`portrait` | `product`), and `subject_wardrobe` (portrait — lock the outfit or the
- paper-doll body drifts) or `subject_desc` (product). Set `"title": false` on shots —
- C-roll posters carry no headline; text belongs to captions. If there is no separate
- script, transcribe/derive narration first and let the audio's ASR timestamps define the
- beats (audio-first, like A-roll — not text-first like B-roll).
- 2. **Anchored keyframes.** `python3 scripts/croll_keyframes.py <project_dir>`
- Uploads the photo once and generates one anchored poster per shot via
- `google/nano-banana-2/edit` (fallback `openai/gpt-image-2/edit`). Portraits get a
- photographic face + illustrated paper-doll body; products get a pixel-faithful sticker
- with label typography intact. Prompt rules that are baked in (all three cost a re-run to
- learn): poses/expressions go to the BODY only — asking for a wink redraws the face;
- halftone must be scoped to the background or it bleeds onto skin; portrait clothing must
- be locked explicitly. The script also writes `anchor_freeze` into beats.json.
- 3. **Animate + audio + assemble.** Standard `clips.py` → `audio.py` → `assemble.py`.
- `clips.py` injects the `anchor_freeze` guard into every motion prompt — without it the
- video stage can re-letter a product label (observed: "PARFUM" → "PAREUM") or re-time a
- face. For narration in the subject's own voice, set `voice.clone_ref` (see Voice + music
- above); derive stamp/snap-zoom timing from the narration's ASR word timestamps
- (`asr_beats.py` works on any audio, not just A-roll footage).
- ## Host mode (a presenter speaks on camera)
- Use when the user wants a **digital presenter on screen** speaking some of the narration,
- from ONE still image of that presenter (not a recorded video: that is A-roll). Mark those
- beats with a shot `"kind": "host"`; every other beat stays normal B-roll. Full recipe,
- rules and limits: `references/host-mode.md` (read it before using this mode).
- 1. Add `host.avatar` (a finished character design, never redrawn) and, per host beat, one
- shot with `kind: "host"`, a world-only `scene` and an `element_motion` that names each
- element and pins its shape. The beat's narration must be at most 9.5 s.
- 2. `audio.py` first, then `python3 scripts/host_plates.py out/<project>`: **look at both
- plates** (flat green, face intact, empty region clear) before spending on video.
- 3. `python3 scripts/host_clips.py out/<project>` prints a cost estimate and stops; show it to
- the user, then re-run with `--yes`. It generates the presenter (Seedance) and the world
- (Omni) separately, adopts the presenter clip's own audio, and keys them together.
- 4. `clips.py` and `keyframes.py` skip host shots; `assemble.py` never stretches them.
- The user can place and size the presenter with `host.position` and `host.size`. 16:9 and
- 9:16 are supported. A host clip costs about twice a B-roll clip per second. Known issue:
- the world video can drift (see the reference); re-roll it if it does.
- ## beats.json schema
- ```json
- {
- "project": "my-film", "topic": "...", "language": "en",
- "aspect": "9:16", // 16:9 | 9:16 | 1:1 | 3:4
- "style": "collage",
- "provider": "atlas_cloud", // media backend — default; pluggable (scripts/provider.py)
- "theme": "american-retro", // THEME_PRESET (styles.THEME_PRESETS) — the LOOK layer
- "arc": "timeline", // narrative arc (beat-layer.md) — the STORY skeleton
- "video_model": "google/gemini-omni-flash/image-to-video", // Kling for real people
- "image_model": "google/nano-banana-2/text-to-image", // keyframes; or openai/gpt-image-2/text-to-image
- "image_resolution": "1k", // 1k (default) | 2k | 4k
- "video_resolution": "720p", // 720p (default); Seedance also 480p/1080p (Omni is 720p-only)
- "motion_style": "punchy", // amplitude: calm | punchy | max (theme sets a default)
- "constraints": "strict", // strict = defect guards on | loose = let AI explore + re-roll
- "voice": {"voice_id": "leo", "language": "en", "speed": 1.0}, // pick per topic/language — see references/voices.md
- // + optional "clone_ref": "path/to/sample.mp3" (clone that voice via seed-audio)
- // and "persona": "YouTube tutorial creator" (delivery style for cloned VO)
- "music": "epic cinematic orchestral, instrumental, no vocals",
- "mix": {"music": 0.6, "voice": 1.25}, // audio balance — optional; these are the defaults (BGM ducks under the VO)
- "caption_style": "white", // white (default: clean white subtitle) | paper (cream cut-out collage look)
- "captions": true, // false = no burned-in captions (deliver clean, subtitle in post)
- "watermark": "Made with Atlas Cloud",
- "host": {"avatar": "path/to/presenter.jpg", "position": "left", "size": 0.25}, // host mode only (references/host-mode.md)
- "mode": "croll", // C-roll only — plus the four fields below
- "anchor_photo": "path/to/photo.png", // C-roll: the still to anchor (person or product)
- "croll_subject": "portrait", // C-roll: portrait | product
- "subject_wardrobe": "a cream knitted sweater and charcoal trousers", // C-roll portrait: outfit lock
- "subject_desc": "the perfume bottle", // C-roll product: short noun phrase for the sticker
- "beats": [
- {
- "id": 1, "title_cn": "", "title_en": "BEFORE MONEY",
- "bg": "earthy clay tan", "feel": "ancient, humble", "hook": "surprising_stat",
- "narration": "For most of history, there was no money...",
- "shots": [
- // shot_size: EST_WIDE|WIDE|MEDIUM|CLOSE|DETAIL ; camera_move: static|push_in|
- // pull_out|pan|tilt|parallax (flat-safe only) — VARY per adjacent beat, static for payoff
- {"id": "a", "dur": 5, "title": true, "shot_size": "WIDE", "camera_move": "push_in",
- "scene": "...wide establishing collage...",
- "element_motion": "traders gesture, goat bobs, a paper bird flaps across the frame, coins scatter"},
- {"id": "b", "dur": 5, "title": false, "shot_size": "CLOSE", "camera_move": "parallax",
- "scene": "...close cut-in detail...",
- "element_motion": "the exchanged goods slide together, halftone pulses"}
- ]
- }
- ]
- }
- ```
- `theme`+`arc` set the two big layers; `element_motion` per shot is the energy (make it rich — see
- below). `motion`/`collage_style`/`era` are still read for back-compat.
- ## Model selection (always verify IDs live)
- Model IDs change — fetch the live list first: `GET https://api.atlascloud.ai/api/v1/models`
- (no auth; keep only `display_console: true`). Defaults that work today:
- | Job | Model | Note |
- |---|---|---|
- | Keyframe / collage poster | `google/nano-banana-2/text-to-image` | default; renders CN+EN text well; `image_resolution` 1k/2k/4k |
- | Keyframe (alternative) | `openai/gpt-image-2/text-to-image` | set via `image_model`; size+quality auto-mapped from aspect+resolution |
- | Cut out an element | `youchuan/v8.1/remove-background` | advanced path only |
- | Animate (non-real content) | `google/gemini-omni-flash/image-to-video` | keeps text stable, layered motion |
- | Animate (**real people / brands**) | `kwaivgi/kling-video-o3-pro/image-to-video` | Omni & Seedance BLOCK celebrities |
- | Narration | `xai/tts-v1` | clean, multilingual, `voice_id` |
- | Music | `minimax/music-2.6` | `is_instrumental: true` |
- See `references/models-and-gotchas.md` for the full model-choice reasoning and every
- API / ffmpeg gotcha (auth header, curl downloads, no-libass captions, content blocks, etc.).
- Read it before debugging any failure — most failures are already documented there.
- **Backends are pluggable.** Every API call goes through a **provider** (`scripts/provider.py`);
- Atlas Cloud is the default and only backend today. Set `"provider"` in beats.json to route to a
- different backend once one is added — the stage scripts don't change. `scripts/provider.py`'s
- `run_jobs()` also does the submit/poll with **auto-resubmit on a stalled or failed job**.
- ## Advanced: element-level motion collage
- The standard path animates the *whole* poster (great, automated, "living poster"). For the
- dramatic **pieces-fly-in-and-assemble** motion collage (à la cr7v2), or to animate **real
- people with full control and zero content filters**, cut each poster into independent
- elements and drive them with the local keyframe engine (no video model needed).
- Read `references/local-engine.md`. In short: `extract_elements.py` (crop + background-removal
- + residue/erase cleanup) → `motion.py` (Layer + keyframes, `fly_in`/`slap`/`drop`/`pop_settle`
- easings, procedural confetti/starburst, camera zoom+shake+whip, frame render). Pieces fly
- back to their **original positions** on a blurred-placeholder backdrop, so the assembled
- frame reconstructs the original poster.
- ## Editions
- - **Auto edition** (this skill): topic in, film out, all on Atlas.
- - **Manual prompt-pack**: if the user isn't on Atlas, just produce the beat map + the per-beat
- image prompts + the per-clip motion prompts + the narration script for them to paste into
- any generator. The creative engine (the prompts) is identical.
README.md · README · 146 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
- <p align="right"><b>English</b> · <a href="README.zh.md">简体中文</a></p>
- # 🎬 Vox Director
- **Turn one topic into a finished Vox-style paper-collage explainer / ad video — script, collage keyframes, motion, voice-over, music and captions, all automated.**
- An **agent skill** that runs end to end on the [Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_campaign=vox_director) API + local `ffmpeg`, usable by any coding agent (Claude Code, Codex, etc.). You give it a one-line topic; it gives you an `mp4`.
-   
- <div align="center">
- https://github.com/user-attachments/assets/ed08d230-7bcb-4b48-a17d-23c079208f9f
- <b>▶ "The evolution of Chinese civilization" · 30s</b>
- </div>
- <table>
- <tr>
- <td width="25%"><a href="https://github.com/user-attachments/assets/216cd62f-6314-456c-94cf-1090b8559a22"><img src="assets/thumbs/football.jpg" width="100%" alt="How football conquered the world"></a></td>
- <td width="25%"><a href="https://github.com/user-attachments/assets/561788b1-5615-4828-b3f8-b24ae5ad7bcd"><img src="assets/thumbs/mexican.jpg" width="100%" alt="Mexican street food"></a></td>
- <td width="25%"><a href="https://github.com/user-attachments/assets/f69f072f-f50a-41ba-9e66-7ed0aae4ddc0"><img src="assets/thumbs/money.jpg" width="100%" alt="A brief history of money"></a></td>
- <td width="25%"><a href="https://github.com/user-attachments/assets/b9ff526f-577f-4acb-aafe-a2519a9b7c1c"><img src="assets/thumbs/silicon-valley.jpg" width="100%" alt="A brief history of Silicon Valley"></a></td>
- </tr>
- <tr>
- <td align="center"><sub>Football history · 60s</sub></td>
- <td align="center"><sub>Mexican street food · 60s</sub></td>
- <td align="center"><sub>A brief history of money · 60s</sub></td>
- <td align="center"><sub>Silicon Valley history · 60s</sub></td>
- </tr>
- </table>
- <p align="center"><sub><em>▶ more films — click any thumbnail to play</em></sub></p>
- ---
- ## What it is
- The look is the modern editorial **paper-collage** popularized by Vox explainers: hand-cut paper cut-outs, torn edges, tape, halftone dots, newspaper clippings, bold flat color per beat, big cut-out headlines — brought to life with motion, a narrator, music and captions.
- ## How it works
- One topic flows through one script per stage, all driven by a single `beats.json` per project:
- ```
- topic
- │
- ├─ 1. beat map pick a narrative arc → write beats.json ◀── GATE 1: you approve the beat map
- ├─ 2. style bake-off render the same beat in 3–4 themes ◀── GATE 2: you pick the look by eye
- ├─ 3. keyframes one collage poster per beat (nano-banana-2)
- ├─ 4. motion animate each poster (gemini-omni-flash i2v)
- ├─ 5. voice + music one narrator (xai/tts) + BGM (minimax/music)
- ├─ 6. assemble ffmpeg: concat, duck music under VO, burn captions + watermark
- └─ final.mp4
- ```
- That flow is **B-roll** — a topic in, everything generated. Two more input modalities, plus a presenter mode, reuse the same engine:
- - **A-roll — you already have a talking-head video.** It is ASR-segmented into beats and re-styled into the collage look, keeping the real face, lip-sync and gestures frame-for-frame (`gemini-omni-flash/video-edit`, auto-retrying on `seedance-2.0/reference-to-video`).
- - **C-roll — you have one still photo** (a selfie, a product shot). The subject is cut out as a photographic sticker — never redrawn — and each beat's poster is generated around it (`nano-banana-2/edit`). The narration can be cloned into the subject's own voice.
- - **Host — one image of a presenter.** Selected beats cut to a digital presenter who speaks the narration, lip-synced, inside the collage world (16:9 and 9:16; position and size adjustable). The presenter and the world are generated as two plates and keyed together (`seedance-2.0/reference-to-video` + `gemini-omni-flash/image-to-video`).
- Two ideas make or break the result, and the skill is built around both:
- 1. **The look is born in the image step.** Each beat is a finished collage *poster*. All the collage DNA (torn paper, cut-outs, halftone, headline text) lives in that image — if the poster isn't a rich collage, nothing downstream saves it.
- 2. **The motion is added after.** By default an AI video model animates the whole poster (the "living poster" path). For dramatic *piece-by-piece* assembly, an optional local keyframe engine cuts the poster into parts and drives them frame-by-frame (no content filters, pixel-exact — great for real people).
- Two human decision gates keep you in control (approve the beat map; pick the style); everything else is automated.
- ## Models (verified on Atlas Cloud)
- | Job | Model |
- |---|---|
- | Keyframe / collage poster | `google/nano-banana-2/text-to-image` |
- | Animate (non-real content) | `google/gemini-omni-flash/image-to-video` |
- | Animate (**real people / brands**) | `kwaivgi/kling-video-o3-pro/image-to-video` |
- | Re-style a talking-head (A-roll) | `google/gemini-omni-flash/video-edit` |
- | Anchor a photo in the collage (C-roll) | `google/nano-banana-2/edit` |
- | Presenter on camera (Host) | `bytedance/seedance-2.0/reference-to-video` + `google/gemini-omni-flash/image-to-video` |
- | Narration | `xai/tts-v1` |
- | Narration in a real person's voice | `bytedance/seed-audio-1.0` (voice cloning) |
- | Music | `minimax/music-2.6` |
- | Cut out an element (advanced path) | `youchuan/v8.1/remove-background` |
- Model IDs drift — the skill fetches the live list from `GET https://api.atlascloud.ai/api/v1/models` before running.
- ## Install
- This is an **agent skill** — it works with any coding agent that can read a workflow and run scripts (Claude Code, Codex, …). Claude Code auto-discovers it as a skill; other agents read [`AGENTS.md`](AGENTS.md) → [`SKILL.md`](SKILL.md).
- **Option A — from this repo:**
- ```bash
- git clone https://github.com/Alisa0808/vox-director.git ~/.claude/skills/vox-director
- ```
- **Option B — from the packaged skill:** download [`vox-director.skill`](vox-director.skill) and install it via your Claude skills UI.
- Then set your Atlas Cloud API key (get one at [atlascloud.ai/console/api-keys](https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=vox_director)):
- ```bash
- export ATLASCLOUD_API_KEY="sk-..."
- ```
- ## Quick start
- Just ask your coding agent, with the skill installed:
- > *"Make me a Vox-style collage video introducing Mexican street food — English, 16:9, 15 seconds."*
- The agent will draft a beat map for your approval, run a style bake-off for you to pick from, then generate keyframes → motion → voice → music and assemble `out/<project>/final.mp4`.
- ## Requirements
- - A **coding agent** — Claude Code, Codex, or similar
- - **Atlas Cloud** API key
- - **ffmpeg** + **ffprobe** (`brew install ffmpeg`)
- - **Python 3** with **Pillow** (`pip install pillow`) — for caption/watermark overlays
- ## What's in the box
- ```
- SKILL.md the skill (English) — the workflow the agent follows
- SKILL.zh.md the same skill in Chinese
- AGENTS.md entry point for non-Claude agents (Codex, …)
- references/ the creative engine
- prompt-guide.md the LOOK layer — prompt structures, vocab & 9 theme presets
- beat-layer.md 14 narrative arcs + hook/pacing + shot patterns
- voices.md xai/tts voice roster — pick a voice_id per language/tone
- models-and-gotchas.md every API / ffmpeg gotcha, already solved
- local-engine.md the advanced element-level motion engine
- scripts/ one script per pipeline stage
- examples/ ready-to-run beats.json examples
- assets/ the showcase film
- ```
- ## Credits
- Built by **[@alisaqqt](https://x.com/alisaqqt)** — follow for more agent-skill experiments.
- Inspired by the collage-ad workflows of **[Stav Zilber](https://x.com/StavZilber)**, **[rom1trs](https://x.com/rom1trs)** and **[Higgsfield](https://x.com/higgsfield_ai)**, and by **[Vox](https://www.vox.com)**'s explainer visual language.
- Built end to end on **[Atlas Cloud](https://www.atlascloud.ai/?utm_source=github&utm_campaign=vox_director)** — one prompt, one film.
- ## License
- [MIT](LICENSE) © 2026 Alisa Qian
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.