Skip to content
Back to search

muapi-director

Turn ONE topic, talking-head video, or photo into a finished Vox-style paper-collage explainer / ad video on the MuAPI platform (api.muapi.ai) + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. 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).

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/anil-matcha--vox-ai-motion-graphics-generator/badge.svg)](/listings/anil-matcha--vox-ai-motion-graphics-generator)

HTML

<a href="/listings/anil-matcha--vox-ai-motion-graphics-generator"><img src="/api/listings/anil-matcha--vox-ai-motion-graphics-generator/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**1. Install local dependencies** - **ffmpeg** + **ffprobe** (`brew install ffmpeg` on macOS / `choco install ffmpeg` on Windows) - **Python 3** with **Pillow** (`pip install pillow`)

**2. Configure environment keys**

export MUAPI_API_KEY="your-api-key"     # image / video / voice / music models — key from muapi.ai
export OPENAI_API_KEY="your-openai-key"  # story planning & ASR

**3. Run Pipeline via Agent or CLI:**

Mode 1: B-roll (Topic → Film)

Ask your coding agent: > *"Make me a 15-second Vox-style collage video introducing the history of coffee."*

Or run CLI scripts manually:

python scripts/style_bakeoff.py out/my-topic american-retro,swiss-modern,punk-zine
python scripts/keyframes.py out/my-topic
python scripts/clips.py out/my-topic
python scripts/audio.py out/my-topic
python scripts/assemble.py out/my-topic

Mode 2: A-roll (Talking-Head Video → Collage)

python scripts/asr_beats.py out/my-aroll source_presentation.mp4
python scripts/aroll_clips.py out/my-aroll
python scripts/aroll_assemble.py out/my-aroll

Mode 3: C-roll (Single Photo / Product → Anchored Collage)

python scripts/croll_keyframes.py out/my-croll
python scripts/clips.py out/my-croll
python scripts/audio.py out/my-croll
python scripts/assemble.py out/my-croll

---

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 · 47 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. ---
  2. name: muapi-director
  3. description: >
  4. Turn ONE topic, talking-head video, or photo into a finished Vox-style paper-collage
  5. explainer / ad video on the MuAPI platform (api.muapi.ai) + local ffmpeg — script,
  6. collage keyframes, motion, voice-over, music, captions, all automated.
  7. Three input modalities: a topic (B-roll), a talking-head video (A-roll mode), or a single
  8. photo of a person/product anchored into the collage (C-roll mode).
  9. ---
  10. # MuAPI Director
  11. Turn a topic, talking-head video, or photo 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. Powered by **MuAPI** (`MUAPI_API_KEY`) + local **ffmpeg**.
  12. ## Input Modalities
  13. 1. **B-roll (topic → film):** Pass a topic (e.g. *"A brief history of Silicon Valley"*). It drafts a script, builds keyframe posters, animates them, synthesizes narration/BGM, and assembles the video.
  14. 2. **A-roll (talking-head video → collage):** Pass a presenter talking-head recording. It runs ASR, segments the transcript, and re-styles the video into paper-collage graphics while preserving facial features, lip-sync, and gestures frame-for-frame.
  15. 3. **C-roll (one photo → collage):** Pass a selfie or product shot. The subject is cut out as an unedited photographic sticker, anchored into generated collage posters per beat, and animated.
  16. ## Prerequisites
  17. - `MUAPI_API_KEY` set in your environment (get one from https://muapi.ai).
  18. - `ffmpeg` + `ffprobe` installed on system path.
  19. - Python 3 with `Pillow` (`pip install pillow`).
  20. ## Workflow Steps
  21. ### B-roll Mode (Topic)
  22. 1. Write `out/<project>/beats.json` containing topic, language, and beat map.
  23. 2. `python3 scripts/style_bakeoff.py out/<project>` (Pick theme from candidates).
  24. 3. `python3 scripts/keyframes.py out/<project>` (Generates collage posters).
  25. 4. `python3 scripts/clips.py out/<project>` (Animates posters into motion clips).
  26. 5. `python3 scripts/audio.py out/<project>` (Generates TTS narration and instrumental BGM).
  27. 6. `python3 scripts/assemble.py out/<project>` (Muxes audio, ducking, captions, watermark -> `final.mp4`).
  28. ### A-roll Mode (Talking Head)
  29. 1. `python3 scripts/asr_beats.py out/<project> <source.mp4>`
  30. 2. `python3 scripts/aroll_clips.py out/<project>`
  31. 3. `python3 scripts/aroll_assemble.py out/<project>`
  32. ### C-roll Mode (Photo Anchor)
  33. 1. Add `"mode": "croll"`, `"anchor_photo": "photo.png"`, `"croll_subject": "portrait"|"product"` to `beats.json`.
  34. 2. `python3 scripts/croll_keyframes.py out/<project>`
  35. 3. `python3 scripts/clips.py out/<project>`
  36. 4. `python3 scripts/audio.py out/<project>`
  37. 5. `python3 scripts/assemble.py out/<project>`
README.md · README · 258 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. <div align="center">
  2. <h1 align="center">Vox AI Motion Graphics Generator</h1>
  3. <h3 align="center">Turn any topic into a finished Vox-style paper-collage explainer video</h3>
  4. <p align="center">
  5. <img src="https://img.shields.io/badge/🐍Python-3.10+-00d9ff?style=for-the-badge&logo=python&logoColor=white&labelColor=1a1a2e">
  6. <img src="https://img.shields.io/badge/🎬ffmpeg-Powered-ff6b6b?style=for-the-badge&logo=ffmpeg&logoColor=white&labelColor=1a1a2e">
  7. <img src="https://img.shields.io/badge/License-MIT-4ecdc4?style=for-the-badge&logo=opensourceinitiative&logoColor=white&labelColor=1a1a2e">
  8. </p>
  9. <p align="center">
  10. <img src="https://img.shields.io/badge/Agent_Skill-Claude_Code_·_Codex-7c3aed?style=for-the-badge&logoColor=white&labelColor=1a1a2e">
  11. <img src="https://img.shields.io/badge/One_Key-Setup-FFC107?style=for-the-badge&logoColor=white&labelColor=1a1a2e">
  12. </p>
  13. </div>
  14. ---
  15. <p align="center">
  16. <a href="https://www.youtube.com/watch?v=chK_pnV1wqQ">
  17. <img src="https://i.ytimg.com/vi/chK_pnV1wqQ/maxresdefault.jpg" alt="Vox AI Motion Graphics Generator video" width="640">
  18. </a>
  19. </p>
  20. <p align="center">
  21. <a href="https://www.youtube.com/watch?v=chK_pnV1wqQ"><b>📺 Watch the Vox AI Motion Graphics Generator in action →</b></a>
  22. </p>
  23. ### 🚨 The problem with making explainer videos today:
  24. - ❌ **Fragmented workflow** — separate tools for scripting, image gen, animation, voice-over, music, and captions
  25. - ❌ **No narrative structure** — raw text-to-video models don't understand story arcs, hooks, or pacing
  26. - ❌ **Inconsistent look** — the collage aesthetic drifts from shot to shot
  27. - ❌ **Hours of manual editing** — stitching, ducking music, and burning captions by hand
  28. ### 💡 The solution:
  29. 🎬 **Screenwriter**, **Collage Artist**, **Animator**, and **Editor** — all in one automated pipeline.
  30. Type one topic. The agent writes the story beats, renders each beat as a torn-paper collage poster, animates it, adds a narrator voice-over, music, and burned-in captions — then stitches everything into a finished `final.mp4`. You stay in control with just **two approval gates**: the story beat map and the visual theme.
  31. ---
  32. <p align="center">
  33. <a href="https://github.com/Anil-matcha/awesome-generative-ai-apps">
  34. <img src="https://img.shields.io/badge/Part%20of-Awesome%20Generative%20AI%20Apps-FFD700?style=for-the-badge&logo=github&logoColor=black" alt="Awesome Generative AI Apps">
  35. </a>
  36. </p>
  37. > 🎨 **[Explore 50+ more open-source AI apps →](https://github.com/Anil-matcha/awesome-generative-ai-apps)**
  38. ## 🎥 Demo
  39. https://github.com/user-attachments/assets/3db826d1-3271-4e8a-b4d0-a843013e67c7
  40. > One topic in, a fully narrated & captioned Vox-style collage video out. ([download the demo](https://raw.githubusercontent.com/Anil-matcha/vox-ai-motion-graphics-generator/main/assets/demo.mp4))
  41. > *"Make me a 15-second Vox-style collage video on the history of coffee."* → a styled `final.mp4`, fully narrated and captioned.
  42. ### 📽️ Generated Showcase Videos (Playable Demo Videos)
  43. Below are end-to-end videos generated using the pipeline:
  44. <div align="center">
  45. https://github.com/user-attachments/assets/d9b3e85b-2f4a-4c64-9692-747f085dfd28
  46. <b>▶ "History of Coffee (Ethiopia 850 AD)" · 5s (B-roll Film)</b>
  47. <br/><br/>
  48. https://github.com/user-attachments/assets/6628b678-78ff-481a-bc39-d7098ec1f2fe
  49. <b>▶ "Cold Brew Product Ad" · 5s (C-roll Film)</b>
  50. </div>
  51. <br/>
  52. | Mode | Film Title | Topic / Subject | Playable Video Link | Keyframe Poster | Motion Model | Narration Voice |
  53. |---|---|---|---|---|---|---|
  54. | **B-roll** | **☕ History of Coffee** | *Ethiopia 850 AD* | [Play Video](https://github.com/user-attachments/assets/d9b3e85b-2f4a-4c64-9692-747f085dfd28) (`out/demo/final.mp4`) | `out/demo/keyframes/kf_1a.jpg` | `veo3.1-image-to-video` | MiniMax TTS (`Q19bea09caa6IRAeW7`) |
  55. | **C-roll** | **🍾 Cold Brew Product Ad** | *Artisanal Cold Brew Bottle* | [Play Video](https://github.com/user-attachments/assets/6628b678-78ff-481a-bc39-d7098ec1f2fe) (`out/demo-croll/final.mp4`) | `out/demo-croll/keyframes/kf_1.jpg` | `veo3.1-image-to-video` | MiniMax TTS (`Q19bea09caa6IRAeW7`) |
  56. > 🎬 **Generated Assets Summary:**
  57. > - ☕ **B-roll (History of Coffee):**
  58. > - 📹 **Video:** [Play Video](https://github.com/user-attachments/assets/d9b3e85b-2f4a-4c64-9692-747f085dfd28) (`out/demo/final.mp4`) \| 🖼️ **Poster:** `out/demo/keyframes/kf_1a.jpg` \| 📹 **Clip:** `out/demo/clips/clip_1a.mp4` \| 🎙️ **Voice:** `out/demo/audio/narr_1.mp3` \| 🎵 **BGM:** `out/demo/audio/bgm.mp3`
  59. > - 🍾 **C-roll (Cold Brew Product Anchor):**
  60. > - 📹 **Video:** [Play Video](https://github.com/user-attachments/assets/6628b678-78ff-481a-bc39-d7098ec1f2fe) (`out/demo-croll/final.mp4`) \| 📸 **Anchor Photo:** `out/demo-croll/anchor_photo.jpg` \| 🖼️ **Poster:** `out/demo-croll/keyframes/kf_1.jpg` \| 📹 **Clip:** `out/demo-croll/clips/clip_1.mp4` \| 🎙️ **Voice:** `out/demo-croll/audio/narr_1.mp3` \| 🎵 **BGM:** `out/demo-croll/audio/bgm.mp3`
  61. ---
  62. ## 📑 Table of Contents
  63. - [✨ Key Features](#-key-features)
  64. - [🎨 The Look](#-the-look)
  65. - [🔄 How It Works](#-how-it-works)
  66. - [🧩 Models](#-models)
  67. - [🚀 Quick Start](#-quick-start)
  68. - [🛠️ Project Structure](#️-project-structure)
  69. - [🔗 Related Projects](#-related-projects)
  70. ---
  71. ## ✨ Key Features
  72. - **3 Input Modalities (A-roll, B-roll, C-roll)**:
  73. - **B-roll (Topic → Film)** — a single one-line prompt produces a complete, captioned, narrated video
  74. - **A-roll (Talking-Head Video → Collage)** — segment a presenter video with ASR (`openai-whisper`) and re-style into paper-collage while keeping real face, gestures, and lip-sync
  75. - **C-roll (Single Photo / Product → Anchored Collage)** — cut out a selfie or product shot as a photographic sticker and build animated collage posters around it
  76. - **Authentic Vox collage aesthetic** — torn paper, cutouts, tape, halftone dots, newspaper clippings, bold flat color, big headlines
  77. - **Story-first** — picks a narrative arc (timeline, problem-agitate-solution, how-it-works…) and writes a hook-led beat map before generating anything
  78. - **Style bake-off** — renders the same beat in 3–4 themes so you pick the look before committing
  79. - **Living-poster motion** — animates each collage keyframe into dynamic motion with Google Veo 3.1
  80. - **Voice + music + captions** — narration (TTS or voice cloning), background music ducked under the voice, and burned-in captions, all automated
  81. - **Two human gates, everything else automated** — approve the beat map, pick the theme; the pipeline handles the rest
  82. - **Agent-native** — a self-contained skill any coding agent (Claude Code, Codex, Antigravity, …) can read and run
  83. - **One API key + ffmpeg** — no cluster of accounts to wire up
  84. ---
  85. ## 🎨 The Look
  86. The aesthetic is the modern editorial **paper-collage** popularized by Vox explainers and creators like Stav Zilber and rom1trs: hand-cut paper cutouts, torn edges, tape, halftone dots, newspaper clippings, bold flat colors per beat, and big cutout headlines — brought to life with dynamic motion, a narrator voice-over, music, and burned-in captions.
  87. The collage look is born in the **image** step (each beat is a finished collage *poster*), and the **motion** is added after — so the DNA of the style is locked in before anything moves.
  88. ---
  89. ## 🔄 How It Works
  90. A single topic, video, or photo flows through the pipeline driven by `beats.json` under `out/<project>/`:
  91. ```
  92. topic / video / photo
  93. │
  94. ├─ 1. Beat Map Pick a narrative arc → write beats.json ◀── GATE 1: approve the beat map
  95. ├─ 2. Style Bake-Off Render the same beat in 3–4 themes ◀── GATE 2: pick the look
  96. ├─ 3. Keyframes One collage poster per beat (nano-banana-2 / flux-dev)
  97. ├─ 4. Motion Animate each poster into a clip (veo3.1-image-to-video)
  98. ├─ 5. Voice & Music Narration (minimax-speech-2.6) + BGM (suno-create-music)
  99. ├─ 6. Assemble Stitch clips, duck music, burn captions (ffmpeg)
  100. └─ final.mp4
  101. ```
  102. ### 3 Modalities:
  103. - **B-roll (Topic → Film):** Topic in → script → keyframe posters → Veo 3.1 motion → TTS narration + Suno music → `final.mp4`.
  104. - **A-roll (Talking-Head → Collage):** Presenter video in → Whisper ASR beat segmentation → video-edit restyling → audio remuxing → `final.mp4`.
  105. - **C-roll (Photo / Product → Collage):** Product photo in → photographic sticker cutout → anchored collage posters → Veo 3.1 motion → cloned voice → `final.mp4`.
  106. ---
  107. ## 🧩 Models
  108. | Pipeline Job | Model Endpoint |
  109. | :--- | :--- |
  110. | **Keyframes / Collage Posters** | `nano-banana-2` / `flux-dev` |
  111. | **Motion / Animation** | `veo3.1-image-to-video` / `veo3.1-fast-image-to-video` / `runway-image-to-video` |
  112. | **Re-style Talking-Head (A-roll)** | `gemini-omni-video-edit` / `veo3.1-image-to-video` |
  113. | **Anchor Photo in Collage (C-roll)** | `nano-banana-2` / `flux-dev` |
  114. | **Narration (TTS)** | `minimax-speech-2.6-turbo` |
  115. | **Voice Cloning (C-roll)** | `minimax-voice-clone` |
  116. | **Background Music** | `suno-create-music` |
  117. | **Audio Transcription (A-roll ASR)** | `openai-whisper` |
  118. | **Background Removal** | `remove-background` |
  119. ---
  120. ## 🚀 Quick Start
  121. **1. Install local dependencies**
  122. - **ffmpeg** + **ffprobe** (`brew install ffmpeg` on macOS / `choco install ffmpeg` on Windows)
  123. - **Python 3** with **Pillow** (`pip install pillow`)
  124. **2. Configure environment keys**
  125. ```bash
  126. export MUAPI_API_KEY="your-api-key" # image / video / voice / music models — key from muapi.ai
  127. export OPENAI_API_KEY="your-openai-key" # story planning & ASR
  128. ```
  129. **3. Run Pipeline via Agent or CLI:**
  130. #### Mode 1: B-roll (Topic → Film)
  131. Ask your coding agent:
  132. > *"Make me a 15-second Vox-style collage video introducing the history of coffee."*
  133. Or run CLI scripts manually:
  134. ```bash
  135. python scripts/style_bakeoff.py out/my-topic american-retro,swiss-modern,punk-zine
  136. python scripts/keyframes.py out/my-topic
  137. python scripts/clips.py out/my-topic
  138. python scripts/audio.py out/my-topic
  139. python scripts/assemble.py out/my-topic
  140. ```
  141. #### Mode 2: A-roll (Talking-Head Video → Collage)
  142. ```bash
  143. python scripts/asr_beats.py out/my-aroll source_presentation.mp4
  144. python scripts/aroll_clips.py out/my-aroll
  145. python scripts/aroll_assemble.py out/my-aroll
  146. ```
  147. #### Mode 3: C-roll (Single Photo / Product → Anchored Collage)
  148. ```bash
  149. python scripts/croll_keyframes.py out/my-croll
  150. python scripts/clips.py out/my-croll
  151. python scripts/audio.py out/my-croll
  152. python scripts/assemble.py out/my-croll
  153. ```
  154. ---
  155. ## 🛠️ Project Structure
  156. ```
  157. .
  158. ├── SKILL.md # full agent workflow + approval gates
  159. ├── AGENTS.md # entry point for coding agents (Claude Code, Codex, Antigravity)
  160. ├── README.zh.md # Chinese documentation
  161. ├── scripts/ # one script per pipeline stage
  162. │ ├── muapi_client.py # MuAPI client wrapper
  163. │ ├── provider.py # task queue & status polling
  164. │ ├── style_bakeoff.py # multi-theme style candidates
  165. │ ├── keyframes.py # B-roll collage poster generator
  166. │ ├── clips.py # B-roll video animator (Veo 3.1)
  167. │ ├── audio.py # TTS narration & Suno music generator
  168. │ ├── text_overlay.py # subtitle captions & watermark generator
  169. │ ├── assemble.py # ffmpeg video assembly, ducking & composition
  170. │ ├── asr_beats.py # A-roll Whisper ASR beat cutter
  171. │ ├── aroll_clips.py # A-roll talking-head video restyler
  172. │ ├── aroll_assemble.py # A-roll clip & audio remuxer
  173. │ └── croll_keyframes.py # C-roll photo sticker anchor generator
  174. ├── references/ # prompt guide, beat/story library, voices
  175. └── examples/ # sample beats.json
  176. ```
  177. This is an **agent skill** — Claude Code auto-loads it from `SKILL.md`; Codex and other agents follow `SKILL.md` via `AGENTS.md`. Just ask for a *"vox video"* or a *"collage video."*
  178. ---
  179. ## 🔗 Related Projects
  180. - [MuAPI](https://muapi.ai) — Unified API for the image, video, speech, voice, and music models used by this pipeline.
  181. - [MuAPI video generation docs](https://muapi.ai/docs/video-generation) — API guidance for the image-to-video and text-to-video stages.
  182. - [MuAPI music and speech docs](https://muapi.ai/docs/music-and-speech) — API guidance for narration, voice cloning, and background-music generation.
  183. - [Open-AI-Micro-Drama-Generator](https://github.com/Anil-matcha/Open-AI-Micro-Drama-Generator) — agentic AI micro-drama video generator
  184. - [AI-B-roll](https://github.com/Anil-matcha/AI-B-roll) — auto-generate AI b-roll for your videos
  185. - [Text-To-Video-AI](https://github.com/SamurAIGPT/Text-To-Video-AI) — generate full videos from text
  186. - [AI-Youtube-Shorts-Generator](https://github.com/SamurAIGPT/AI-Youtube-Shorts-Generator) — auto-clip long videos into viral vertical shorts
  187. - [awesome-ai-video-models](https://github.com/Anil-matcha/awesome-ai-video-models) — compare AI video models by API, price & speed
  188. ---
  189. <div align="center">
  190. ⭐ **Star this repo if it helped you** — and [explore 50+ more open-source AI apps →](https://github.com/Anil-matcha/awesome-generative-ai-apps)
  191. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.