▶️ Watch the Short on YouTube · youtube.com/shorts/8ud3AaGKtP0

🐴➡️🦄 Google Flow Vectors

📺 YouTube upload page (title, description, thumbnails) →

A 48-second YouTube Short that explains how AI understands words as vectors — with a horse. Left: the output. Below: the input from Google Flow and how it was assembled.

🎬 Output

short_1080x1920.mp4 — 1080×1920, 24 fps, H.264/AAC, 49.5 s, 18 MB.

Six clips stitched, ElevenLabs voice-over (via fal.ai), animated word-by-word captions, a 2-second Skool end screen, and a crossfade from the end screen back to the first frame so it loops.

  • 1️⃣ Clips
  • 2️⃣ Voice-over
  • 3️⃣ Word timings
  • 4️⃣ Remotion compose
  • 5️⃣ Export

🚀 Join the community: Delivery Pilot on Skool

⬇️ Download the MP4 · 📦 Source on GitHub

📥 Input: the six Google Flow scenes

Each clip is 8 s, vertical 9:16, with its lower-third card already burned in. The voice line below each is the ElevenLabs take used in the export.

Scene 1 · The Hook

“How does an AI actually understand words? It doesn't read letters—it turns features into direction arrows on a giant map!”

Lower third: AI maps concepts as direction vectors.

Scene 2 · Base Vector Node (Horse)

“Think of this horse as a base vector. Every single concept sits at its own specific spot on the coordinate grid.”

Lower third: Base Vector Node: Horse

Scene 3 · Horse + Wings = Pegasus

“Add the “Wings” direction vector to the Horse... and the AI moves directly to the coordinate for Pegasus!”

Lower third: Horse + Wings = Pegasus

Scene 4 · Horse + Horn = Unicorn

“Add the “Horn” direction vector instead... and the coordinate shifts straight to Unicorn!”

Lower third: Horse + Horn = Unicorn

Scene 5 · Pegasus − Wings + Horn = Unicorn

“Which means... Pegasus, minus Wings, plus Horn, equals Unicorn! To an AI, concept logic is just basic geometry.”

Lower third: Pegasus - Wings + Horn = Unicorn

Scene 6 · Token 9246 & the Loop

“Token 9246 is hiding inside! But... how do these vectors talk to each other? How DOES an AI understand concepts?”

Lower third: Token 9246 | Seamless Loop

🧭 Input: how the idea evolved in Google Flow

  1. King − Man + Woman = Queen — hook “Tokens are just numbers”; the loop and the Token 9246 Easter egg were born here.
  2. Simplified for a 4-year-old — Kitty + Wings = Flying Kitty (Pip the Pixie-Bot, Toy Box Galaxy).
  3. Aged up — Horse + Wings = Pegasus, Horse + Horn = Unicorn, Pegasus − Wings + Horn = Unicorn.
  4. Format fixed — six 8-second vertical scenes with lower thirds = a 48 s YouTube Short.
  5. Clips + voice script — six clips generated; voice-over written in ElevenLabs format (Stability 35–45 %, Similarity 75–85 %, Style 15–20 %, Speaker Boost on).

Full written record: docs/input/google-flow-brief.md.

🥚 The Easter egg & the loop

Scene 6 zooms into the unicorn horn where Token 9246 ignites, then returns to the dark star-field of scene 1. The last question flows straight into the first line, so the Short loops.

🗺️ Workflow: Google Flow → Claude

You started in Google Flow (idea, storyboard, six clips, voice-over script) and moved to Claude Code to build, verify and publish. Source: docs/workflow.md.

1 · The whole journey

flowchart TD
  subgraph FLOW["Phase 1 · Google Flow"]
    A["Idea: how does AI understand words?"] --> B["King - Man + Woman = Queen"]
    B --> C["Simplify for a 4-year-old: Kitty + Wings"]
    C --> D["Age up: Horse + Wings = Pegasus, Horse + Horn = Unicorn"]
    D --> E["Storyboard images: 6 panels, 9:16, lower thirds"]
    E --> F["Script and ElevenLabs voice-over text"]
    F --> G["6 video clips, 8 s each"]
  end
  subgraph CLAUDE["Phase 2 · Claude Code with superpowers"]
    H["Hand-off: 6 clips, scene list, VO script"] --> I["Brainstorm: pick Remotion"]
    I --> J["Design doc"]
    J --> K["Implementation plan"]
    K --> L["Execute test-first, commit to main"]
  end
  subgraph SHIP["Phase 3 · Ship"]
    M["Export MP4"] --> N["GitHub Pages site"]
    N --> O["YouTube page: title, description, thumbnails, pinned comment"]
  end
  G -->|"download to Downloads"| H
  L --> M

2 · What the code does

flowchart TD
  CL["assets/clips: 6 Flow clips"] --> ING["npm run ingest"]
  SC["src/script.ts: scene lines"] --> TTS["npm run tts: fal.ai ElevenLabs"]
  TTS --> VO["assets/vo: scene1-6.mp3"]
  VO --> AL["npm run align: fal.ai Whisper"]
  SC --> AL
  AL --> CAP["assets/captions.json: word timings on script words"]
  ING --> RM["Remotion composition"]
  VO --> RM
  CAP --> RM
  LOGO["skool-logo.png"] --> RM
  RM --> MP4["out/short_1080x1920.mp4"]
  MP4 --> VER["verify-export: format, 49.5 s, under 25 MB, audible"]
  VER --> GIT["git commit and push to main"]
  GIT --> PG["GitHub Pages workflow: static.yml"]
  TH["scripts/thumbnails.mjs: fal.ai nano-banana-2"] --> YT["youtube.html"]
  PG --> YT

3 · Who did what

sequenceDiagram
  autonumber
  participant You
  participant Flow as Google Flow
  participant CC as Claude Code
  participant Fal as fal.ai
  participant GH as GitHub
  You->>Flow: Idea, then simplified, then Horse/Pegasus/Unicorn
  Flow-->>You: Storyboard, script, 6 clips
  You->>CC: 6 newest videos, scene list, VO script, fal key
  CC->>You: Approaches (Remotion chosen), design, plan
  CC->>Fal: ElevenLabs TTS per scene
  Fal-->>CC: Voice-over mp3 files
  CC->>Fal: Whisper for word timings
  Fal-->>CC: Timestamps mapped onto script words
  CC->>CC: Remotion render and verify-export
  You->>CC: Add CTA, move captions, thumbnails, pinned comment
  CC->>Fal: nano-banana-2 vertical thumbnails
  CC->>GH: Commit and push to main
  GH-->>You: Pages site and YouTube page

4 · The superpowers process

flowchart TD
  B["brainstorming: approaches A / B / C"] --> D["design doc"]
  D --> W["writing-plans"]
  W --> E["executing-plans"]
  E --> T["test-first per task"]
  T --> V["verification before completion"]
  V --> M["trunk-based commit to main"]

🛠️ How it was created

The whole video is code in this repo, so anyone can re-run it. Here is the path from idea to MP4:

  1. 🧠 Idea → storyboard (Google Flow). You started with “King − Man + Woman = Queen”, simplified it, and landed on Horse + Wings = Pegasus and Horse + Horn = Unicorn. Google Flow generated a six-panel storyboard, then six 8-second vertical clips with lower-third cards burned in. Those six MP4s are the input.
  2. 📥 Ingest. npm run ingest copies the six newest clips from Downloads into assets/clips/scene1…6.mp4 in story order.
  3. 🎙️ Voice-over (fal.ai → ElevenLabs). npm run tts sends each scene’s line to ElevenLabs through fal.ai (voice Adam, stability 0.4, similarity 0.8, style 0.15). Any line over 7.5 s is regenerated slightly faster so it never outruns its clip.
  4. ⏱️ Word timings (fal.ai Whisper). npm run align transcribes each voice file for word timestamps, then maps them onto your script’s own words, so “Pegasus” and “9246” are always spelled right.
  5. 🎞️ Compose (Remotion). A React project stacks six clips, the voice-over (clip audio ducked to 12 %), animated yellow word-highlight captions in the lower band above the burned-in cards, and a 2-second focused Skool end screen with a loop crossfade.
  6. 📤 Export + check. npm run build:video renders out/short_1080x1920.mp4; node scripts/verify-export.mjs confirms format, 49.5 s length, under 25 MB, and audible voice.
  7. 🚢 Ship. Trunk-based commits straight to main; GitHub Pages publishes this page, the clips and the final video.
npm install
cp .env.example .env     # add FAL_KEY
npm run build:video      # ingest → tts → align → render
npm run studio           # preview in Remotion Studio

Built test-first with the superpowers skills: design → plan → execution.