---
title: "Money Tips — a practical numbered side-hustle / money listicle short"
tier: hero
format: short-form-video
theme: money | side-hustle | listicle | personal-finance-education
persona: finance creator, side-hustle channel, productivity coach, brand social
duration: "1 topic → 45–90s vertical short in ~3–6 min"
budget_usd: "$0.40–$3.00 per short (4–6 scene images/clips + TTS + music + finishing)"
caps: ["gpt-image", "flux-dev", "mai-image-2.5", "ltx-q-i2v", "seedance-i2v", "inworld-tts", "music", "hyperframes-caption", "ffmpeg-burn-subtitles", "ffmpeg-concat", "ffmpeg-mux", "ffmpeg-export"]
skills: ["short-form-video"]
showcases: []
status: "playbook (2026-06-08) — ported from the Pixelle-Video format study; runs on existing Storyboard caps. Showcase render pending."
reliability: 3.7 # 5 − image gen .3 − i2v .6 − tts .2 − music .2; finishing chain deterministic; subtitles/export OPTIONAL; no E2E showcase yet
---

# Money Tips — a punchy numbered listicle in 90 seconds

Point this at a money or side-hustle topic — "5 ways to start earning on weekends", "3 budgeting habits that actually stick" — and it builds a **punchy numbered-tips short**: a bold claim hook, 3–5 numbered tips with big number cards, and a CTA. Confident, fast, lifestyle-driven. Runs entirely on Storyboard's existing Livepeer caps.

## What you'll get

> **A finished reel = vertical 9:16 + voiceover + looped music bed + 45–90s, every second covered by audio.** A silent tail, or one whose music cuts out partway, is a draft — not a deliverable. The numbered enforcement below is the *definition of done*; also see the `short-form-video` skill.

A 45–90s **vertical (9:16, 1080×1920)** listicle short: 4–6 punchy lifestyle / icon scenes with big number cards, a confident energetic narrator, an upbeat driving music bed that runs the full length, captions, and a finished MP4.

## The cap chain (the enforced recipe)

```
topic (money / side-hustle theme)
  → agent writes the listicle script + 4–6 scene beats (bold claim → numbered tips → CTA)
  → generate_project  aspect_ratio:"9:16"        # punchy lifestyle / icon visuals per tip
       image: gpt-image | flux-dev | mai-image-2.5   (mai-image-2.5 = readable branding text)
  → motion: animate EVERY scene, duration 8–12s   # ltx-q-i2v (resolution:"auto") or seedance-i2v
                                                   #   — fire in waves of ≤4–5 (see Watch-outs)
  → create_media action:"tts" model_override:"inworld-tts"   # confident energetic narrator
  → create_media action:"music"                  # "upbeat driving, motivational, modern, no vocals"
       lyrics_prompt:"[Instrumental]"             #   MANDATORY — else the bed is sung aloud
  → hyperframes-caption                           # BIG number cards ("1","2","3") + tip titles — the format's signature
  → OPTIONAL: ffmpeg-burn-subtitles               # spoken-word captions in post — skip on a first cut
  → ffmpeg-concat                                 # stitch the per-scene clips → base reel
  → create_media model_override:"ffmpeg-mux"  audio_fill:"loop"   # VO + looped ducked score over the FULL reel
  → OPTIONAL: create_media model_override:"ffmpeg-export"   # only if the mux output isn't already 1080×1920 9:16
  # audio_fill:"loop" repeats a short (15s) bed across the whole reel — without it the score cuts out
  #   and the last third runs silent (the silent-tail bug). NON-NEGOTIABLE.
```

## How the agent should run this (interaction contract)

1. **CONFIRM (one message, ≤1 question):** restate in 1 line ("5-tip 9:16 money short on <topic>, inworld VO + looped bed + number cards, ~$1–3, ~5–10 min") + real choices: 3 vs 5 tips · flux-dev (fast) vs gpt-image (cleanest) · stills-draft vs full animated reel. If the topic is clear, state assumptions and start.
2. **PREVIEW CHECKPOINT:** show the SCRIPT (numbered tips + the "not financial advice" CTA, $0) and then the still keyframes (~$0.20) BEFORE any i2v fires — vague tips and earnings-claim problems get fixed at the script gate, not after $2 of video.
3. **NARRATE:** per wave: "animating tips 1–4 (ltx-q-i2v, ~2–4 min each), job …"; poll `get_create_media` every 10–15s, ≤4–5 i2v in flight, post a 1-liner at least every 2 min.
4. **FAIL GRACEFULLY:** gpt-image 422/timeout → soften wording → flux-dev or nano-banana; `seedance-i2v` hang/"fetch failed" → retry once → `ltx-q-i2v` (`num_frames:241`, `resolution:"auto"`) → Ken-Burns still as last resort; music comes back sung → re-run with `lyrics_prompt:"[Instrumental]"`. 1-line WHAT/WHY/fallback each time; ≤2 retries per scene; a 4-tip reel beats no reel.
5. **DELIVER:** final MP4 + one honest line ("tips kept general/educational, NFA line baked into the CTA; number cards rendered in post — any in-image text was verified") + ONE next step ("add burned captions, or run the next topic").

## Script structure (beats)

1. **Bold claim hook (0–4s)** — the promise, stated with confidence. "Five ways to make your first $100 this weekend."
2. **Numbered tips (3–5 beats)** — one tip per scene, each opening with a huge number card. Keep each tip to one concrete, do-this-now action.
3. **CTA (last beat)** — "Save this, pick one, and start today. Follow for more."

## Pacing & aspect

- **Fast and energetic** — 8–12s per tip clip; the big number card snaps in on each cut. 9:16, 1080×1920. 5 tips × ~10s + a 4s hook/CTA ≈ 60–90s.
- Number cards are the format's signature — render them large and high-contrast via `hyperframes-caption`, NOT inside the AI image.
- Driving music runs the FULL reel, ducked under narration — that is what `audio_fill:"loop"` in the mux step guarantees.

## Watch-outs

- **Render in WAVES — never fire every clip at once (tested the hard way, 2026-06-08).** Animating a whole reel by firing all its scene i2v jobs simultaneously — ×N reels — overwhelmed the SDK `/inference` worker (BYOC video caps have capacity ~2 each behind a single dispatch worker); a ~30-clip burst crashed it and most renders failed. Cap in-flight **video** renders at **≤4–5**, animate **one reel at a time**, and poll each batch to *done* before firing the next. Images are cheaper (cap ~4) but still wave large sets.

- **Don't fabricate financial claims.** No "make $5,000/month guaranteed", no fake returns, no specific stock/crypto picks. Keep tips **general and educational**. Add a clear on-screen + spoken **"not financial advice"** line — bake it into the CTA caption.
- **Number cards go in post, not in the image.** AI text-in-image mangles digits and tip titles. Render clean visuals, then overlay numbers/titles with `hyperframes-caption`. Verify any text that does appear.
- **Stay honest and platform-safe.** Finance content gets demonetized or removed for unrealistic-earnings claims. Educational, general, caveated — every time.
- **The multi-link quality ceiling.** A vague tip ("budget better") wastes the slot; make each one specific and actionable. A flat narrator kills the energy — listen once before stitching.

## Cross-surface (MCP / CLI / Webapp)

- **MCP:** `generate_project` (`aspect_ratio:"9:16"`, lifestyle/icon scenes) → animate scenes (`create_media` action:"animate") → `create_media` action:"tts" (inworld-tts) + action:"music" (`lyrics_prompt:"[Instrumental]"`) → `hyperframes-caption` number cards → `ffmpeg-concat` → `create_media model_override:"ffmpeg-mux"` with `audio_fill:"loop"` → `ffmpeg-export`.
- **CLI:** `livepeer story "5 money tips: <theme>, punchy listicle, lifestyle visuals"` → TTS + music via `livepeer media create` → `livepeer media export --aspect 9:16 --caption numbers.json --subtitles captions.srt` (the export loops the bed over the full reel).
- **Webapp chat:** `make a 5-tip money short about <theme>` — the agent writes the numbered tips (with a not-financial-advice CTA) and offers number cards + finishing as follow-ups.