Skip to content

gooseworks-ai/goose-skills / skills/video/render-editorial-motion-podcast

render-editorial-motion-podcast

Verified

Assemble an editorial-motion podcast-clip ad from a config — a real clipped podcast MP3 carries the narrative while N flat limited-palette editorial-illustration keyframes (one look pack) are animated NOT by generative i2v but by DETERMINISTIC ffmpeg ken-burns (zoompan) + hard cuts (no crossfades, which expose geometric drift), each beat snapped to its spoken line, the real audio muxed, Whisper-driven captions burned only mid-sentence, and closed on a PIL brand end card — never AI-rendered text. This is the FREE deterministic assembly stage (ffmpeg ken-burns + hard concat + audio mux + captions + end card); the real audio is clipped from source and the keyframes come from create-image-fal. Use for the editorial-motion-podcast format.

FileKindSize
SKILL.mdskill md6.0 KB
scripts/PIPELINE.mdmarkdown6.6 KB
scripts/README.mdmarkdown4.7 KB
scripts/config.example.jsonconfig14.9 KB
skill.meta.jsonconfig225 B
tests/smoke-test.mdmarkdown1.1 KB

scripts/PIPELINE.md

View on GitHub
# Pipeline — editorial-motion-podcast

How `config.example.json` maps to the real production steps. This molecule ships a
**config + this map**, not a bundled runner: the worked example (the fictional Ironfern "The Trees With No Wind" demo) is
produced by hand-run bash + PIL scripts that are not shipped; the steps below are the
reproducible recipe, with the gotchas inline.

The steps run **in order** because each depends on the last: the clipped audio sets the
timeline, the timeline marks the beats, the style anchor locks the look pack, the anchor
seeds every keyframe, the keyframes drive the ffmpeg motion, and assembly muxes the real
audio + Whisper captions + PIL end card.

**Paid stages:** the Whisper calls and the Nano Banana keyframes (GooseWorks quotes the
price; the retired Seedance detour only added cost) — the motion + assembly + end card
layers are **free**.

## 1. Clip audio + transcribe  (config: `audio`)  [paid]

**Clip the real podcast to the payoff moment — it sets the timeline.** Find the moment in
the source transcript and `ffmpeg -ss/-to` the episode MP3 to `audio.clip_start_sec ..
clip_end_sec`, adding `afade=t=out` (`audio.fade_out`) so the trailing next sentence
doesn't bleed in:

```bash
ffmpeg -y -ss 412.0 -to 451.80 -i <source_mp3> \
  -af "afade=t=out:st=39.30:d=0.5" -c:a libmp3lame -b:a 192k \
  audio/podcast-clip-40s.mp3        # -> 39.84s clip ending cleanly on "against."
```

Then Whisper word timings via the **`caption-burn`** skill's `transcribe.py` (`fal-ai/whisper`,
paid, <30s — default to it; local whisper ran 40min+ CPU and was killed) →
`audio/words.json`. Mark every payoff word's time; each beat's visual must START within
~0.5s of its line (never ahead = spoils the reveal, never lag = redundant). There is
**no generated song and no VO** — the host's real recorded line is the narration.

## 2. Style anchor → Nano Banana  (config: `look_pack.style_ref`, `look_pack.anchor_keyframe`, `keyframe_engine`)  [PAID]

`create-image-fal` (nano-banana edit) from `look_pack.style_ref` (`moodboard/style-ref-01.png`)
→ the FIRST keyframe (`generated/style-anchor/anchor-dome-1.png`, the dome). This anchor is
the reference EVERY subsequent keyframe chains off (`--ref-image`), so set/character
geometry stays consistent. **Approve the anchor before fanning out** — it locks the whole
look pack (palette, line weight, halftone discipline, geometry).

## 3. Remaining keyframes → Nano Banana (chained refs!)  (config: `beats[].keyframe(s)`, `look_pack`, `keyframe_engine`)  [PAID]

Per beat, build the prompt as `look_pack.style_opener + beats[i].keyframe_prompt +
look_pack.negative_tail`, and call Nano Banana **passing the anchor (and any earlier
matching frame) as an additional `--ref-image`** — otherwise Nano Banana invents a new
set every time. One PNG per beat (or a small panel set for the decline arc). Full
set ≈ 26 rolls incl. re-rolls. Keep prompts **metaphor-forward, never clinical**
(blunt words for harm or death can trip FAL's `content_policy` filter; "settles / lies down
softly" gives the same visual and passes). Review ALL N before motion;
re-roll drift, leaked color, or a stray leaked label (add all-caps "ABSOLUTELY NO TEXT,
NO LETTERS, NO LABELS").

## 4. ffmpeg ken-burns motion + assembly → `build_v4.sh`  (config: `beats[].motion`, `motion_engine`)  [FREE]

A hand-run `build_v4.sh` (not shipped) renders each
keyframe as a ken-burns segment and hard-concats them. **NO generative i2v** — Seedance
hallucinated a photoreal drawing hand + morphed flat silhouettes into naturalistic shapes +
added stray cartoon elements; it's photoreal-trained and can't hold a flat limited-palette discipline (retired). The two
reusable helpers:

- `render_kb  <src> <out> <dur> [zoom_end=1.04]` — push-in: scale to 2×, crop, `zoompan
  z='min(zoom+step,zoom_end)' d=dur*fps`, `trim=duration=dur`, `-t dur`.
- `render_kb_out <src> <out> <dur> [zoom_start=1.08]` — pull-back: `zoompan` from
  `zoom_start` down to `1.0` (reflective held frames, e.g. the fallen-tree hold).

Long beats split into micro-cuts (target **8–10 distinct visual moments**; anything held
> 6s reads static even with active zoompan). **Hard-concat on the beat — NO
crossfades** (they ghost two slightly drifted frames). **Never `-loop 1` with `zoompan d=N`** —
d runs per input frame per loop, so a 3s target ballooned to 225s; feed a single
image, clamp with `-t` + `trim=duration`. Concat all beats → `edits/master-video-only.mp4`,
then mux the real clip letting the video run a ~1.5s silent hold past the audio:

```bash
ffmpeg -y -i edits/master-video-only.mp4 -i audio/podcast-clip-40s.mp3 \
  -c:v copy -c:a aac -b:a 192k -map 0:v:0 -map 1:a:0 edits/master.mp4
```

## 5. End card → `build_endcard.py`  (config: `end_card`)  [FREE]

A hand-run `build_endcard.py` (not shipped) composites the brand lockup via **PIL** from the REAL brand
wordmark PNG (`end_card.brand_asset`): stretch a 1px center column of the source →
1080×1920 + `GaussianBlur(80)` for the gradient bg; feathered radial-alpha ellipse crop of
the brand mascot pasted centered-upper; wordmark (Helvetica 160) + tagline (Helvetica 48)
drawn with `ImageDraw.text` → `generated/ironfern-endcard-9x16-final.png`. **Never AI-render
brand text** — Nano Banana misspells words it renders. Before building from
scratch, `find <brand> -name "*wordmark*"` — the brand team usually already made the right asset.

## 6. Captions + final  (config: `captions`)  [PAID]

Whisper (fal) on `edits/master.mp4` → `frosted-subtle` ASS via the **`burn-in-captions`**
skill → `edits/master-captioned.mp4` (the FINAL deliverable). Captions **ON only while the
speaker is mid-sentence** — leave silent/reflective beats and the end card uncaptioned so
they don't double up with the visual. This is real spoken VO, so Whisper works (sung audio
returns "🎵 Music Playing 🎵"). `ls templates/` before assuming a style exists — only
`frosted-subtle` + `karaoke-fill` were present.

```bash
python3 .claude/skills/burn-in-captions/scripts/caption.py \
  --video edits/master.mp4 --style frosted-subtle
cp edits/master.captions/master__frosted-subtle__ass.mp4 edits/master-captioned.mp4
```

## 7. Watch / QC  [free]

`/watch:watch edits/master-captioned.mp4 --fps 2` and Read every 4–5 frames across the
full duration — the ONLY honest loop (single frames miss timing drift, caption collisions,
black first-frame, band artifacts). Iterate on timing per findings.

---

Re-cuts (new beat windows, added micro-cuts, re-timed caption ranges, swapped end card)
reuse the existing clipped audio / keyframes / clips and spend nothing — only steps 1–3
(+ the two Whisper calls) spend.
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall