gooseworks-ai/goose-skills / skills/video/render-editorial-motion-podcast
render-editorial-motion-podcast
VerifiedAssemble 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.
render-editorial-motion-podcast
Assemble an editorial-motion podcast-clip ad from a config: a real clipped podcast audio line carries the whole narrative and every visual beat is timed to the sentence it describes, in ONE flat, strictly limited-palette editorial-illustration look pack ("a magazine spot-illustration that moves" — the style and palette are the caller's choice). The motion is not generative video but deterministic ffmpeg ken-burns on static keyframes, so it reads as a printed page that moves. This capability is that FREE, deterministic assembly — the ffmpeg motion, hard-concat, audio mux, caption burn, and PIL end card.
scripts/config.example.json is the worked example (the fictional Ironfern "The Trees With No Wind" demo, ~40.8s
1080×1920 9:16, 6 beats — its 2-tone Niemann look, cream/charcoal/sage palette and dome-tree
metaphor are that demo's picks, never defaults); scripts/PIPELINE.md maps every config block to its source step and
scripts/README.md documents the free assembly.
Choices
The creative calls are the caller's (the video-format recipe asks the user); this assembly never picks them. The demo's value is an example only:
- Illustration style — demo: bold flat 2-tone silhouettes, halftone (Niemann / Steinberg lineage).
- Palette — demo: cream #F4EBD9 + charcoal #1A1A1A + one sage #86987A accent.
- Central metaphor — demo: a tree grown in a windless dome vs. trees in a windswept grove.
- Tone / voice — demo: warm and reflective, the real podcast host (no generated voice).
Run
This is the FREE, deterministic assembly stage — it spends nothing on the motion layer.
The paid inputs are separate: the real podcast MP3 is clipped from source (free ffmpeg) with
its Whisper word timings, and one editorial-illustration keyframe per beat (chained ref images
so set/character geometry holds) comes from create-image-fal (Nano Banana). Given the
clipped audio + words.json + the per-beat keyframes + the real brand wordmark PNG,
render-editorial-motion-podcast renders each keyframe as a ken-burns segment, hard-concats
on the beat, muxes the real audio, burns the mid-sentence captions, and composites the PIL end
card → the master. Re-cuts reuse the existing audio / keyframes and spend nothing.
Contract (the free assembly)
- A spoken narration carries the whole spot — no generated SONG. Mux the provided
narration MP3 (
-map 0:v:0 -map 1:a:0) — a real clipped podcast line (preferred) OR an approved generated VO (create-vo-elevenlabs). Never a sung/generated track. (Clip-vs-generate is the recipe's STEP-0 intake decision — if no source episode is supplied, ASK the user.) - NO generative i2v — deterministic ffmpeg ken-burns only. Animate each static keyframe
with
zoompan(push-in / pull-back, 1.0→~1.06×, 24fps); Seedance/Kling are photoreal-trained and invent naturalistic middle states that collapse the flat limited-palette look look. Never-loop 1withzoompan d=N(it balloons the duration); feed a single image and clamp with-t+trim. - Hard cuts on the beat — no crossfades. Crossfades ghost two slightly drifted frames through each other; hard-concat each beat's segments and split long beats into micro-cuts (target 8–10 distinct visual moments). Each beat's visual STARTS within ~0.5s of its spoken line.
- Captions from Whisper word-timestamps, ON only mid-sentence. Burn
frosted-subtlecaptions while the speaker talks; leave silent/reflective beats and the end card uncaptioned. THREE mandatory rules (each bit us in prod — bake them in):- NON-OVERLAP — clamp every line to END before the next STARTS
(
end = min(last_word_end + ~0.15, next_start - 0.03)). Two boxes must never stack at the same spot; an end-tail bleeding into the next window is the #1 caption bug. - SAFE AREA — captions sit in the lower third, so the keyframe's subject must stay in the
upper ~75% (see the recipe's
look_pack.caption_safe_area). If a finished keyframe's subject intrudes into the caption band, deterministically shift the subject UP into the empty top space (PIL: paste up ~0.24H onto a canvas pre-filled with the exact paper color from a clean corner) — never let the box sit on the subject. - BURN ENGINE — prefer libass (
ass/subtitlesfilter), but checkffmpeg -filtersfirst: many builds (Homebrew) lack libass/drawtext. If absent, use the deterministic overlay fallback — render each line as a transparent PNG (frosted rounded box + white text, PIL) and composite via the ffmpegoverlayfilter with timedenable='between(t,st,en)'windows. Same look, no libass.
- NON-OVERLAP — clamp every line to END before the next STARTS
(
- End card via PIL from the real wordmark PNG — never AI-render brand text. The lockup is composited deterministically (stretched-gradient bg + feathered mascot crop + wordmark + tagline with a system font); a diffusion model garbles a wordmark (misspelled letters). The video runs a ~1.5s silent hold past the audio on the end card (fade first/last 0.3s).
- FFmpeg composite, deterministic, FREE. Ken-burns each keyframe, hard-concat, mux the real audio, burn the captions, hold on the end card → a 1080×1920 h264+aac master. No paid calls.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| 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: 194k | Updated | Claude CodeCodex | Verified | Install |