Communitygithub.com

render-editorial-motion-podcast

以設定檔組裝一支編輯動畫風格的Podcast片段廣告——由真實的Podcast MP3剪輯敘事,搭配一組有限色調的編輯插畫關鍵影格,透過確定性的ffmpeg Ken Burns效果與無縫硬剪輯動態呈現,並嵌入Whisper字幕與結尾品牌卡。

render-editorial-motion-podcast 是什麼?

此技能提供一個完全免費且確定性的影片組裝流程,專為「編輯動畫Podcast」格式設計。它接收一個包含剪輯音訊、Whisper逐字時間戳、每拍關鍵影格以及品牌Logo PNG的設定檔,並執行以下步驟:使用ffmpeg的zoompan濾鏡對每張靜態關鍵影格進行Ken Burns推拉效果(無生成式影像轉影片),在語句節拍點上進行硬剪接(無淡入淡出以避免幾何偏移),混入真實Podcast音訊,並僅在句子中段嵌入Whisper驅動的字幕,最後以PIL合成的品牌結束卡收尾。此技能的最大價值在於其透明且無成本的組裝邏輯——所有視覺動態皆為確定性計算,不依賴任何付費生成API,因此重新剪輯時無需額外花費。它強制執行嚴格的技術合約:禁止生成式音樂或影像、禁止淡入淡出、字幕不得重疊且需避開主體區域、品牌文字不得使用AI生成。支援的平台為任何能執行ffmpeg與Python的環境。

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/gooseworks-ai/goose-skills/tree/HEAD/skills/ads/capabilities/render-editorial-motion-podcast

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

render-editorial-motion-podcast 是做什麼的?

根據設定檔組裝一支編輯動畫Podcast片段廣告:一段真實的Podcast剪輯音訊線承載整個敘事,每一個視覺節拍都精準對應其描述的句子,全部使用一組單一、嚴格限制色調的編輯插畫風格包(「一本會動的雜誌插圖」——風格與色調由呼叫方選擇)。動畫效果並非生成式影片,而是使用ffmpeg的確定性Ken Burns效果作用於靜態關鍵影格,使其讀起來像是一本會動的印刷頁面。此技能提供的是免費、確定性的組裝流程——包含ffmpeg動態、硬剪接、音訊混入、字幕燒錄以及PIL結束卡。

scripts/config.example.json 是一個實際範例(Klarify「老鼠公園」,約40.8秒,1080×1920 9:16,6個節拍——其雙色調Niemann風格、奶油色/炭灰色/鼠尾草色調以及老鼠公園隱喻皆為該示範的選擇,並非預設值);scripts/PIPELINE.md 將設定區塊對應至來源步驟,而 scripts/README.md 則紀錄了這個免費組裝流程。

選擇

創意決定皆由呼叫方負責(影片格式食譜會詢問使用者);此組裝流程絕不替他們選擇。示範僅作為一個範例:

  • 插畫風格 — 示範:大膽的平面雙色調剪影、網點(Niemann / Steinberg 風格)。
  • 色調 — 示範:奶油色 #F4EBD9 + 炭灰色 #1A1A1A + 一個鼠尾綠 #86987A 強調色。
  • 核心隱喻 — 示範:老鼠公園研究。
  • 語氣/聲音 — 示範:溫暖且反思性,真實的Podcast主持人(無生成聲音)。

執行

這是免費、確定性的組裝階段——它不會在動畫層上花費任何費用。付費輸入是分開的:真實的Podcast MP3從來源剪輯(免費ffmpeg)並搭配其Whisper逐字時間戳,以及每個節拍一張的編輯插畫關鍵影格(串聯參考影像以保持框架/角色幾何)來自 create-image-fal(Nano Banana)。給定剪輯音訊 + words.json + 每拍關鍵影格 + 真實品牌字標PNG,render-editorial-motion-podcast 將每個關鍵影格渲染為Ken Burns片段,在節拍點上硬剪接,混入真實音訊,燒錄句子中段字幕,並合成PIL結束卡 → 最終母帶。重新剪輯會重複使用現有音訊/關鍵影格,成本為 $0。

合約(免費組裝)

  • 口語敘述承載整個廣告——不得使用生成的歌曲。 混入提供的敘述MP3(-map 0:v:0 -map 1:a:0)——一條真實的Podcast剪輯片段(首選)或一個經核准的生成VO(create-vo-elevenlabs)。絕不允許歌曲/生成音軌。(剪輯 vs. 生成是食譜中STEP-0的初始決定——如果未提供來源集數,請詢問使用者。)
  • 不得使用生成式i2v——僅限確定性ffmpeg Ken Burns。 使用 zoompan 動畫化每個靜態關鍵影格(推近/拉遠,1.0→約1.06倍,24fps);Seedance/Kling 是基於真實照片訓練的,會創造出破壞平面限制色調風格的自然主義中間狀態。絕對不要使用 -loop 1 搭配 zoompan d=N(這會使時長暴增);餵入單張圖片並使用 -t + trim 來限制。
  • 在節拍點上硬剪接——不得使用淡入淡出。 淡入淡出會使兩個漂移的框架互相穿透;對每個節拍的片段進行硬剪接,並將長節拍拆分為微剪接(目標8–10個不同的視覺時刻)。每個節拍的視覺起點應在其對應語句的約0.5秒內開始。
  • 字幕來自Whisper逐字時間戳,僅在句子中段顯示。 當說話者說話時燒錄 frosted-subtle 字幕;在寂靜/反思性節拍以及結束卡上不留字幕。三個強制規則(每個都在正式環境中咬過我們——務必牢記):
    1. 不重疊 — 將每行字幕限制在下一個開始之前結束 (end = min(last_word_end + ~0.15, next_start - 0.03))。兩個字幕框絕不能在同一位置疊加;結尾殘影流入下一個時間窗是#1字幕錯誤。
    2. 安全區域 — 字幕位於下方三分之一處,因此關鍵影格的主體必須保持在約上方75%的區域(請參閱食譜的 look_pack.caption_safe_area)。如果完成的關鍵影格主體侵入字幕帶,則確定性地將主體向上移動到空白的上方空間(PIL:將主體向上貼約0.24H,貼到預先填充了來自乾淨角落之確切紙張顏色的畫布上)——絕不讓字幕框疊在主體上。
    3. 燒錄引擎 — 優先使用 libass(ass/subtitles 濾鏡),但先檢查 ffmpeg -filters:許多版本(如Homebrew)缺少 libass/drawtext。如果缺少,請使用確定性的疊加(overlay)備案——將每行字幕渲染為透明PNG(磨砂圓角框 + 白色文字,使用PIL),並透過ffmpeg的 overlay 濾鏡加上計時的 enable='between(t,st,en)' 時窗進行合成。相同的外觀,無需 libass。
  • 結束卡使用PIL從真實字標PNG合成——絕不使用AI渲染品牌文字。 標誌組合是確定性合成的(漸層背景 + 羽化吉祥物裁切 + 字標 + 使用系統字型的標語);擴散模型會弄亂字標(例如「therapits」)。影片會在結束卡上於音訊結束後停留約1.5秒的靜止畫面(在前/後0.3秒淡入淡出)。
  • FFmpeg合成,確定性,免費。 對每個關鍵影格進行Ken Burns、硬剪接、混入真實音訊、燒錄字幕、停留在結束卡上 → 一個1080×1920 h264+aac最終母帶。無需付費呼叫。

Individual skills in this repo

This repo contains 10 individual skills — each has its own dedicated page.

gooseworks-ai/goose-skills

Burned-in captions for a finished vertical video, three kinds. transcribe.py gets word timings from the video's own audio through the GooseWorks proxy (fal Whisper, bills the Ads agent, cents); captions.py burns one to three words at a time with Pillow + ffmpeg (no libass needed), either pinned to a split-screen seam (plate 25% above / 75% below) or at a fixed height, in a plate, outline or one-word serif style, with an optional red hook card; plates.py burns per-beat caption blocks (black, one union silhouette, placed in the emptiest band) for formats with no voice. The last caption (the CTA) holds to the final frame. Use as the last step of any video ad.

gooseworks-ai/goose-skills

Assemble a cartoon / animated / hand-crafted music-video ad from a config — a sung song carries the whole narrative while N per-bar i2v clips (one recurring animated character, one look pack) are each cut to their BAR window from librosa beat-tracking and hard-concatenated on the bar, VEED-whisper white bold-sans captions in the BOTTOM third (Alignment 2, above the logo bug, no pill) burned from the song's word timings re-spelled against the locked lyrics, a persistent brand logo bug held over the body (suppressed on the end card), and closed on a solid-brand-color PIL end card with the song still playing under it — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-bar + hard concat + logo bug + captions + end card + song mux); the song, character, keyframes, and clips come from create-music-elevenlabs / create-image-fal / create-video-fal. Use for the cartoon-music-video format.

gooseworks-ai/goose-skills

Assemble a cinematic live-action-style music-video ad from a config — an original sung anthem carries the whole narrative while N 35mm-film-look i2v clips are each cut to their lyric window and hard-concatenated on the beat as a 3-act arc, the anthem muxed at loudnorm I=-14, cinematic lower-third serif captions built from the song's OWN word timings (never Whisper) with the hook line landing on the chorus drop, and closed on a brand end card composited from the real asset — never AI-rendered text. This is the FREE deterministic assembly stage (cut-to-window + hard concat + anthem mux + captions + end card); the anthem, keyframes, and clips come from create-music-elevenlabs / create-image-gpt-image-fal / create-video-fal. Use for the cinematic-music-video format.

gooseworks-ai/goose-skills

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

gooseworks-ai/goose-skills

Generate a single 4-15s vertical video clip with ByteDance Seedance 2.0 reference-to-video via fal.ai. Multi-image reference (avatar + product + setting), native lip-synced VO + ambient audio (generate-audio on by default), internal multi-cut handling within one render. Routes through the GooseWorks FAL proxy (bills the Ads agent). The default clip atom for AI-creator UGC ads built on the NB2 + Seedance architecture. Validated on beauty-by-earth/video-01.

gooseworks-ai/goose-skills

Mandatory pre-publish review gate for a UGC video render. Transcribes the finished render's AUDIO with Whisper and word-diffs it against the approved spoken script, then gates set_final_render — blocking a render whose generated audio mis-voices a word (e.g. the approved "human-vetted" spoken as "human witted"), drops an approved phrase, or comes back silent. Runnable, gating counterpart to content-goose's review-transcript-integrity atom. Every ugc-video-formats recipe runs this after render and BEFORE set_final_render.

gooseworks-ai/goose-skills

Render pixel-accurate Apple Notes (iPhone, light mode) screenshot mockups from a JSON note spec. Outputs HTML + PNG at the iPhone 16/15 Pro native 1180×2556. Supports paragraphs, images, checklists, dividers, autocorrect underline, smart quotes, and an optional iOS keyboard chrome overlay used by the parent video-ad molecule.

gooseworks-ai/goose-skills

Extract competitor and customer intelligence from any company's landing page HTML. Discovers tech stack, analytics tools, ad pixels, customer logos, SEO metadata, CTAs, hidden elements, and more. No API keys required.

gooseworks-ai/goose-skills

Find speakers, hosts, and guest profiles at conferences and events on Luma. Two modes - free direct scrape for hosts, or Apify-powered search for full guest profiles with LinkedIn/Twitter/bio.

gooseworks-ai/goose-skills

Find Twitter/X influencers to promote a product or brand. Use when asked to find influencers, discover Twitter accounts for partnerships, identify creators in a niche, or build an influencer outreach list.

相關技能