Communitygithub.com

gooseworks-ai/goose-skills

為完成後的垂直影片添加三種風格的字幕,基於實際音訊逐字定時,支援分割畫面、固定位置,以及無語音格式的節拍式字幕。

goose-skills 是什麼?

此技能專為影片廣告的最後處理階段設計,能從最終版本的影片音訊中提取逐字時間戳,並生成精準對時的字幕。它支援三種主要風格:Plate(深灰圓角底板上的粗體白字,一次1–2個詞)、Outline(無底板,一次1–3個詞)、以及Serif-word(一次一個詞,Georgia Bold襯線字體,固定基線高度,模擬螢幕插入效果)。對於無語音的格式(如步行展示影片),plates.py 會根據節拍生成黑色區塊字幕,並自動放置在畫面中最空曠的水平帶上,支援多行文字合併為單一圓角輪廓。此外,還可選用紅色鉤卡(hook card)作為開場視覺鉤子,並透過 --highlight 參數將特定詞(如品牌關鍵字)標記為黃色。整個技能依賴 GooseWorks 代理服務(fal Whisper)進行轉錄,按使用量計費,並遵守最後一句話持續到最終幀的規則,確保呼籲行動始終可見。

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

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

caption-burn

根據完成影片中實際說出的內容產生字幕,而非依據劇本估算的時間。

執行

python transcribe.py --media reel.mp4 --out reel.words.json          # 付費,按分計費
python captions.py --video reel.mp4 --beats cutlist.aligned.json \
    --words reel.words.json --out final.mp4 [--style plate|outline] [--highlight Brand]

--beats 提供台詞 (vo)、其時間點,以及用於分割版面的 seam、size 和每個 beat 的 state。任何包含 beats: [{start, end, vo}] 格式的檔案皆可使用。

放置與樣式

  • --anchor seam(當 beats 包含 seam 時為預設值):在 split 的 beat 上,字幕底板固定於接縫處,由底板而非文字決定位置:底板的 25% 位於線條上方,75% 位於線條下方。全畫面的 beat 使用 --full-y。

  • --anchor fixed --y 0.62:每個字幕的底板中央位於該畫面高度的指定比例處。

  • plate(預設):白粗體字,置於深灰圓角底板上,1–2 個詞,上限約 0.019 畫面高度。

  • outline:白粗體字搭配深色外框,無底板,1–3 個詞,上限約 0.034 畫面高度。

  • --highlight WORD 將該詞標示為黃色(CTA 關鍵字)。可重複使用。

  • serif-word:一次一個詞,粗襯線字體(Georgia Bold),白色搭配黑色外框,固定基線於 0.77 畫面高度(螢幕插入效果)。高亮詞用引號標示。

  • --card "LINE ONE|LINE TWO" --card-until 4.7:在開場秒數內,於靠近頂部位置顯示一個白色圓角鉤卡,包含兩行粗體紅色大寫文字。每行約 14 個字元。

無語音格式的字幕 (plates.py)

python plates.py --video walk.mp4 --beats cutlist.json --out captioned.mp4 [--logo logo.png]

每個 beat 的 caption(一個字串或多行列表)在該 beat 的持續時間內顯示於一個黑色區塊上(先將方形矩形合併為聯集,再統一導圓角成為單一輪廓:如果逐行導圓角會留下接縫),文字靠左對齊,區塊以最寬的行為基準置中。除非該 beat 指定了 cap_y,否則區塊會放置於該畫面中最空曠的水平帶上。若 beat 設有 logo: true,則在區塊下方懸掛標誌圖塊。請撰寫人類會打的文字:將同一簡短「片段. 片段.」形式重複三次看起來像 AI 寫的。不要用重複的表情符號。

規則

  1. 轉錄完成後的音訊。 合併錄音片段並對齊台詞會改變時間點;只有最終影片的音訊能給出正確的提示。
  2. 最後一句字幕持續到最後一幀。 它就是行動呼籲。
  3. Whisper 以不同方式寫出的詞(例如 "200" 替代 "two hundred")會在其相鄰詞之間內插處理,而非捨棄或拉長至整行。
  4. 若無 --words 則時間點根據音節數估算。 可用於判斷放置位置,切勿用於正式交付。
  5. 字型: 在 macOS、Linux 或 Windows 上會尋找粗體無襯線字型;若找不到,則會從網路取得 Roboto Bold 一次,存放於 ~/.cache/gooseworks/fonts。可使用 --font 或環境變數 GW_CAPTION_FONT 覆蓋。

Individual skills in this repo

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

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

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.

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