Communitygithub.com

Talking Head Recut – 圖像疊加剪輯

為現有的談話性/訪談/播客影片,加上經過設計、與逐字稿同步的圖像疊加卡片(動態標題、下方三分之一處資訊、數據區塊、引言、側邊面板、子母畫面),影片本身保持原樣播放。

Talking Head Recut – 圖像疊加剪輯 是什麼?

此技能專為處理現有談話性影片(如訪談、播客)而設計,能根據影片逐字稿的內容與時間點,自動生成一系列經過設計的圖像疊加卡片,例如動態標題、資訊圖表、引言和子母畫面等。影片本身的播放不受影響,疊加的卡片會精準地與說話內容同步。它主要透過 HyperFrames CLI 與本地 Whisper 模型運作,不需要任何第三方 API 金鑰,所有處理都在本地完成。這項技能非常適合用來「包裝」現有影片,為其加上專業的視覺元素,提升觀看體驗與資訊傳達效率,並且支援 16:9、9:16、4:5 等多種畫布比例。

相容平台~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/samyakiasonline-ctrl/hyperframe/tree/HEAD/.claude/skills/talking-head-recut

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

Plugin installs: Before setup or freshness commands, follow plugin execution rules when this skill is inside a HyperFrames plugin. Standalone installs keep the update instructions below.

First, keep this skill fresh — confirm with the user before running: npx hyperframes skills update talking-head-recut. A fast no-op when everything is current; otherwise it refreshes this skill plus the core domain skills it depends on before you rely on them.

Talking Head Recut

Talking Head Recut 會取用一個完整播放的本地影片,並在其上層疊一系列經過時間設定與設計的圖像卡片——包含標題、下方三分之一資訊、數據區塊、引言、側邊面板、子母畫面——這些卡片會與影片中的說話內容同步。AI 助手會設計卡片(決定時間點與內容),並直接在對話中撰寫每張卡片的 HTML,然後組合出一個單一的合成 HTML,並透過 hyperframes 將其渲染為 MP4 影片。這裡沒有固定的卡片類型列表,也沒有預先定義的卡片結構——疊加卡片的內容完全來自於逐字稿實際說了什麼。

主要入口是 /hyperframes。 此技能負責為現有的談話性影片加上設計好的圖像卡片(標題、下方三分之一資訊、數據區塊、引言、側邊面板、子母畫面)——而不是純粹的字幕(將說話內容以文字形式呈現)。原始影片不受影響地播放。 任何其他意圖——純字幕、獨立圖像、從頭建立影片——或者有任何不確定性 → 請先閱讀 /hyperframes:意圖層負責所有路徑的決定。

作為 embedded-captions 的圖像包裝同類技能。 字幕是在影片上加入_說話內容_的可讀文字;而此技能則是在播放的影片上加入設計過的圖像。純字幕 → 使用 embedded-captions。從頭建立影片 → 使用創作工作流程(product-launch-video / faceless-explainer / …)。

透過 /hyperframes 路由,意圖層只會確認輸入(要處理哪個影片)並宣告渲染策略的相關問題為延後詢問——畫面比例、版面配置、風格組和卡片數量會保留到第 7 步,屆時已探查的影片素材和逐字稿能為建議提供依據;意圖層的執行形狀問題並不適用。當存在 BRIEF.md 時,它會包含已確認的輸入和任何使用者備註——請優先閱讀它。

在工作目錄中可檢查的中間檔案:

  • metadata.json — 影片長度 / 寬度 / 高度 / fps
  • audio.mp3 — 擷取的音訊
  • transcript.json — 一個扁平的單字陣列 [{ text, start, end }, …](使用 Whisper 模型;沒有 segments 包裝,也沒有 words 包裝)
  • storyboard.json — 輕量級的卡片大綱(AI 助手的計畫)
  • public/cards/card-XX.html — 每張卡片一個 HTML 片段
  • public/index.html — 最終組合好的合成畫面
  • output.mp4 — 渲染完成的影片

CLI 指令解析

# hyperframes — 轉錄(本地 Whisper)+ 將組合好的 HTML 渲染為 MP4
npx hyperframes --help

此技能完全依賴 hyperframes CLI 以及系統的 ffmpeg / ffprobe。轉錄功能是透過 hyperframes transcribe 在本地執行 Whisper 模型——無需第三方服務、API 金鑰或任何速率限制的代理。

工作流程

1. 檢查環境

npx hyperframes doctor          # 檢查 ffmpeg、無頭瀏覽器、渲染依賴
# 確認捆綁的資源:
ls "<SKILL_DIR>/assets/fonts" "<SKILL_DIR>/assets/vendor/gsap.min.js"

必要項目:

  • ffmpeg / ffprobe(系統級)
  • <SKILL_DIR>/assets/fonts/*.woff2、<SKILL_DIR>/assets/vendor/gsap.min.js(捆綁在此技能內,會在第 9 步複製到工作目錄)

轉錄不需要任何金鑰——hyperframes transcribe 會在本地執行 Whisper 模型(第 4 步)。

在 macOS 上強烈建議為 hyperframes render 設定以下環境變數:

export PRODUCER_BROWSER_GPU_MODE=hardware

2. 建立工作目錄

所有成品都存放在 videos/<專案名稱>/ 目錄下——這與其他影片工作流程(product-launch-video / faceless-explainer / pr-to-video)的慣例相同。保持當前工作目錄在專案根目錄;以下所有步驟都會在此單一子目錄下建立檔案。

VIDEO_PATH="/absolute/path/input.mp4"
WORK_DIR="videos/$(basename "$VIDEO_PATH" | sed 's/\.[^.]*$//')"
mkdir -p "$WORK_DIR"

3. 擷取音訊與中繼資料

# 中繼資料 — 影片長度 / 寬度 / 高度 / fps
ffprobe -v error -select_streams v:0 \
  -show_entries stream=width,height,r_frame_rate \
  -show_entries format=duration -of json "$VIDEO_PATH" > "$WORK_DIR/metadata.json"
# 音訊
ffmpeg -y -i "$VIDEO_PATH" -vn -acodec libmp3lame -q:a 2 "$WORK_DIR/audio.mp3"

輸出:metadata.json(讀取 width/height/duration;fps 是 r_frame_rate 分數的計算結果,例如 30000/1001 → 29.97) + audio.mp3。

4. 轉錄

npx hyperframes transcribe "$WORK_DIR/audio.mp3" -d "$WORK_DIR" --json --model small.en

本地 Whisper 模型——無需 API 金鑰、無代理、無速率限制。會將單字層級的 transcript.json 寫入工作目錄(單字 text + start / end 時間戳)。讀取它以取得驅動第 6 步卡片時間設定的單字/句子時間點;如果需要段落層級的區塊,請根據標點符號或停頓自行將單字分組為句子。

限制在影片長度內。 Whisper 回傳的最後一個單字的 end 時間戳可能會稍微超過實際影片長度——請將每張卡片的 endSec 和 composition.durationSeconds 限制在 metadata.json 的影片長度內,否則渲染結果會在影片結束後顯示黑色的尾巴。

5. 修正轉錄稿

transcript.json 是一個扁平化的單字物件陣列——[{ "text": "...", "start": s, "end": s }, …](沒有 segments 陣列,也沒有 words 包裝;每個單字的鍵是 text)。請讀取它並修正明顯的語音辨識錯誤:

  • 同音異義詞、產品名稱、技術術語、標點符號
  • 就地編輯某個單字的 text;保留它的 start / end 時間戳
  • 沒有預先分組的 segments 陣列——當你需要段落層級的區塊來設定卡片時間時,請自行將單字分組為句子(在句末標點或停頓處分割)

6. 草擬輕量級分鏡腳本(在對話中進行)

無需使用 CLI。 讀取 transcript.json + metadata.json 並直接設計卡片。storyboard.json 是 AI 助手內部的規劃產物——沒有任何 CLI 指令會讀取它;它存在的目的是讓你能在撰寫每張卡片的 HTML 之前,清晰地思考時間點和內容。請保持以下範例的形狀一致,以便相同的大綱能驅動你在第 9 步創作的合成內容:

{
  "schemaVersion": 3,
  "composition": {
    "fps": 30,
    "width": 1080,
    "height": 1920,
    "durationSeconds": 121.2,
    "layout": "portrait",
    "themeId": "noir",
    "seed": 42
  },
  "videoTrack": {
    "sourcePath": "input-video.mp4",
    "startSec": 0,
    "endSec": 121.2,
    "bounds": { "x": 0, "y": 0, "width": 1080, "height": 1920 }
  },
  "subtitles": { "enabled": false },
  "cards": [
    {
      "id": "card-01",
      "intent": "以講者在深夜的焦慮提問作為鉤子",
      "startSec": 0.5,
      "endSec": 13.0,
      "accentIndex": 0,
      "zone": "fullscreen",
      "contentHints": {
        "kicker": "一個誠實的問題",
        "title": "晚上 11 點的靈魂拷問",
        "detail": "客戶 60 秒的語音留言:『如果人民幣升值,是否代表我的美元保單會虧損慘重?』"
      }
    }
  ]
}

必要的卡片欄位:

欄位類型用途
id字串在卡片 HTML 與 GSAP 選擇器中使用的穩定 ID
intent字串自然語言描述;提供給卡片合成使用
startSec / endSec數字以秒為單位的時間(endSec > startSec)
accentIndex0 | 1 | 2 | 3 | 4此卡片使用的主題強調色索引(共 5 種)
zone列舉(見下方)卡片在畫布上所處的區域
contentHints物件自由格式的袋子;AI 助手在此放置引導文/標題/詳細/數據/引言等內容
archetype (可選)字串你可附加的自由格式標籤,用以記住卡片的模式;若省略則為自由格式,此為預設
transition (可選)列舉:cut | fade | slide | wipe宣告式的卡片到卡片過渡效果

五種 zone 值:

zone解析後的邊界使用時機
fullscreen覆蓋整個畫布英雄時刻、大數字、口號
whiteboard-area內縮 40px 邊距(或垂直畫布高度的 45%)密集的數據 / 註解內容
lower-third底部 30% 區域在可見影片上進行註解
side-panel右側 42%(橫向)或底部 40%(垂直)一側放數據,另一側放影片
video-overlay全畫布,預期卡片為大部分透明在全版影片上的註解疊加

當你在第 9 步組合合成畫面時,請根據上表將每張卡片的 zone 解析為卡片主機包裝元素上的像素邊界。影片邊界在合成層級設定一次(videoTrack.bounds);若要讓影片看起來在「卡片之間移動」,請在第 9 步的合成 <script> 中針對 #video-wrap 撰寫 GSAP 動畫(請見第 9 步)。

沒有預設的卡片角色,也沒有預設的敘事弧線。 卡片應從影片實際內容中湧現——可能全是引言或全是數據,可能以數字開頭或以故事開頭。讓逐字稿來驅動節奏。

要多少張卡片?——根據影片長度與資訊密度自動推斷。 沒有固定的上限。根據影片長度選取一個基礎節奏,然後根據資訊密度進行調整。只有下限是固定的:最少 5 張卡片,這樣即使是短片也有其節奏。

第 1 步 — 根據影片長度設定基礎節奏(中等密度下自然的秒數/卡片):

影片長度基礎節奏(秒/每張卡片)理由
< 60 秒(短影片)6–8 秒觀看者在短格式中期待快速剪輯
60 秒 – 3 分鐘8–12 秒正常的社群媒體節奏
3 – 10 分鐘12–20 秒給予呼吸空間;每張卡片承載更多內容
10 – 30 分鐘20–35 秒長篇講座 / 訪談的節奏
> 30 分鐘30–60 秒章節式的、接近章節的氛圍

第 2 步 — 密度乘數(乘以基礎節奏):

逐字稿中的訊號乘數效果
高密度 — 許多數字、明確的主張、斷續的節奏、列表式的列舉,每隔 1–2 個句子就是一個新想法× 0.7剪輯更快,更多卡片
中等密度 — 混合了數據和敘事× 1.0基礎節奏
低密度 — 一個延伸的故事、重複的重新框架、緩慢反思的節奏、單一論點的展開× 1.5剪輯更慢,較少卡片

第 3 步 — 計算:

secPerCard = basePace × densityMultiplier
cardCount  = max(5, round(videoDurationSec / secPerCard))

範例(請注意——沒有上限限制;長影片自然會產生更多卡片):

  • 30 秒短片,單一重點(低密度) → 7 × 1.5 = 10.5 秒/卡片 → round(30/10.5)=3 → 下限為 5 張卡片
  • 60 秒反思獨白(低密度) → 10 × 1.5 = 15 秒/卡片 → 4 → 下限為 5 張卡片
  • 121 秒談話性影片,豐富數據(高密度) → 10 × 0.7 = 7 秒/卡片 → 17 張卡片
  • 5 分鐘訪談,混合密度 → 16 × 1.0 = 16 秒/卡片 → 19 張卡片
  • 10 分鐘深度解析,高密度 → 16 × 0.7 = 11 秒/卡片 → 55 張卡片
  • 30 分鐘講座,中等密度 → 28 × 1.0 = 28 秒/卡片 → 64 張卡片
  • 1 小時播客,低密度 → 45 × 1.5 = 67.5 秒/卡片 → 53 張卡片

當一張卡片持續時間超過 ~15 秒時,請規劃一個更豐富的卡片(數據區塊、多步驟呈現、數個子要點以交錯動畫展開)——靜態的一句話在 8 秒後就會變得無聊。對於許多卡片都超過 30 秒的長篇作品,請考慮將時間軸分割成子合成(每個章節一個 .html 檔案,使用 data-composition-src 掛載),讓每個檔案的 GSAP 時間軸保持可管理——請參閱 HyperFrames 的 timeline_track_too_dense 檢查警告。

contentHints 是一個自由格式的物件;其鍵和巢狀結構可以採用任何能捕捉數據的形式。AI 助手會決定每張卡片的形狀。

可選的結尾。 此技能沒有內建固定的品牌結尾。如果使用者想要一張結束卡片,請自行設計一張中性的卡片(標誌 + 一行標語,約 1.5-2 秒,淡入 -> 短暫停留 -> 淡出),將其附加到 cards[] 陣列中,並將 composition.durationSeconds 延長至其

…

[truncated for translation]

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

samyakiasonline-ctrl/hyperframe

Add captions or subtitles to an existing single-subject talking-head video without editing the footage. Use for plain verbatim captions, cinematic captions embedded behind the subject, VFX captions, “炸/特效/酷炫字幕,” or a named identity from the 35-style catalog. Route by visual identity, not by backend engine. The quiet `anchor` rail is the default; embed every word only when the user explicitly wants a fully cinematic treatment. The workflow runs locally end to end, including transcription and subject matting; split multi-shot footage before applying it.

samyakiasonline-ctrl/hyperframe

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

samyakiasonline-ctrl/hyperframe

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

samyakiasonline-ctrl/hyperframe

Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated motion-first unit, including an animated title. Route fresh creation through hyperframes before using this skill.

samyakiasonline-ctrl/hyperframe

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

samyakiasonline-ctrl/hyperframe

Use when audio already placed in a HyperFrames composition needs to be mixed: fade-in/fade-out, crossfade, track gain or volume, volume automation, ducking, a music bed that fights a voiceover (voiceover carve), effects on a track (EQ, compressor, limiter, gate, saturation, delay, reverb, chorus, phaser, bitcrush), automation envelopes drawn on a track's volume or any effect parameter, or one submix bus carrying a chain, a fader and an automation clock for several tracks at once (`<hf-audio-group>`). Don't use for sourcing or generating audio — finding BGM, SFX, or making a voiceover is `/media-use`. Don't use for clip timing or track layout, which is `/hyperframes-core`.

samyakiasonline-ctrl/hyperframe

Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, timeline, history, clean, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.

samyakiasonline-ctrl/hyperframe

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

samyakiasonline-ctrl/hyperframe

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

samyakiasonline-ctrl/hyperframe

Use when a HyperFrames composition needs a punch-in, punch-out, zoom, reframe, Ken Burns treatment, camera move, visual match/whip handoff, or other seek-safe 2D/3D keyframes; also for GSAP, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

samyakiasonline-ctrl/hyperframe

Search, install, and wire registry blocks and components into HyperFrames compositions. Use BEFORE hand-building any named visual — whenever a brief, a user, or a storyboard names a look, effect, treatment, or transition such as CRT scanlines, glitch, chromatic aberration, film grain, a shimmer sweep, a chart, a code or terminal window, a map, or a confetti burst — because roughly 400 hosted items already cover many of them and the search ranks all of them with nothing installed, no project, and no account. Also use when running hyperframes add or hyperframes catalog, installing one item or every block matching a tag, wiring an installed item into index.html, or working with hyperframes.json. Covers discovery, install locations, block sub-composition wiring, component snippet merging, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

samyakiasonline-ctrl/hyperframe

Mandatory entry point: read this first for any request to make, create, edit, animate, or render a video, animation, or motion graphic, including a promo, explainer, captioned clip, title card, overlay, slideshow or interactive deck, Remotion port, or any HyperFrames HTML composition. Also use it to inspect, diagnose, validate, preview, publish, or batch-render an existing HyperFrames project. Inputs may be a website URL, GitHub PR, Figma design or URL, text or brief, existing footage, or music. It resumes project state, captures intent when applicable, selects and installs the owning workflow, and routes domain capabilities. HyperFrames is the default output framework unless the user explicitly chooses another framework for the deliverable or asks only to record a browser session.

samyakiasonline-ctrl/hyperframe

Use when working with a person on a HyperFrames project in Studio: first, whether their message asks for a change at all (questions, loose ideas and "don't change anything" get an answer and a plan, not an edit); for a new film, the plan, storyboard and build order that the HyperFrames launch films follow; and how the timeline should be laid out so it reads well (one caption track, one element kind per track, every scene a sub-composition) and where captions and key content may sit (safe zones). Don't use for how to perform an individual edit (split, trim, retime, volume, copy, swap): that is `creator-editing-recipes.md` in `/hyperframes-core`.

samyakiasonline-ctrl/hyperframe

Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + ledger record (one verb, `resolve`); generate via TTS / music / image models when the catalog misses; produce voiceover, transcription, captions, and background removal through one shared audio engine; operate on media (cut / reframe / transform); and reuse assets across projects. Also use for vague feedback that real footage looks dark, flat, boring, should feel retro/camcorder/print/ASCII, needs privacy, or needs a media reveal.

samyakiasonline-ctrl/hyperframe

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.

samyakiasonline-ctrl/hyperframe

Turn a music track (an audio file, a video to pull audio from, or a track generated from a mood brief) into a beat-synced video — lyric video, slideshow, or kinetic promo. The music drives all pacing; any user-supplied images/videos are cut onto the same beat grid, and a complete video needs zero assets. Narrated pieces → the input-matched workflow (see /hyperframes). Unclear → /hyperframes.

samyakiasonline-ctrl/hyperframe

Turn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market, launch, promote, or reveal a product; the default for any commercial URL. Site tours / showcases of a website route here too — the brief carries the show-it-as-is intent. Unclear → /hyperframes.

samyakiasonline-ctrl/hyperframe

Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR topic explainer (/faceless-explainer). Unclear → /hyperframes.

samyakiasonline-ctrl/hyperframe

Port an existing Remotion (React) composition''s source to HyperFrames HTML. Use ONLY on an explicit ask to port/convert/migrate/translate a Remotion source — one-way, Remotion-only. A passing Remotion mention, reference-only code, or "make something like my Remotion video" is a fresh build (/general-video). Unclear → /hyperframes.

samyakiasonline-ctrl/hyperframe

Author a HyperFrames slideshow — a presentation, pitch deck, or interactive deck with discrete slides, fragment reveals, branching, hotspot navigation, and built-in presenter mode with speaker notes; also converts an existing page into a deck. Output is a navigable deck, not a rendered MP4. If the user didn't explicitly ask for a slideshow, confirm before authoring. Unclear → /hyperframes.

相關技能