Communitygithub.com

freudianflips/breakout-launch-videos

製作發佈影片的配音工具手冊(配音選角、一行一檔案、對白調整、拼接、強制對齊、復古風格、本地克隆以及免費草稿配音)。為發佈影片產生旁白,跨 Higgsfield 所有預設聲線進行選角,每句台詞獨立成檔並符合畫面、節奏與長度規則,透過強制對齊取得單字層級時間戳,確保每個關鍵字與視覺同步,並修復超長台詞。在 launch-story 劇本獲准後、picture timing 鎖定前使用,適用於「旁白」、「敘述者」、「選聲」、「錄製台詞」、「對齊單字」、「草稿配音」。

breakout-launch-videos 是什麼?

此技能提供一套完整的發佈影片配音工作流程,從選角、台詞錄製、長度調整、強制對齊到最終拼接,確保每個關鍵字精準落在對應的畫面上。它支援多種語音提供者,包括預設的 Higgsfield(約 100 種預設聲線)、免費的 macOS say 或 Linux espeak-ng 草稿配音,以及基於 Chatterbox 的本地聲線克隆。技能透過強制對齊(使用 torch 或 whisper.cpp)為每句台詞產生單字層級時間戳,讓影片中的視覺提示能跟隨語音。工作流程分為固定模板與自由格式兩種,皆包含選角、台詞調整(目標每分鐘 2.2–2.7 字)、時間對齊與拼接等步驟。它還包含復古敘述者效果(限制頻寬、加入磁帶飽和與唱片炒豆聲),以及當語音提供者無法使用時的備援策略。此技能適用於 Claude Code、Cursor 等 AI 代理開發工具,協助開發者與創作者高效產出高品質的發佈影片旁白。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/freudianflips/breakout-launch-videos/tree/HEAD/skills/launch-voice

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

發佈配音

屬於 launch-film 的工具手冊。請從 skills/launch-film/SKILL.md 開始:其中包含核心、鉤子加主體模板以及經驗教訓。若此頁面與其不同,以 launch-film 為準。

在現代發佈影片中,語音引導視覺,畫面逐字說明:當語音說「標記」時,某個東西就被標記。這只有在每個單字都有時間戳時才有效。

提供者

  • 預設:您自己的 Higgsfield 帳戶。 text2speech_v2(引擎 elevenlabs、minimax、seed_speech 及其他按聲線區分)用於選角,涵蓋約 100 種預設聲線,每行約 0.3 積分。Seed Audio 用於可由提示和音訊參考引導的敘述者。scripts/hf_voice.py 封裝了 CLI。
  • 免費草稿配音: scripts/scratch_voice.py 使用 macOS say(或 Linux 上的 espeak-ng)製作佔位音軌。用它來建立和調整整部影片的時間,將每次審查標記為「草稿配音」,然後再替換為真實音軌。
  • 免費本地克隆: scripts/clone_local.py(Chatterbox,MIT)從 8 到 10 秒的台詞中克隆您已批准的敘述者。這是一個替代品,而非最終成品。僅克隆您擁有權利的聲音。
  • 在完整的影片中審查配音,而不是作為零散的片段。保留一份被拒絕聲線的清單,以免再次被提出。

選角

  1. python3 skills/launch-voice/scripts/hf_voice.py cast "<the film's opening line>" film/vo/audition 使用每種預設聲線(約 110 種聲線耗費約 34 積分)朗讀該行,並使用 whisper 檢查每個錄音,測量節奏和音高變化。ranking.md 首先列出精準的錄音,最接近每秒 2.5 個單字和約 2 個半音的變化(對話式,非宣告式)。--only Name,Name 可重新選角少數幾個。
  2. 將排名前 6 左右的聲線(跨性別)應用於完整劇本(hf_voice.py lines),然後進行調整(見下文)。如果需要加速超過 12% 才能適應的聲線對該劇本來說太慢:放棄它或刪減單字。
  3. 為每個倖存的聲線建立完整的影片,讓擁有人挑選。在測試中,ElevenLabs 在節奏和音高上的變化最小,因此它是預設引擎。

長度與節奏

  • 目標為每秒 2.2 到 2.7 個口語單字。一個強力的參考發佈影片節奏為 2.4(63 秒內 151 個單字)。
  • 20 秒的影片約承載 45 個單字;30 秒約 70 個;60 秒約 140 個。在加速語音之前,先刪減單字。
  • 每個故事板畫面對應一行台詞,6 到 20 個單字,措辭應使關鍵名詞或動詞落在節拍上。

影片模板流程

  1. 劇本位於 film/film.json 的 lines 中。將每行台詞錄製為一個檔案,置於 film/vo/body/line-<id>.wav:使用 hf_voice.py lines 錄製真實音軌(將台詞寫為 {"lines": [{"line": "02", "text": "..."}]}),或使用 python3 skills/launch-voice/scripts/scratch_voice.py film/film.json 錄製草稿音軌(加上 --hook film/hooks/<name> 也可為鉤子行配音)。
  2. 執行 python3 skills/launch-voice/scripts/prep_lines.py film/film.json(使用 --align force 強制進行強制對齊;若已安裝 uv,首次執行時會下載 torch,約 2 GB)。它會寫入 film/vo/body/lines.json,包含每行台詞的時長和單字時間:當 torch 可用時使用強制對齊,否則使用 whisper.cpp,再否則使用標記為 estimate 的均勻估計。
  3. film/build.py 將台詞放置在影片時間軸上,每個畫面提示跟隨其對應的單字。新的錄音只需一次 prep 執行和一次重建。

自由格式影片流程

  1. vo/script-lines.json({"lines": [{"line": "01", "text": "..."}]}),然後每行一個檔案:hf_voice.py lines vo/script-lines.json vo/takes/<voice> --voice <Name>。文字、聲線、引擎和工作 ID 會記錄在 lines.json 中。
  2. 調整:python3 skills/launch-voice/scripts/fit_lines.py vo/placement.plan.json vo/takes/<voice> vo/versions/<voice>。該計劃為每行台詞提供其最早開始時間、呼吸間隙,以及當畫面必須結束時的 end_by。行內超過 0.25 秒的停頓縮短為 0.22 秒;仍然超出的連續行會作為一個整體加速,上限為 12%。然後拼接:python3 skills/launch-voice/scripts/stitch.py vo/versions/<voice>/placement.json vo/versions/<voice> vo/versions/<voice>/vo.wav。
  3. 每行台詞的單字時間。對於任何視覺效果必須對齊的內容,請使用強制對齊:uv run -q --with torch --with torchaudio --with soundfile python skills/launch-voice/scripts/force_align.py line.wav "the exact words"。對於快速讀取,align_lines.py 會逐行執行 whisper.cpp。錨點按說話順序解析(每個都是前一個之後的第一個匹配項),因此任何聲線都會重新定時影片。對整部影片執行單次 whisper 遍歷會在行尾附近產生漂移;逐行遍歷則不會。
  4. 將單字時間交給 launch-motion(將每個建置錨定到其單字)和 launch-sound(事件跟隨單字)。

復古敘述者

對於檔案或紀錄片風格的開場:python3 skills/launch-voice/scripts/vintage.py IN.wav OUT.wav --crackle crackle.wav 將頻寬限制在 150 Hz 到 5.8 kHz,加入磁帶飽和、緩慢的顫動和真實的唱片炒豆聲基底(使用 Seed Audio 生成一個)。Seed Audio 也可以直接用復古敘述者的聲音朗讀台詞(「一個溫暖、低沉的老式唱片上的 1960 年代紀錄片敘述者……正是這些詞:……」);它讀得慢且可能重新措辭(例如 "gotta" 變成了 "got to"),因此請用 whisper 檢查。

同步規則

  • 關鍵單字與其視覺效果的偏差應在 2 幀以內。從單字的第一幀開始建置;如果您讓視覺效果領先於其單字,請將其保持在 4 幀以下,並在每個地方都這樣做。
  • 在場景切換處讓語音喘息:行與行之間留 0.25 到 0.5 秒。
  • 最後一行至少比標誌結束早 1 秒結束;標誌有自己的近乎靜音(launch-mix 淡出)。

當語音提供者不可用時

根據草稿配音進行建置,將每次審查標記為草稿,並保持畫面錨定到對齊的單字,這樣替換為真實配音只需要一次 prep 執行和一次渲染。未經擁有者同意,切勿切換語音提供者或帳戶。

修復

  • 一行台詞超長不到 5%:ffmpeg -af atempo=1.04。超過此限制:重寫該行。
  • 單字發音錯誤:在該行的 say 欄位中進行語音拼寫(用於 hf_voice.py),切勿在劇本中進行。
  • Whisper 誤聽軟結尾:使用強制對齊或縮短錨點前綴;不要重新錄製。
  • 數字:在您用來對齊的文字中拼寫出來(「二十四」,而不是「24」)。
  • Whisper 基礎模型會誤聽產品名稱。使用小型模型或更大模型(WHISPER_MODEL)檢查最終單字。

Individual skills in this repo

This repo contains 9 individual skills — each has its own dedicated page.

freudianflips/breakout-launch-videos

Build the brand kit a launch film uses from a website. Runs tools/brand-from-url.mjs on the reader's site to extract branding (colours, fonts, logo, name, tagline, copy, product images), then reviews the preview sheet with the reader and fixes any wrong role by hand. Use for "brand from website", "brand kit", "extract branding", "get our colours and fonts", "use our logo", or before the first launch film for a new brand.

freudianflips/breakout-launch-videos

Make or change a product launch film in your own brand. A film is a hook (the story before the cut) on a shared body (the name punching in, hero words cut on the voice, your product at close range, the logo lockup in near silence), built in HyperFrames from brand/brand.json and film/film.json. Holds the core, the template workflow (build, render and mix 1 hook or all of them), the generation recipes, the checks and the lessons. Use for "launch video", "launch film", "product video", "promo", "reveal", "announcement video", "new hook", "change the body", "render all launch videos".

freudianflips/breakout-launch-videos

Tool manual under launch-film (mixdown.py for buses, ducking, loudness and the brickwall). Mix and master the audio of a launch film. Music, SFX and voice-over on separate buses, the bed ducked by the voice's real envelope with a presence carve, the music dropped out for the logo, glue compression, a true-peak-safe limiter, -14 LUFS and -1 dBTP, then laid onto the rendered picture. Use after the score, the sound effects and the voice exist, for "mix", "master", "loudness", "LUFS", "ducking", "mux the audio".

freudianflips/breakout-launch-videos

Tool manual under launch-film (the motion language for launch films built in HyperFrames). Ease tokens, camera doctrine, continuity at every cut, type and cursor craft, and brand-neutral signature moves (logo build, world pass, branch and pulse, waterfall fill, identity morph, macro pull-back, rise) that replace HyperFrames' stock look. Says which HyperFrames blueprints and transitions to keep, transform or avoid. Use whenever a launch film's picture is designed or animated, for "animation", "motion design", "transitions", "camera move", "make it feel like Apple", "less template".

freudianflips/breakout-launch-videos

Tool manual under launch-film (measuring a render and studying a reference film). Review a rendered launch film like a demanding creative director, then drive the v1 to v2 loop. Measures rhythm, static runs, cuts against the beat grid, loudness, true peak and voice pace with a script, then applies an eye checklist for continuity at every cut, legibility, brand, real UI, claims and differentiation. Writes a gap list and a scorecard; nothing ships on numbers alone. Use on every render, and on a reference film to learn from it, for "review the video", "check the film", "what is wrong with this cut", "study this reference".

freudianflips/breakout-launch-videos

Tool manual under launch-film (music fitted to the edit with Higgsfield Sonilo, ACE-Step locally, or the free scratch bed). Score a launch film with music whose sections are the film's acts. Each take is measured for tempo and section energy, stretched onto the film's BPM and offset so its drop lands on the cut. Use after the storyboard's beat sheet exists, for "music", "score", "soundtrack", "background track", "the drop", "beat grid".

freudianflips/breakout-launch-videos

Tool manual under launch-film (the sound palette, the event map, the cue sheet and generated sound kits). Design the sound effects of a launch film. Builds an event map from the storyboard, the voice-over word timings and the rendered timeline, voices every event from 1 consistent palette (the free synthesised, key-locked forge, or real glass, felt, wood, marimba, clicks and air generated on Higgsfield and pitched into the film's key), and renders 1 SFX stem in a shared acoustic space. Use once picture timing and the score are fixed, for "sound effects", "SFX", "sound design", "UI sounds", "sonic logo".

freudianflips/breakout-launch-videos

Tool manual under launch-film (the brief, the story spine, the script, the beat sheet and reference studies). Turn a launch brief into a launch film's story in your own brand, with the one message, the narrative spine, the voice-over script at the right length, a beat sheet on the music's bar grid and a STORYBOARD.md where every shot names its continuity in and out, its signature move and its sound. Includes the reference study and the logo-swap differentiation test. Use first, before voice, score or motion, for "launch video script", "storyboard", "brief", "what should the launch film say", "study this reference video".

freudianflips/breakout-launch-videos

Tool manual under launch-film (backgrounds, plates, Blender glass and 3D shots, shader layers). Build the world a launch film lives in, in your own brand, with generated background plates (cost-gated), Blender for real 3D glass objects and camera moves rendered as alpha layers, WebGL shader layers for atmosphere, and the layer order, depth of field and grade that keep UI legible over living backgrounds. Use when a storyboard needs backgrounds, 3D or atmosphere, for "background", "plate", "3D object", "glass", "Blender", "shader", "atmosphere"; motion of the UI itself is launch-motion.

相關技能