Voiceover Budget Fit

Mode: Download — one-time purchase
Price: US$9.99
Version: 1.0.0
State: locally produced; not yet independently forward-tested or platform submitted

English short description

Fit an existing English or Chinese voiceover to a fixed slot. Get explicit-rate timing estimates, one concise cut draft, exact must-keep checks and a change ledger. Text estimates and drafts only; no audio generation.

English description

Your script is too long, but the product name and important qualification cannot disappear. Voiceover Budget Fit separates spoken lines from production notes, counts English words and Chinese Han characters, applies your stated speech rates and total pause allowance, then helps shorten repetition while retaining the meaning.

You receive original and candidate counts, a count-based timing report, a complete proposed recording draft, exact protected-string audit and a phrase-anchored change ledger. The included local Python helper makes the arithmetic reproducible. Numeric runs, unsupported scripts and symbols are flagged for explicit spoken expansion rather than silently guessed. It does not claim that text timing is measured audio.

Included: SKILL.md, English and Traditional Chinese buyer guides, input contract, Python 3.10+ standard-library helper, synthetic worked examples and one runnable example with its generated report.

Requires your own compatible AI agent client and model; their fees and terms are separate. Local Python is required for the executable helper. No API keys, TTS, paid service or network access are required by this package. Manual use is possible but calculations must be labeled unverified. No voice recording, MP4, sound file, image generation or automatic publishing is included.

Best for English and Chinese spoken drafts. Han-only Japanese cannot be reliably detected. Accents, names, abbreviations, URLs, delivery style and breaths need a real timed read. Exact-string checks verify presence, not factual meaning or repeated-phrase counts. Review all edits before recording.

繁體中文短介紹

固定秒數放不下口播稿？用明示語速與停頓估時，交付精簡稿、逐字必留檢查與修改紀錄。適用英文與中文，交付文字估算與稿件，不產生錄音。

繁體中文介紹

原稿太長，但商品名稱和重要限制不能消失。Voiceover Budget Fit 先把口播和畫面備註分開，計算英文詞數與中文漢字，再依你提供的語速、全部停頓和目標長度估時，刪除重複內容並保留原意。

交付原稿與精簡稿計數、可驗算估時報告、一版完整錄製稿、逐字必留核對及對照原句的修改紀錄。內附 Python 工具重現計數與運算；數字、未支援語言和符號會列為發音待確認，不會暗猜。文字估時不會被包裝成實際錄音測量。

下載包含 SKILL.md、中英文使用指南、輸入規格、Python 3.10 以上標準函式庫工具、虛構示例，以及一份可執行輸入與產出的報告。

需自備相容 AI Agent Client 與模型，其費用及條款另計。執行工具需本機 Python；套件本身不需 API 金鑰、付費外部服務、TTS 或網路。不能執行時可人工操作，但須標明計算未驗證。不包含配音、錄音、MP4、圖片生成或自動發布。

適用英文與中文口播；全漢字日文無法可靠識別。口音、人名、縮寫、網址、呼吸與演繹仍需實際計時試讀。逐字檢查驗是否存在，不驗語意或指定重複次數。錄製前請審閱所有修改。

Reproducible synthetic demonstration / 可重跑合成示範

45 English words at an assumed 150 words/minute plus three seconds of pauses estimate 21 seconds against a 15-second target. A proposed cut must preserve the supplied must-keep strings. Text estimates are not a recorded performance.

45個英文詞、假設150詞/分，加3秒停頓，估時21秒，超過15秒目標；縮稿提案需保留指定字串。文字估時不代表實際錄音時長。