talking-head-guide

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Before using this skill, read the required continuation in full. It is part of this skill and contains mandatory workflow, tool-contract, and safety instructions; do not act from this entry file alone.
使用此 skill 前,请完整阅读必需的续篇。它属于此 skill,包含强制性的工作流、工具契约和安全说明;不要仅依据此入口文件采取行动。

Speech-Led Video Editing (Talking Head, Interview, Podcast)

语音主导的视频剪辑(口播、访谈、播客)

What this skill covers

此 skill 涵盖的内容

Required input: an existing speech-led source registered or imported into the project — for example a single-speaker talking-head / 口播, a two- or multi-speaker interview / 访谈, a video podcast, lecture, tutorial, or course. For transcript-based A-roll editing, follow
asset-import
, then start as soon as the transcript is ready. If the user wants to start without source footage (e.g., generate a fresh talking-head from scratch), this skill doesn't apply.
必需输入:项目中已注册或导入的现有语音主导源素材——例如单人口播、双人或多人访谈、视频播客、讲座、教程或课程。对于基于文字稿的 A-roll 剪辑,先执行
asset-import
,文字稿就绪后立即开始。如果用户想在没有源素材的情况下开始(例如从零生成一段全新的口播视频),则此 skill 不适用。

When source media is missing

当源媒体缺失时

  • Antigravity: First check the project's asset library. The user may provide the source in the conversation or upload it directly in the linked ChatCut editor. Use
    asset-import
    when an attachment or readable local path still needs import. Reuse editor-uploaded registered assets without importing them again.
When creating, targeting, or opening a project for visible work, provide the clean
editorUrl
before nontrivial edits and again before final delivery if the visible project no longer matches. Antigravity's browser agent may open it when the user asks; do not require an internal browser handoff.
Independent treatments that can be applied to speech-led videos. Pick the ones that match what the user wants — not all are needed every time.
  • A-roll editing (Chinese product term: 语音剪辑, including 去口癖、停顿、重复) — transcript-based speech editing. Common operations include cleanup, highlight extraction, restructure, opening hook, and others as needed for the aligned outcome.
  • Motion graphics overlay (write the full name Motion Graphics in English user-facing copy, not "MG"; the fixed Chinese product term is MG 动画, not alternatives such as "动效", "字幕条", or "动态字幕") — reinforce key information, structured content, and topic transitions with on-screen motion graphics
  • B-roll (industry term — keep as "B-roll" in any language, do not translate) — cover jump cuts or visualize what's being said
  • Background music (Chinese product term: 背景音乐) — set mood and smooth micro-gaps
  • Captions (Chinese product term: 字幕) — on-screen text for accessibility
  • AI Voice Isolation (Chinese product term: AI 人声隔离) — clean or isolate spoken human voice with DeepFilterNet3, picture untouched. See the
    voice-isolation
    skill.
When the user's language is Chinese, use the exact product terms in parentheses above in widget options, choices options, and conversation copy. Do not retranslate them; that would conflict with terminology elsewhere in the product.
  • Antigravity: 首先检查项目的素材库。用户可能在对话中提供源素材,或直接将其上传到关联的 ChatCut 编辑器。当附件或可读取的本地路径仍需导入时,使用
    asset-import
    。复用已通过编辑器上传并注册的资源,不要再次导入。
在创建、指定或打开用于可视化工作的项目时,应在非简单剪辑前提供干净的
editorUrl
;如果最终交付前当前可见项目已与目标不一致,也应再次提供。Antigravity 的 browser agent 可以在用户提出要求时打开它;不要要求进行内部浏览器交接。
可独立应用于语音主导视频的处理方式。请选择符合用户需求的项目——并非每次都需要全部处理。
  • A-roll editing(中文产品术语:语音剪辑,包括 去口癖、停顿、重复)——基于文字稿的语音剪辑。常见操作包括清理、亮点提取、重构、开场钩子,以及为实现对齐目标所需的其他操作。
  • Motion graphics overlay(面向用户的文案中应写全称 Motion Graphics,不要写“MG”;固定中文产品术语为 MG 动画,不要使用“动效”“字幕条”或“动态字幕”等替代说法)——通过屏幕上的 Motion Graphics 强化关键信息、结构化内容和主题转场
  • B-roll(行业术语——任何语言中都保留“B-roll”,不要翻译)——遮盖跳切,或将所说的内容可视化
  • Background music(中文产品术语:背景音乐)——营造氛围并平滑微小间隙
  • Captions(中文产品术语:字幕)——用于提升无障碍访问体验的屏幕文字
  • AI Voice Isolation(中文产品术语:AI 人声隔离)——使用 DeepFilterNet3 清理或分离说话人声,不改动画面。参见
    voice-isolation
    skill。
当用户使用中文时,在 widget options、choices options 和 conversation copy 中,必须使用以上括号内的确切产品术语。不要重新翻译;否则会与产品其他位置的术语发生冲突。

What shapes the edit

影响剪辑方式的因素

Beyond picking treatments, a talking-head edit is shaped by several orthogonal variables. When the user's ask is vague, these are what's worth clarifying first:
  • Target — platform (YouTube / TikTok / Shorts / ...), desired length, aspect ratio
  • Which treatments to apply — the treatments above are optional; don't assume all of them apply
  • Pacing / tone — tight / energetic / formal / casual; brand or voice preferences if stated. (For MG visual style, follow the active Motion Graphics skill/workflow.)
When more than one of these variables is missing, ask concise related text questions after loading
widget-forms
, keeping stable choice ids internally. Do not emit native form or
<choices/>
tags.
除了选择处理方式外,口播剪辑还受多个相互独立的变量影响。当用户需求含糊时,以下内容最值得优先澄清:
  • 目标——发布平台(YouTube / TikTok / Shorts / ...)、期望时长、宽高比
  • 要应用哪些处理方式——上述处理方式均为可选项;不要假定它们全部适用
  • 节奏 / 语气——紧凑 / 活力 / 正式 / 随意;如果用户说明,还应遵循其品牌或声音偏好。(对于 MG 视觉风格,应遵循当前启用的 Motion Graphics skill/workflow。)
当上述变量中有一个以上缺失时,在加载
widget-forms
后,提出相互关联的简洁文本问题,同时在内部保持 choice id 稳定。不要输出原生 form 或
<choices/>
标签。

Order of execution

执行顺序

When multiple treatments have been aligned with the user, they depend on each other and must be finalized in dependency order. This section is only relevant after alignment — it doesn't tell you what to start with on a fresh request.
The speech timing (set by A-roll editing) anchors everything downstream — MG placement, B-roll cut-covers, music duration, and caption sync all reference the final speech timeline.
So: finalize A-roll editing before committing any visual, audio, or text layer. Don't write captions against pre-edit speech, don't cut music to pre-edit length, don't place MG against timing that will shift.
Once the cut structure is final, run
smooth_audio
once as the last audio step — it micro-crossfades every hard audio cut and fades exposed edges so edits don't pop. Run it after
apply_script
/
clean_script
restructuring (reflow drops transitions); it's idempotent, so re-run it if the timeline changes again.
You must confirm the result with the user after each major step before starting the next, unless the user has explicitly asked to run end-to-end without stopping. Key checkpoints when multiple treatments apply: after A-roll editing finalizes the speech timing; before MG generation (confirm style and direction, and, when it isn't obvious, whether it sits over the video as an overlay or takes the whole frame); after MG generation; same pattern for B-roll, music, and captions. Don't bundle multiple checkpoints into one response — confirm each step separately. An upstream mistake forces redoing everything downstream (e.g., MG placed against pre-cleanup timing wastes generation credits when the timeline shifts).

当多种处理方式已与用户对齐后,它们彼此依赖,必须按照依赖顺序完成。本节仅在对齐后适用——它不会告诉你全新请求应从哪里开始。
语音时间轴(由 A-roll editing 确定)是所有下游工作的基准——MG 布局、B-roll 跳切遮盖、音乐时长和字幕同步都要参考最终的语音时间轴。
因此,应先最终确定 A-roll editing,再提交任何视觉、音频或文本图层。不要根据剪辑前的语音制作字幕,不要按照剪辑前的长度裁剪音乐,也不要基于之后会变化的时间轴放置 MG。
剪辑结构最终确定后,将
smooth_audio
作为最后一个音频步骤运行一次——它会为每个生硬的音频剪切点添加极短的交叉淡化,并淡出暴露的边缘,避免编辑产生爆音。完成
apply_script
/
clean_script
重构后运行它(重排会移除转场);该操作是幂等的,因此如果时间轴再次变化,可以重新运行。
除非用户明确要求不中断地端到端执行,否则每个主要步骤完成后、开始下一步前,都必须向用户确认结果。 多种处理方式同时适用时的关键检查点包括:A-roll editing 最终确定语音时间轴后;MG 生成前(确认风格和方向,并在情况不明显时确认它是作为叠加层覆盖在视频上,还是占据整个画面);MG 生成后;B-roll、音乐和字幕也遵循相同模式。不要将多个检查点合并到一次回复中——应分别确认每个步骤。 上游错误会迫使所有下游工作返工(例如,MG 基于清理前的时间轴进行布局,时间轴变化后会浪费生成额度)。

A-roll editing

A-roll editing

Scenario

场景

In a talking-head workflow, the first step is usually A-roll editing: editing the original spoken footage.
A-roll edits are ultimately applied to the timeline and change what the viewer actually hears and sees. However, the editing decisions should usually start from the transcript, because the core question is: what spoken content should the viewer hear, and what should be removed, compressed, or reordered?
在口播工作流中,第一步通常是 A-roll editing,即编辑原始口播素材。
A-roll 编辑最终会应用到时间轴,并改变观众实际听到和看到的内容。不过,编辑决策通常应从文字稿开始,因为核心问题是:观众应该听到哪些口语内容,哪些内容应该删除、压缩或重排?

Common A-roll tasks

常见的 A-roll 任务

A-roll editing is not only cleanup. First decide what spoken-content task the user is asking for, then choose the editing strategy and tools.
Common tasks:
  • Cleanup — remove mistakes, repeated attempts, verbal habits, filler words, and meaningless pauses so the speech becomes clearer and more natural.
  • Highlight extraction — pull the most valuable, opinionated, emotional, or topic-relevant moments from longer footage.
  • Restructure — reorder spoken content, such as moving the conclusion earlier, grouping by topic, or combining scattered parts into a clearer structure.
  • Hook / short version — use a strong claim, result, conflict, or question from the source as the opening, or compress long content into a shorter version.
  • Target-script / script alignment — match, keep, and reorder spoken content according to a user-provided target script, target paragraph, or desired content.
Cleanup is the most common task and the one most likely to fail from bad boundary decisions. It is described in detail below. Other tasks get shorter rules, but still follow the shared A-roll principles: complete meaning, clear boundaries, and natural listening flow.
A-roll editing 不只是清理。首先应确定用户要求完成哪种口语内容任务,再选择编辑策略和工具。
常见任务:
  • 清理——删除错误、重复尝试、口语习惯、填充词和无意义的停顿,使表达更清晰、更自然。
  • 亮点提取——从较长素材中提取最有价值、最具观点、最富情绪或与主题最相关的时刻。
  • 重构——重新安排口语内容,例如将结论提前、按主题分组,或将零散内容合并成更清晰的结构。
  • 钩子 / 短视频版本——使用素材中有力的主张、结果、冲突或问题作为开场,或将长内容压缩为更短的版本。
  • 目标脚本 / 脚本对齐——根据用户提供的目标脚本、目标段落或期望内容,对口语内容进行匹配、保留和重排。
清理是最常见的任务,也是最容易因边界判断失误而失败的任务。下文将详细介绍清理。其他任务适用较简短的规则,但仍须遵循 A-roll 的共同原则:内容完整、边界清晰、收听自然。

Shared A-roll principles

A-roll 共同原则

These principles apply to all A-roll tasks, not only cleanup.
  • Decide the task before choosing the tool. Do not let tool availability change the editing strategy.
  • Edit by complete semantic units. Whenever possible, move/delete/keep complete sentences, complete ideas, complete answers, or complete steps. Do not cut out a half-sentence just because a few words match.
  • When the task names what to keep, trim to that boundary. The inverse of the rule above, for any task that specifies which content to keep — restoring a specific sentence, matching a target script, pulling a named highlight, building a version: keep exactly the requested span. Trim the kept range to start and end at the requested words and drop the off-script head/tail of the source
    [sN]
    segment it sits in; keeping a whole segment for one requested sentence is over-keeping that drags in unrequested speech. This applies only when the task names what to keep — never to open-ended cleanup, where you keep complete units (above).
  • Do not stitch unfinished fragments across retakes. Do not combine incomplete pieces from different attempts into one artificial sentence. This does not make the earlier attempt disposable: keep a complete useful lead-in, setup, contrast, category, evaluation, or context if it is not repeated later and can naturally connect to the later complete retake.
  • Preserve connective tissue. List labels, contrast words, subjects, verbs, and adjacent source words are not filler when removing them makes a kept idea ungrammatical, abrupt, or misleading. Trim the smallest span that keeps the line speakable.
  • Keep listening flow natural. The result should still have natural phrasing and breathing room. Do not make sentences feel glued together just to make them "clean."
  • Be conservative when boundaries are uncertain. If unsure whether a cut harms meaning, logic, or listening flow, keep it or make a smaller cut.
  • Confirm complex changes first. For complex restructuring, aggressive shortening, structural changes, or generated hooks, confirm target length, structure direction, and what to preserve with the user before editing.
  • Explain content, never indices. You MUST NOT explain edits to the user with internal addresses such as
    [sN]
    ,
    [cN]
    ,
    [gap]
    , word indices, clip ids, or segment ids. The user cannot see those addresses and will not understand what they mean. Use the actual spoken content, a short quote, or a plain-language description of the edit.
  • Never name a screen position for a panel. When you invite the user to review or fine-tune the result, call it "the Transcript panel" (Chinese product term: "文字稿面板") — never a direction (left / right / side / 左侧 / 右侧). The layout is rearrangeable and the panel does not sit in a fixed corner.
以下原则适用于所有 A-roll 任务,不只限于清理。
  • 先确定任务,再选择工具。 不要让工具的可用性决定编辑策略。
  • 按完整的语义单元进行编辑。 尽可能移动、删除或保留完整句子、完整观点、完整回答或完整步骤。不要只因为几个词匹配就切掉半句话。
  • 当任务明确指定保留内容时,将裁剪范围收紧到该边界。 这条规则与上一条相反,适用于明确指定要保留哪些内容的任务——恢复特定句子、匹配目标脚本、提取指定亮点或制作某个版本:严格保留所请求的区间。将保留范围裁剪到从请求的词语开始、到请求的词语结束,并删除源
    [sN]
    片段中位于该范围之外的脚本外前后内容;仅因为请求中的一句话而保留整个片段属于保留过多,会带入未请求的语音。此规则仅适用于明确指定保留内容的任务;绝不适用于开放式清理,开放式清理应遵循上一条,保留完整语义单元。
  • 不要跨不同重拍拼接尚未完成的片段。 不要把不同尝试中不完整的内容组合成一句人为拼凑的话。这并不意味着应丢弃较早的尝试:如果其中完整且有用的引入、铺垫、对比、分类、评价或上下文没有在后续内容中重复,并且能够自然衔接到后面的完整重拍,就应予以保留。
  • 保留连接性内容。 列表标签、对比词、主题、动词以及相邻的源词语并非填充词;如果删除它们会让保留的观点变得不 grammatically、不连贯或产生误导,就不应删除。只裁剪能够让语句自然朗读的最小范围。
  • 保持收听 flow 自然。 结果仍应具有自然的措辞和呼吸空间。不要为了显得“干净”而让句子听起来像是被强行拼接在一起。
  • 边界不确定时保持保守。 如果无法确定剪切是否会损害意义、逻辑或收听体验,就保留内容或采用更小范围的剪切。
  • 复杂修改必须先确认。 对于复杂重构、大幅缩短、结构性变更或生成式钩子,编辑前应与用户确认目标时长、结构方向和需要保留的内容。
  • 解释内容,绝不解释索引。 绝不能使用
    [sN]
    、
    [cN]
    、
    [gap]
    、词语索引、clip id 或 segment id 等内部地址向用户解释编辑。用户看不到这些地址,也无法理解其含义。应使用实际的口语内容、短引文或对编辑操作的通俗描述。
  • 绝不为面板指定屏幕位置。 邀请用户审阅或微调结果时,应称其为“Transcript panel”(中文产品术语:“文字稿面板”),绝不能使用方位词(left / right / side / 左侧 / 右侧)。布局可以重新排列,面板并不固定在某个角落。

Cleanup goals and decisions

清理目标与决策

What good cleanup means

什么是好的清理

Good cleanup does not mean making the video as short as possible, and it does not mean rewriting the speaker into a different script.
Good cleanup means:
  • The logic stays coherent
  • The expression becomes clearer
  • The audio feels natural
  • Obvious mistakes, repeated attempts, meaningless stalls, and filler are removed
  • The speaker's intent, tone, and natural rhythm are preserved
Bad cleanup usually falls into two failure modes:
  • Under-cleaning: obvious mistakes, repetition, long pauses, or filler remain.
  • Over-cleaning: sentences are cut off, meaning is missing, rhythm becomes too hard, or the result sounds stitched together.
Default principle: remove defects without changing meaning; make speech smoother, not harder; prefer small local cuts over whole-sentence or whole-segment deletion; when unsure whether a cut harms meaning, keep it.
好的清理并不意味着让视频尽可能短,也不意味着把说话者改写成另一套脚本。
好的清理意味着:
  • 逻辑保持连贯
  • 表达更加清晰
  • 音频听起来自然
  • 明显的错误、重复尝试、无意义停顿和填充词被删除
  • 说话者的意图、语气和自然节奏得到保留
糟糕的清理通常表现为两种问题:
  • 清理不足: 明显的错误、重复、长停顿或填充词仍然存在。
  • 过度清理: 句子被切断、意义缺失、节奏过于生硬,或结果听起来像是拼接而成。
默认原则是:删除缺陷但不改变意义;让语音更流畅,而不是更生硬;优先采用小范围局部剪切,而不是删除整个句子或片段;无法确定剪切是否会损害意义时,应予以保留。

How to judge common cleanup cases

如何判断常见的清理情况

Below are the common cleanup categories and how to make editing decisions for each.
以下是常见的清理类别,应分别采用相应的编辑决策。
Meaningless filler words
无意义的填充词
Fillers fall into two categories.
The first category is clearly meaningless hesitation sounds. These are usually safe to remove:
  • um
  • uh
  • er
  • ah
  • 呃
  • 额
  • えー
    /
    えーと
    /
    えっと
  • あー
  • んー
When they do not carry special meaning, use
clean_script
for bulk cleanup of its supported literal tokens:
um
,
uh
,
er
,
ah
,
呃
, and
额
. Japanese hesitation sounds require a Script edit (
read_script
→ edit
timeline.md
→
apply_script
);
clean_script
does not currently remove them.
The second category depends on context and must not be removed by word list alone:
  • so
  • like
  • 然后
  • 就是
  • 嗯
  • 啊
  • 那个
  • 那
  • 对
  • 所以
  • 但是
  • あの
    /
    あのー
  • その
    /
    そのー
  • まあ
  • なんか
  • ちょっと
  • で
  • うーん
  • やっぱり
How to decide:
  • If the word is only hesitation or padding, remove it.
  • If it carries sequence, continuation, contrast, cause, reference, response, emphasis, or natural tone, keep it.
  • If removing it makes the surrounding words sound hard-spliced, keep it or only compress the pause.
  • If unsure, keep it.
Examples:
  • um, I think this solves the main problem
    -> remove
    um
    .
  • It works like a checklist
    -> keep
    like
    ; it is a comparison.
  • The upload failed, so we retried it
    -> keep
    so
    ; it carries cause/result.
  • right after the call, send the recap
    -> keep
    right
    ; it modifies timing.
  • 然后我们再看第二点
    -> keep
    然后
    ; it marks sequence.
  • えーと、次のポイントです
    -> remove
    えーと
    ; it is pure hesitation.
  • あの人が言っていた通りです
    -> keep
    あの
    ; it is a demonstrative, not hesitation.
  • あの、ちょっと待ってください
    -> remove the leading
    あの
    ; it is hesitation here.
  • まあ、悪くないと思います
    -> keep
    まあ
    ; it softens the judgement and carries tone.
  • なんか違和感がある
    -> keep
    なんか
    ; it means "somehow" here, not padding.
填充词分为两类。
第一类是明显没有意义的迟疑音,通常可以安全删除:
  • um
  • uh
  • er
  • ah
  • 呃
  • 额
  • えー
    /
    えーと
    /
    えっと
  • あー
  • んー
当它们不承载特殊含义时,使用
clean_script
批量清理其支持的字面 token:
um
、
uh
、
er
、
ah
、
呃
和
额
。日语迟疑音需要通过 Script 编辑处理(
read_script
→ 编辑
timeline.md
→
apply_script
);
clean_script
目前无法删除这些日语迟疑音。
第二类是否需要删除取决于上下文,不能仅依据词语列表处理:
  • so
  • like
  • 然后
  • 就是
  • 嗯
  • 啊
  • 那个
  • 那
  • 对
  • 所以
  • 但是
  • あの
    /
    あのー
  • その
    /
    そのー
  • まあ
  • なんか
  • ちょっと
  • で
  • うーん
  • やっぱり
决策方法:
  • 如果该词只表示迟疑或填充,则删除。
  • 如果它承载顺序、承接、对比、因果、指代、回应、强调或自然语气,则保留。
  • 如果删除后周围词语听起来像是被生硬拼接,则应保留该词,或只压缩停顿。
  • 如果无法确定,则保留。
示例:
  • 呃,我认为这能解决主要问题
    -> 删除
    呃
    。
  • 它的使用方式像一份检查清单
    -> 保留
    像
    ;它表示比较。
  • 上传失败了,所以我们重试了
    -> 保留
    所以
    ;它表示因果关系。
  • 通话结束后马上发送回顾
    -> 保留
    马上
    ;它修饰时间。
  • 然后我们再看第二点
    -> 保留
    然后
    ;它标示顺序。
  • えーと、次のポイントです
    (“呃ー,下一个重点是……”)-> 删除
    えーと
    ;它只是纯粹的迟疑。
  • あの人が言っていた通りです
    (“正如那个人所说”)-> 保留
    あの
    ;它是指示词,不是迟疑词。
  • あの、ちょっと待ってください
    (“那个,请稍等”)-> 删除开头的
    あの
    ;在这里它是迟疑词。
  • まあ、悪くないと思います
    (“我觉得也还可以”)-> 保留
    まあ
    ;它弱化判断并传达语气。
  • なんか違和感がある
    (“总觉得有点不对劲”)-> 保留
    なんか
    ;这里表示“不知怎么的”,不是赘词。
Retakes and repeated attempts
重拍和重复尝试
A retake is when the speaker retries the same intended idea because they misspoke, got stuck, forgot words, or restarted. Retake cleanup is not "delete repeated text." The goal is to keep one complete, natural, logically coherent version of the intended idea.
Use this decision path:
  1. Decide whether it is really a retake. Treat it as a retake only when multiple attempts are trying to say the same intended idea. Do not treat it as a normal retake when the repetition is intentional emphasis, a rhetorical beat, a structural marker, or a second pass that adds new information or tone.
  2. Define the complete version to keep. A complete version may include more than the main content sentence. It may need a lead-in, connector, section marker, topic setup, contrast, qualifier, subject, object, or conclusion. These are not filler when the kept content depends on them.
  3. Cut only the failed or covered part. Remove only words that are wrong, dangling, abandoned, or fully covered by the kept version. The cut boundary starts at the repeated or failed idea, not automatically at the earlier transition, setup, or continuous speech. If earlier speech contains useful context that the kept version does not repeat, keep it.
  4. Choose the best complete attempt. If several attempts are complete, usually prefer the later one because it is often closer to the speaker's intended take. But do not choose the last attempt mechanically. If the later attempt is missing needed context, structure, subject, object, or conclusion, keep the more complete version or preserve the missing lead-in from the earlier attempt.
A repeated lead-in is redundant only when another equivalent lead-in remains naturally connected to the kept content. If removing every copy makes the result lose structure or sound abrupt, keep one natural copy and remove only the extra restarts. Do not stitch unfinished fragments from different attempts into one artificial sentence.
Examples are patterns, not a closed list:
  • Local false start inside a kept sentence:
    There, there's no After Effects, no Premiere, no DaVinci Resolve learning.
    Keep the complete sentence, but remove the abandoned restart:
    There's no After Effects, no Premiere, no DaVinci Resolve learning.
    Do not keep the stray first word just because the full sentence is otherwise useful.
  • Repeated structural lead-in:
    And secondly, ... and secondly, we're introducing a brand new UI.
    Remove the extra restart, but keep one natural lead-in attached to the kept content:
    And secondly, we're introducing a brand new UI.
    Do not delete every structural marker and leave only:
    We're introducing a brand new UI.
  • Useful setup before a failed ending:
    Then the next one is different from comedy. It is popular on Disney Plus. It is called...
    Later retake:
    It is a popular Disney Plus show called Love Story.
    Keep useful setup that the later retake does not repeat, and cut from the failure point:
    Then the next one is different from comedy. It is a popular Disney Plus show called Love Story.
当说话者因为说错、卡住、忘词或重新开始,而再次尝试表达同一个意图时,这段内容就是一次重拍。重拍清理并不是“删除重复文本”。目标是保留一个完整、自然且逻辑连贯的意图版本。
请遵循以下决策路径:
  1. 先判断它是否确实属于重拍。 只有当多次尝试试图表达同一个意图时,才应视为重拍。如果重复属于有意强调、修辞性停顿、结构标记,或第二次尝试补充了新信息或新语气,则不要将其视为重拍。
  2. 定义要保留的完整版本。 完整版本可能不只包含核心内容句。它可能需要引入语、连接语、章节标记、主题铺垫、对比、限定词、主题、宾语或结论。当保留内容依赖这些部分时,它们就不是填充词。
  3. 只剪切失败或已被覆盖的部分。 仅删除错误、悬空、被放弃或已被保留版本完整涵盖的词语。剪切边界应从重复或失败的想法开始,而不是自动从更早的转场、铺垫或连续语音开始。如果更早的语音包含保留版本没有重复的有用上下文,应予以保留。
  4. 选择最佳的完整尝试。 如果多次尝试都完整,通常优先选择后一次,因为它往往更接近说话者想要的版本。但不要机械地选择最后一次。如果后一次缺少必要的上下文、结构、主题、宾语或结论,应保留更完整的版本,或从更早的尝试中保留缺失的引入内容。
只有在保留内容后仍有一个等价引入语能够自然连接时,重复的引入才算冗余。如果删除所有副本会使结果失去结构或听起来突兀,应保留一个自然的副本,只删除多余的重启。不要将不同尝试中未完成的片段拼接成一句人为拼凑的话。
以下示例是模式,而非封闭列表:
  • 保留句中出现的局部错误开始:
    那个,那里没有 After Effects、没有 Premiere,也不学 DaVinci Resolve。
    保留完整句子,但删除被放弃的重启:
    那里没有 After Effects、没有 Premiere,也不学 DaVinci Resolve。
    不要仅仅因为完整句子基本有用,就保留那个孤立的首词。
  • 重复的结构性引入:
    其次,……而且其次,我们正在推出一个全新的 UI。
    删除多余的重启,但保留一个与保留内容自然衔接的引入:
    其次,我们正在推出一个全新的 UI。
    不要删除所有结构标记后只剩下:
    我们正在推出一个全新的 UI。
  • 失败结尾之前存在有用铺垫:
    然后下一个与喜剧不同。它在 Disney Plus 上很受欢迎。它叫……
    后续重拍:
    它是一部在 Disney Plus 上很受欢迎的剧集,叫 Love Story。
    保留后续重拍没有重复的有用铺垫,并从失败点开始剪切:
    然后下一个与喜剧不同。它是一部在 Disney Plus 上很受欢迎的剧集,叫 Love Story。
False starts and unfinished fragments
错误开始和未完成片段
Use
false starts / unfinished fragments
for this category.
False start
is the more natural editing/transcription term for a speaker beginning a phrase and then restarting or abandoning it;
unfinished fragment
makes the dangling half-sentence case explicit.
Only remove a fragment when it clearly does not form useful information.
Safe to remove:
  • The speaker abandons the thought and a complete version appears later.
  • The segment is only a dangling phrase, such as "this is actually..." with no completion.
  • It is clearly the leftover beginning of a failed attempt.
Do not remove:
  • A sentence that is imperfect but contains useful information.
  • A lead-in that provides the subject, object, or context needed later.
  • Content that provides setup, contrast, conclusion, emotion, or tone.
If only part of a sentence or segment is wrong, do not delete the useful content around it. Remove only the bad word, phrase, or pause; if a local cut cannot sound natural, keep the segment.
对此类别使用
false starts / unfinished fragments
。
False start
是更自然的剪辑/转录术语,指说话者开始一句话后又重新开始或放弃;
unfinished fragment
则明确表示悬空的半句话。
只有当片段明显不包含有用信息时,才应将其删除。
可以安全删除:
  • 说话者放弃了一个想法,后续出现了完整版本。
  • 该片段只是一个悬空短语,例如“其实这是……”却没有后续内容。
  • 明显是失败尝试遗留的开头。
不要删除:
  • 虽然不完美但包含有用信息的句子。
  • 为后续内容提供主题、宾语或必要上下文的引入内容。
  • 能够提供铺垫、对比、结论、情绪或语气的内容。
如果一个句子或片段只有部分内容错误,不要删除周围的有用内容。只删除错误的词语、短语或停顿;如果局部剪切无法自然衔接,则保留该片段。
Pauses and breaths
停顿与呼吸
Pause cleanup should default to compression, not zeroing out. Spoken video needs natural breathing room.
Default rules:
  • Obvious long pauses over 0.8-1s: usually compress to about 0.3s.
  • Between sentences: keep about 0.3-0.5s so listeners can hear natural phrasing.
  • Around topic shifts, contrast, or emphasis: keep slightly longer pauses when needed; do not make the delivery too rushed.
  • Short breaths inside one sentence: if they are normal breathing, do not remove them.
  • Clear long pauses inside one sentence: compress them, but not so tightly that adjacent words sound glued together.
  • Long pauses before a retake: if the failed attempts around it are removed, remove the pause with them.
  • If the user provides explicit thresholds, follow them. For example, if the user says "only process pauses over 0.8s and keep at least 0.3s", do not process natural pauses under 0.8s.
停顿清理默认应采用压缩,而不是完全归零。口播视频需要自然的呼吸空间。
默认规则:
  • 明显超过 0.8-1s 的长停顿:通常压缩到约 0.3s。
  • 句子之间:保留约 0.3-0.5s,让听众能听到自然的语句节奏。
  • 主题转换、对比或强调附近:必要时保留稍长的停顿,不要让表达过于仓促。
  • 同一句内部的短促呼吸:如果属于正常呼吸,不要删除。
  • 同一句内部明显的长停顿:可以进行压缩,但不要压缩到相邻词语听起来被强行粘连。
  • 重拍前的长停顿:如果失败尝试 surrounding 已被删除,则连同停顿一起删除。
  • 如果用户给出了明确阈值,应遵循该阈值。例如,用户说“只处理超过 0.8s 的停顿,并至少保留 0.3s”时,不要处理短于 0.8s 的自然停顿。

Other A-roll task guidance

其他 A-roll 任务指导

Load only the reference for the branch the user selected. Do not preload references for unrequested treatments; default cleanup requires no reference.
For A-roll editing scenarios other than cleanup — including highlight extraction, restructure, hook / short version, target-script / script alignment, or building versions, highlights, and excerpts — read
references/other-a-roll-editing-scenarios.md
from this skill's base directory completely before planning or editing that A-roll branch.
仅加载用户所选分支对应的 reference。不要预加载未请求处理方式的 reference;默认清理不需要 reference。
对于清理以外的 A-roll 场景——包括亮点提取、重构、钩子/短视频版本、目标脚本/脚本对齐,以及制作版本、亮点和节选——在规划或编辑该 A-roll 分支之前,完整阅读此 skill 基础目录中的
references/other-a-roll-editing-scenarios.md
。