transcript-polisher

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Transcript Polisher

转录稿润色

Transform raw podcast or interview transcripts into polished, professional documents that maintain authentic voice while dramatically improving readability and flow.

将原始播客或访谈转录稿转换为经过润色的专业文档，既保留真实语气，又显著提升可读性和流畅度。

When to Use This Skill

适用场景

Use this skill when:

Processing raw podcast transcripts from automated services (Rev, Otter, Descript, YouTube auto-captions)
Cleaning up interview recordings or video transcripts
Preparing spoken content for publication as articles or show notes
Converting conversational content into readable written format

Not for: Written content that wasn't originally spoken, pre-polished articles, or scripts that are already edited.

使用本技能的场景：

处理来自自动化服务（Rev、Otter、Descript、YouTube自动字幕）的原始播客转录稿
整理访谈录音或视频转录稿
为将口语内容发布为文章或节目笔记做准备
将对话内容转换为易读的书面格式

不适用场景： 原本并非口语的书面内容、已完成润色的文章或已编辑过的脚本。

Core Philosophy

核心原则

Balance authenticity with clarity: Remove everything that doesn't add meaning while preserving what was actually said. Create the "ideal version" of what the speaker wanted to communicate—without changing their words or ideas.

Target: 25-35% length reduction while maintaining 100% fidelity to meaning.

平衡真实性与清晰度： 删除所有无意义内容，同时保留实际表达的信息。打造说话者想要传达内容的“理想版本”——不改变其用词或观点。

目标： 在100%保留原意的前提下，将篇幅缩短25-35%。

Workflow

操作流程

Step 1: Add Document Structure

步骤1：添加文档结构

Create proper header with:

markdown

undefined

创建规范的标题部分，格式如下：

markdown

undefined

[Guest Name]: [Compelling Episode Title]

[嘉宾姓名]: [引人入胜的剧集标题]

[Podcast Name] Episode - [Host Names]

[播客名称] 剧集 - [主持人姓名]

Timestamped Outline

带时间戳的大纲

[Add 10 chapters maximum - see guidelines below]

[最多添加10个章节 - 详见下方指南]

[Time] Chapter Title

[时间] 章节标题

[Content starts here]


**Timestamped Outline Rules** (My First Million style):
- Format: `**MM:SS** - Descriptive Chapter Title`
- 10 chapters maximum for 45-60 minute episodes
- Focus on major topic changes, not minute-by-minute
- Use compelling, specific titles (not generic descriptions)

**Good Examples:**
- ✅ **12:25** - The 13th Percentile to Grade Level Miracle
- ✅ **29:08** - Why Successful Reforms Don't Spread

**Poor Examples:**
- ❌ **12:25** - Michelle talks about her students
- ❌ **29:08** - Discussion about education reform

[内容从此处开始]


**带时间戳的大纲规则**（参考《My First Million》风格）：
- 格式：`**MM:SS** - 描述性章节标题`
- 45-60分钟的剧集最多设置10个章节
- 聚焦主题的重大转变，而非逐分钟划分
- 使用引人入胜、具体的标题（避免通用描述）

**优秀示例：**
- ✅ **12:25** - 从13百分位到年级水平的奇迹
- ✅ **29:08** - 为何成功的改革难以推广

**反面示例：**
- ❌ **12:25** - Michelle谈论她的学生
- ❌ **29:08** - 关于教育改革的讨论

Step 2: Identify and Label Speakers

步骤2：识别并标记说话人

Replace generic speaker markers (>>, Speaker 1, etc.) with actual names:

Bold all speaker names:
```
**Isaac:** Content here
```
Use first names for casual podcasts, full names for professional interviews
Be consistent throughout

将通用的说话人标记（>>、Speaker 1等）替换为真实姓名：

所有说话人姓名加粗：
```
**Isaac:** 内容此处
```
休闲播客使用名字，专业访谈使用全名
全程保持一致

Step 3: Aggressive Editing Pass

步骤3：深度编辑

Apply aggressive polishing while maintaining 100% fidelity. See Editing Guidelines for detailed rules.

Quick checklist:

Remove ALL filler words ("um," "uh," "you know," "like," "so," "I mean")
Consolidate false starts and restarts
Pick the clearest version when speakers repeat themselves
Remove verbal hedging ("kind of," "sort of," "I think," "probably") when excessive
Cut conversational detours that don't serve the narrative
Fix awkward grammar and incomplete thoughts
Keep only 1-2 strongest examples if speaker gives 5+
Add clarity to vague pronouns (minimal bracketed additions)

在100%保留原意的前提下进行深度润色。详细规则请参阅编辑指南。

快速检查清单：

删除所有填充词（“um”、“uh”、“you know”、“like”、“so”、“I mean”等）
合并错误的开头和重复表述
当说话人重复内容时，选择最清晰的版本
过度使用的口头犹豫词（“kind of”、“sort of”、“I think”、“probably”）予以删除
删减对叙事无帮助的对话偏离内容
修正别扭的语法和不完整的表述
如果说话人给出5个以上例子，仅保留1-2个最有力的
对模糊的代词补充说明（尽量使用括号标注）

Step 4: Preserve What Matters

步骤4：保留关键内容

Never edit:

Unique voice and natural rhythm
Exact wording of powerful statements
Emotional moments and authenticity
Specialized terminology
Cultural references that reveal personality
Natural dialogue patterns

绝对不能编辑：

独特的语气和自然节奏
有力表述的准确用词
情感时刻与真实性
专业术语
能体现个性的文化引用
自然的对话模式

Step 5: Quality Check

步骤5：质量检查

Quick Reference

快速参考

For detailed examples and transformation patterns, see:

Editing Guidelines - Complete rules with before/after examples
Structure Template - Header format and chapter guidelines

如需详细示例和转换模式，请参阅：

编辑指南 - 包含完整规则及修改前后示例
结构模板 - 标题格式和章节指南

Common Transcription Errors to Fix

需要修正的常见转录错误

Auto-caption issues:

OCR errors (e.g., "quad code" → "Claude Code")
Homophone mistakes (e.g., "their" vs "there")
Missing punctuation
Run-on sentences
Mis-identified technical terms

Audio transcription issues:

Speaker confusion
Overlapping dialogue
Background noise artifacts
Timestamp errors

自动字幕问题：

OCR识别错误（例如：“quad code” → “Claude Code”）
同音词错误（例如：“their”与“there”混淆）
缺少标点符号
连句
识别错误的专业术语

音频转录问题：

说话人混淆
对话重叠
背景噪音干扰
时间戳错误

Output Format

输出格式

Final polished transcript should be:

Markdown formatted
Properly sectioned with timestamps
Speaker names bold and consistent
25-35% shorter than original
Grammar perfect but voice authentic
Ready for publication or repurposing

最终的润色转录稿应满足：

采用Markdown格式
按时间戳合理分段
说话人姓名加粗且格式一致
篇幅比原文短25-35%
语法完美但语气真实
可直接用于发布或二次创作

Critical Reminders

重要提醒

100% Fidelity Rule: ❌ Never paraphrase or change meaning ❌ Never add ideas not present in original ❌ Never remove key insights or stories ✅ Only remove redundancy and inefficiency ✅ Preserve exact wording of powerful statements ✅ Keep all substantive content

Aggressive Editing: ❌ "So, um, I think that, you know, what we really need to focus on..." ✅ "What we really need to focus on..."

Voice Preservation: ❌ Removing authentic expressions like "bugged the crap out of me" ✅ Keeping natural language that shows personality

100%原意保留规则： ❌ 绝不意译或更改原意 ❌ 绝不添加原文未提及的观点 ❌ 绝不删除关键见解或故事 ✅ 仅删除冗余和无效内容 ✅ 保留有力表述的准确用词 ✅ 保留所有实质性内容

深度编辑示例： ❌ “So, um, I think that, you know, what we really need to focus on...” ✅ “What we really need to focus on...”

语气保留示例： ❌ 删除“bugged the crap out of me”这类真实表达 ✅ 保留能体现个性的自然语言