transcript-polisher
Transcript Polisher transforms raw speech transcripts—from interviews, lectures, podcasts, and meetings—into well-formatted, readable article paragraphs. It preserves the speaker's original phrasing, tone, and distinctive voice while removing filler words, correcting transcription errors, and restructuring content around natural pauses in thought.
Transcript Polisher converts raw speech transcripts into polished, readable articles while keeping the speaker's original voice intact.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-25
Transcript Polisher converts raw speech transcripts into polished, readable articles while keeping the speaker's original voice intact. Transcript Polisher transforms raw speech transcripts—from interviews, lectures, podcasts, and meetings—into well-formatted, readable article paragraphs. It preserves the speaker's original phrasing, tone, and distinctive voice while removing filler words, correcting transcription errors, and restructuring content around natural pauses in thought.
Use it when
- Yes.
- Transcript Polisher organizes multi-speaker dialogue transcripts with clear speaker attribution.
Verify before relying
Read SKILL.md below before installing (3 files). Open directory: indexed for reading, not audited.
Install
rookie-ricardo/erduo-skills/transcript-polisher · repository language: JavaScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does transcript-polisher polish transcripts into readable articles?
Transcript Polisher transforms raw speech transcripts into well-formatted, readable article paragraphs by removing filler words, correcting transcription errors, and restructuring content around natural pauses in thought. The tool preserves the speaker's original phrasing, tone, and distinctive voice throughout the process, making transcripts from interviews, lectures, podcasts, and meetings publication-ready without altering meaning.
Can transcript-polisher clean up podcast transcripts for publication?
Yes. Transcript Polisher is designed to clean up podcast transcripts for publication by fixing transcription errors, optimizing punctuation, and organizing content into coherent paragraphs. It maintains the podcast host's or guest's original voice and wording while removing speech artifacts, making the final output suitable for readers without changing the intended message or tone.
Does transcript-polisher organize multi-speaker conversation transcripts?
Transcript Polisher organizes multi-speaker dialogue transcripts with clear speaker attribution, making it easy to follow conversations between multiple participants. It structures interview and meeting transcripts so each speaker's contributions are properly labeled and formatted, improving readability while preserving the flow and authenticity of the original discussion.
Can I convert SRT or VTT subtitle files with transcript-polisher?
Transcript Polisher can process SRT and VTT subtitle files, converting them into continuous, semantically segmented text. Rather than keeping the line-by-line subtitle format, it restructures the content into proper paragraphs and article format, making subtitle text readable as flowing prose while maintaining accuracy and meaning.
Does transcript-polisher fix grammar while preserving the speaker's voice?
Yes. Transcript Polisher fixes grammar, punctuation, and transcription errors in speech-to-text output while carefully preserving the speaker's original voice, phrasing, and tone. The tool refines transcribed speech for readability and professionalism without changing the distinctive way the speaker expressed their ideas or their unique communication style.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
转录文本精修师
你的角色
你是一位资深访谈主笔与原声剪辑师。你的任务是将视频字幕的"文本切片"精修梳理为"可读性更高的文章段落"。
核心原则：你是一个"文字打磨者"而非"内容总结者"。你必须最大程度保留主讲人的原句、原词、比喻和个人特色，拒绝高度抽象的总结概括。想象你是演讲者本人的私人编辑——他信任你帮他把口头表达整理成书面文字，但绝不允许你替他改写观点。
输入格式
支持以下输入方式：
方式一：结构化输入
视频标题：<标题>
视频作者：<作者>
视频时长：<时长>
--- 字幕内容 ---
<字幕文本>
方式二：直接文本
用户直接给出文本，只需精修。
方式三：文件路径（.txt / .srt / .vtt）
读取文件内容。如果是 SRT 或 VTT 格式，先执行预处理（见第一步）。
如果用户没有提供视频标题/作者/时长，输出中省略 ## 视频信息 部分。
工作流程
第一步：预处理
纯文本：直接进入第二步。
SRT 格式：去除序号行、时间戳行（00:01:23,456 --> 00:01:25,789），只保留字幕文本行，合并为连续文本。
VTT 格式：去除 WEBVTT 头部、时间戳行（00:01:23.456 --> 00:01:25.789）、样式标签（<c>、<b> 等），只保留字幕文本行，合并为连续文本。
合并时，如果相邻字幕行明显是同一句话的延续（无句末标点），用空格连接；否则换行。
第二步：模式识别
判断文本是"单人表达"还是"多人对谈"。
判断依据：
- 有明确的说话人标注（如 主持人：、嘉宾：、A：、B：）→ 对谈模式
- 有明显的问答交替结构（一方提问、一方回答）→ 对谈模式
- 出现"你觉得呢"、"我想问一下"、"谢谢邀请"等对话信号词 → 对谈模式
- 全程单一视角叙述 → 单人模式
无标注说话人的对谈文本处理：
- 根据语气、称谓、问答逻辑推断说话人身份
- 用 **提问者：** /
(truncated - see the full file via the links below)
File tree — 3 files
skills/transcript-polisher/SKILL.md
skills/transcript-polisher/references/common-errors.md
skills/transcript-polisher/references/examples.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Convert raw speech transcripts into readable, well-formatted article paragraphs”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Translate Polisher delivers publication-grade translations between Chinese, English, and Japanese through a structured four-step process: deep source analysis, initial draft, editorial review, and polished final output. It preserves tone, handles rhetoric and cultural references intelligently, and adapts to your target audience—whether general readers, technical professionals, academics, or business stakeholders.
Daily News Report orchestrates parallel content fetching across multiple tech sources, applies intelligent filtering to surface high-quality articles, and compiles a structured daily markdown report. The skill uses a tiered strategy with browser-based rendering for JavaScript-heavy sites, caching to avoid duplicates, and early-stopping once 20 quality items are collected.
Anthropic Style Diagram generates semantic SVGs following Anthropic's visual language and design system, then renders them to PNG. The skill handles architecture, flow, and structural diagrams—automatically managing colors, themes, viewBox cropping, and style baking. Author the geometry and meaning; the rendering pipeline owns the design.
Faster-whisper delivers rapid, offline speech-to-text transcription using CTranslate2, achieving 4-6x speed over OpenAI Whisper while maintaining identical accuracy. Generate subtitles in multiple formats (SRT, VTT, TTML, CSV), identify speakers, process batches with ETA, search transcripts, and detect chapters—all without API dependencies.
Transcription Automation handles speech-to-text conversion for audio files, video recordings, and live streams, automatically identifying speakers and generating formatted transcripts. The skill produces searchable archives, meeting notes with action items, and subtitles in SRT or VTT formats across multiple languages. It integrates with platforms like Zoom, YouTube, and podcasting workflows to streamline content processing end-to-end.
This skill pulls captions directly from YouTube videos and outputs them as Chinese text. It handles both auto-generated and manually uploaded subtitles, automatically translating English captions to Chinese when needed. Output options include plain text, Markdown, or JSON formats, with optional timestamps.