菜单
Convert PDF files to MP3 audio using MiniMax MCP Server's text-to-audio tool. Use when user wants to convert a PDF to audio/MP3, create audiobook from PDF, or text-to-speech for PDF documents. Requires PDF file path; voice ID is optional (auto-selects based on content).
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
通用短篇小说创作技能包。支持多种类型（武侠/科幻/童话/现言），执行大纲、人物、目录、章节的专业创作。根据类型参数加载对应的创作方法论和写作风格。
Generate story specification markdown files for various fiction genres. Use when: (1) User says "write a [genre] story" in pinyin (e.g., "tonghua", "wuxia", "kehuan") (2) User says "策划/设计一个[类型]类别的小说" (e.g., "童话故事", "武侠江湖", "科幻小说") (3) User wants to design/plan a new story before writing (4) User mentions story design, story spec, or story planning for fiction Supported genres: tonghua/童话故事, dushi/都市言情, gufeng/古风权谋, kehuan/科幻小说, keji/科技创业, kepu/科普纪实, kongbu/恐怖灵异, lishi/历史军事, mori/末日生存, qingchun/青春校园, wuxia/武侠江湖, xianyan/现代言情, xuanhuan/玄幻修仙, xuanyi/悬疑推理, yiliao/医疗生命
Parallel PDF to MP3 conversion using MiniMax. Convert multiple PDF chapters to audio simultaneously using parallel subagents. Use when: (1) User says 'generate mp3 for the story of [STORY_NAME]', (2) User says '为故事[STORY_NAME]生成mp3', (3) User says '为故事[STORY_NAME]第[X]章生成mp3', (4) User says 'generate mp3 for story of [STORY_NAME], chapter [X]', (5) Converting a range of PDFs like 'story-[01-05].pdf' to MP3, (6) Batch audiobook creation from PDF chapters.
Convert Markdown files to beautifully styled PDFs with full Chinese font support. Use when: (1) Converting .md files to PDF format, (2) Creating printable documents from Markdown, (3) Generating book chapters or story PDFs, (4) Needing PDF output with custom styling (colors, fonts, backgrounds), (5) Working with Chinese text that needs proper rendering in PDF.
| name | pdf2audio-minimax |
| description | Convert PDF files to MP3 audio using MiniMax MCP Server's text-to-audio tool. Use when user wants to convert a PDF to audio/MP3, create audiobook from PDF, or text-to-speech for PDF documents. Requires PDF file path; voice ID is optional (auto-selects based on content). |
Convert PDF documents to MP3 audio files using MiniMax text-to-audio.
/pdf2audio-minimax <pdf_file_path> [voice_id]
Examples:
/pdf2audio-minimax /path/to/story.pdf (auto-select voice)/pdf2audio-minimax /path/to/story.pdf Chinese (Mandarin)_GentlemanExtract from user input:
pdf_path: Full path to the PDF file (required)voice_id: Voice identifier (optional)Read: file_path = <pdf_path>
Extract readable text, skipping page numbers and headers. Keep chapter titles, body text, dialogue.
Extract metadata for file naming:
/path/我的世界/chapters/file.pdf → 我的世界)*-XX.pdf or content like 第X章 (e.g., 我的世界-03.pdf → 03)第3章：迷宫里的真心话 → 迷宫里的真心话)If voice_id provided: Use the specified voice.
If voice_id not provided: Auto-select based on content keywords:
| Content Keywords | Voice ID |
|---|---|
| 童话、儿童、小朋友、冒险 | Chinese (Mandarin)_Cute_Spirit |
| 言情、爱情、浪漫、甜蜜 | Chinese (Mandarin)_Sweet_Lady |
| 科幻、悬疑、历史、战争 | Chinese (Mandarin)_Gentleman |
| 新闻、报告、公告 | Chinese (Mandarin)_News_Anchor |
| Default | Chinese (Mandarin)_Gentleman |
For complete voice list, see references/voices.md.
mcp__MiniMax__text_to_audio:
text: <extracted_text>
voice_id: <selected_voice_id>
output_directory: <audiobook subdirectory in story folder>
language_boost: "Chinese"
speed: 1
After MiniMax generates the MP3, rename it to follow the naming convention:
<STORY_NAME>_<CHAPTER_NUMBER>_<CHAPTER_TITLE>.mp3
Examples:
我的世界_03_迷宫里的真心话.mp3文明的最后一个变量_01_第一次接触.mp3Rename command:
mv "<generated_file>.mp3" "<output_directory>/<STORY_NAME>_<CHAPTER_NUMBER>_<CHAPTER_TITLE>.mp3"
Report the final MP3 path with the properly formatted filename.
| Use Case | Voice ID |
|---|---|
| Audiobook (male) | Chinese (Mandarin)_Gentleman |
| Audiobook (female) | Chinese (Mandarin)_Soft_Girl |
| Children's story | Chinese (Mandarin)_Cute_Spirit |
| News/Formal | Chinese (Mandarin)_News_Anchor |
Full voice reference: references/voices.md