audiobook-maker

Split long text into chaptered TTS audio segments and save them.

37|4|Updated Mar 31, 2026
One-click install
npx skills add https://github.com/MerkyorLynn/Lynn --skill audiobook-maker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audiobook-maker
Source: https://github.com/MerkyorLynn/Lynn/tree/main/plugins/tts-bridge/skills/audiobook-maker
Command: npx skills add https://github.com/MerkyorLynn/Lynn --skill audiobook-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts long articles, novels, and reports into ready-to-listen audiobook audio, so users can consume content hands-free.

Core Features & Use Cases

  • Long-Text Chunking: Splits text longer than 3000 Chinese characters into natural paragraph blocks (each block ≤ 2500 characters).
  • Chapter-by-Chapter TTS Generation: Generates audio per chunk using tts_speak and names files with ordered chapter numbers (chapter_01, chapter_02, ...).
  • One-Click Delivery: Saves all generated audio into the桌面 audio/ subdirectory and notifies the user with total duration and the file list.
  • Speed Tuning by Content Type: Recommends different speech speeds and tone styles for novels/literary, reports/news, and short social content.

Quick Start

Ask Lynn to generate an audiobook by reading this long text and saving the chapters to your desktop audio folder.

Frequently Asked Questions about audiobook-maker

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert long text into listenable audiobook chapters?

To convert long text into listenable audiobook chapters, the audiobook-maker splits content over 3000 characters into natural paragraph blocks under 2500 characters. It sequentially generates audio per chunk and saves ordered chapter files to a desktop audio directory.

Can I use text to speech for multiple chapters without manual splitting?

Yes, text to speech generation handles multiple chapters automatically by splitting long text into blocks of 2500 characters or less. It calls TTS sequentially per chunk and names files with ordered chapter numbers.

What is the best way to generate TTS audio for novels and reports?

The best way to generate TTS audio for novels and reports is applying speed tuning by content type. It recommends different speech speeds and tone styles for literary works, news reports, and short social content.

Does text to speech chunking work with content over 3000 characters?

Text to speech chunking works with content over 3000 characters by automatically dividing the text into smaller paragraph blocks. Each block is kept at or under 2500 characters to ensure sequential TTS processing.

How does the desktop audio notification report generated TTS files?

The desktop audio notification reports generated TTS files by sending a notification after all audio chunks are saved. It reports the total duration of the audiobook and provides a complete file list of the generated chapters.