Convert technical documents into TTS-optimized audiobooks with narrative synthesis.
npx skills add https://github.com/Motium-AI/claude-code-toolkit --skill audiobook
Please help me install this Agent Skill. Skill: audiobook Source: https://github.com/Motium-AI/claude-code-toolkit/tree/main/config/skills/audiobook Command: npx skills add https://github.com/Motium-AI/claude-code-toolkit --skill audiobook
This Skill converts technical documents into engaging, long-form audiobooks optimized for text-to-speech. It uses a four-agent heavy analysis workflow, targeted narrative synthesis, and production-ready formatting to save time and improve accessibility.
Use the skill to transform a set of documents into a production-ready audiobook by issuing a request like "Create an audiobook from technical documents."
High-intent search queries and answers about installing and using this skill.
To convert technical documents into TTS-ready audiobooks, provide source files like API docs or whitepapers to trigger a four-agent heavy analysis workflow, which outputs a single narrative synthesis optimized for text-to-speech narration.
The generated audiobook satisfies strict production constraints, yielding a total length of 7,000 to 10,000 words, divided into chapters of 800 to 1,200 words each, alongside a 90-word preamble.
Multi-agent analysis improves audiobook narrative synthesis by orchestrating multiple perspectives to extract essential insights from technical manuals, crafting a compelling arc and ensuring stop-slop enforcement for a human-like cadence.
Yes, you can use API references, technical manuals, and whitepapers to create an onboarding audiobook. The process applies targeted narrative synthesis and TTS optimization to transform dense technical documentation into engaging audio.
Yes, the audiobook generation applies stop-slop enforcement to remove AI writing tropes and rhythm issues. This ensures the text-to-speech output maintains a characterful, human-like narration style without awkward phrasing.
The output includes a guide for production quality and stop-slop enforcement, designing specific pacing, pauses, and pronunciation for natural text-to-speech narration across the entire 7,000 to 10,000 word audiobook.
agentic-inExtracts searchable text from scanned and image-heavy documents via OCR processing.
dnvriendConvert text to speech via the ElevenLabs API with CLI options.
ldmrepoGenerate personalized meditation scripts and TTS audio in selectable durations.
PrettiFlowExtract and condense web articles, PDFs, files, and YouTube transcripts into summaries.
