audiobook-production
Produce full-length audiobooks and long-form narration with generative voice tools. Use when the task is to turn a manuscript or long text into hours of spoken audio: preparing the manuscript for narration (front/back matter, footnotes, tables, dialogue), casting a single narrator or full cast, controlling pronunciation and voice consistency across a whole book, running a proofing/QC listen, meeting a retailer's technical delivery specs (RMS, peak, noise floor, room tone, chapterized files, metadata), and choosing a distribution route under each platform's current AI-narration policy. Not f
Profile →npx skills add calesthio/generative-media-skills --skill audiobook-production --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
It instructs an agent to manage full-length audiobook production using generative voice tools. It covers preparing manuscripts for narration (front/back matter, footnotes, tables, dialogue), casting a narrator or full cast, ensuring voice consistency across the book, conducting a proofing/QC listen, meeting technical delivery specs (RMS, peak, noise floor, room tone, chapterized files, metadata), and choosing a distribution route aligned with platform AI-narration policies. It explicitly excludes short TTS clips, single-line voiceover, podcast production, or captioning existing video.
How it works
The skill emphasizes hour-scale production as a craft, not short-clip generation. It advises selecting a production route before touching the manuscript:
- Human narration
- Author/producer-driven generative narration
- Platform auto-narration Then it provides manuscript preparation steps, including decisions about front/back matter, handling footnotes, tables, and dialogue attribution, and building a pronunciation lexicon. It prescribes chunking and per-chapter architecture to enable QC checkpoints, consistent pacing, and per-chapter files. It details pronunciation control via a book-wide lexicon and SSML overrides, and notes homographs require context-specific overrides. It mandates proofing the entire audiobook at normal speed and logs error types for fixes (mispronunciations, homographs, skipped text, inserted text).
When to use it
Use when turning manuscript or long text into hours of spoken audio, and when you need structured chapterized files with consistent narration, metadata, and retailer-ready delivery, across hour-scale projects. Not intended for short clips, single-line voiceover, or captioning existing video.
What it can touch
The skill references usage of SSML, a pronunciation dictionary/lexicon, per-chapter generation, and per-chapter file organization. It implies handling metadata, chapterization, and delivery specs, but does not enumerate executable tools beyond mentioning generic generative voice capabilities and per-chapter regeneration.
Caveats
The skill notes that platform policies and delivery specs are volatile and vary by retailer; it cautions that AI narration platforms may ban or restrict usage. It labels content as craft and provider-neutral, avoids brand-specific claims, and requires maintaining a living pronunciation lexicon across titles.
# Audiobook production An audiobook is not a long TTS clip. It is a **structured deliverable of many chapterized files**, each of which must pass an automated loudness/noise gate, carry the right metadata, and sound like the same performer that opened Chapter 1. The problems that dominate this work — voice drift over ten hours, a proper noun mispronounced 40 times, a footnote that makes no sense r
What does the audiobook-production skill do?
Produce full-length audiobooks and long-form narration with generative voice tools. Use when the task is to turn a manuscript or long text into hours of spoken audio: preparing the manuscript for narration (front/back matter, footnotes, tables, dialogue), casting a single narrator or full cast, controlling pronunciation and voice consistency across a whole book, running a proofing/QC listen, meeting a retailer's technical delivery specs (RMS, peak, noise floor, room tone, chapterized files, metadata), and choosing a distribution route under each platform's current AI-narration policy. Not f
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill audiobook-production --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.