AI Audiobook Generator Skill

English | 简体中文 | 日本語

👉 See also AI Podcast Voiceover Skill

Turn a final manuscript or course text into ordered chapter audio with one narrator, a representative sample chapter first, and focused refinements, from inside Claude Code, Cursor, Codex, Windsurf, Cline, or OpenClaw.

Important

Rendering needs a Beatra account and uses credits. The skill itself is free to install.

Listing cover for The Lighthouse Keeper's Almanac, an invented novella, showing a storm-battered lighthouse lit by a single candle. AI-generated with Beatra.

This repository is published automatically from beatra-ai/beatra-skills. Report issues there.

Install

With the skills CLI:

npx skills add beatra-ai/ai-audiobook-generator-skill

As a Claude Code plugin:

claude plugin marketplace add beatra-ai/ai-audiobook-generator-skill
claude plugin install ai-audiobook-narration@ai-audiobook-generator-skill

As a Codex plugin:

codex plugin marketplace add beatra-ai/ai-audiobook-generator-skill
codex plugin add ai-audiobook-narration@ai-audiobook-generator-skill

As a GitHub Copilot CLI plugin:

copilot plugin marketplace add beatra-ai/ai-audiobook-generator-skill
copilot plugin install ai-audiobook-narration@ai-audiobook-generator-skill

As a Gemini CLI extension:

gemini extensions install https://github.com/beatra-ai/ai-audiobook-generator-skill

With the GitHub CLI:

gh skill install beatra-ai/ai-audiobook-generator-skill ai-audiobook-narration

Or clone this repository and copy skills/ai-audiobook-narration into ~/.claude/skills/ for Claude Code, ~/.cursor/skills/ for Cursor, ~/.agents/skills/ for Codex, ~/.codeium/windsurf/skills/ for Windsurf, ~/.cline/skills/ for Cline, or ~/.openclaw/skills/ for OpenClaw.

Or paste this into your agent:

Install the ai-audiobook-narration skill from https://github.com/beatra-ai/ai-audiobook-generator-skill (folder skills/ai-audiobook-narration), then follow its SKILL.md to connect my Beatra account.

Examples

▶ Listen (MP3)

Representative sample chapter from an invented novella, The Lighthouse Keeper's Almanac, read in 43 seconds by one narrator voice with dialogue and recurring names. AI-generated with Beatra.

Ask your agent:

Narrate ./almanac-manuscript.md as an audiobook with one narrator voice. Start with a representative sample from chapter one so I can check the pacing and how the names are pronounced before you do the rest.

Prompt:

The Lighthouse Keeper's Almanac. Chapter one: the night the lamp went dark.

On the ninth of November, at a quarter past two in the morning, the lamp at Gullrock Point went out. Maren Holloway had kept that light for eleven winters, and it had never once failed her.

She climbed the hundred and six iron steps with a candle cupped in her hand. Outside, the wind worked at the glass like a patient thief.

"Tobias," she called down the stairwell, "bring the spare wick, and bring the almanac."

Her nephew's voice came up thin and frightened. "The almanac says nothing about tonight, Aunt Maren."

"Then we shall write tonight into it," she said, and struck the match.

Technical Specifications & Output Limits

As of 2026-10-18. Live list: https://docs.beatra.ai/en/docs/models

• Uploads — up to 100 MB per file; the per-model input limits below also apply
• Text to speech — 2 models (MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo); FLAC, MP3, OPUS, PCM, WAV; 40 languages; sample rates 8, 16, 22.05, 24, 32, 44.1 kHz; up to 50000 characters per request
  • Languages (ISO 639 codes): zh, yue, en, es, fr, ru, de, pt, ar, it, ja, ko, id, vi, tr, nl, uk, th, pl, ro, el, cs, fi, hi, bg, da, he, ms, fa, sk, sv, hr, fil, hu, no, sl, ca, nn, ta, af
• Voice cloning — 1 model (MiniMax Voice Clone); sample 10–300 s, up to 20 MB; consent attestation required
• Text to image — 10 models (Qwen Image 2.0 Fast, Qwen Image 3.0, Qwen Image 3.0 Pro, GPT Image 2.5 Flare, GPT Image 2.5 Sunburst, GPT Image 2, Wan Image 2.7 Fast, Qwen Image 2.0 Pro, Wan Image 2.7 Pro, MiniMax Image 01 Live); PNG; up to 4 images per request; canvas up to 16.8 MP
  • 16.8 MP (4K tier): Wan Image 2.7 Pro (up to 4 images per request); GPT Image 2.5 Flare, GPT Image 2.5 Sunburst, GPT Image 2 (1 image per request)

Why use Beatra instead of calling model APIs directly

• One account for every model this skill uses — Text to speech 2; Voice cloning 1; Text to image 10 (MiniMax Speech 2.8 HD, MiniMax Speech 2.8 Turbo, MiniMax Voice Clone, Qwen Image 2.0 Fast, Qwen Image 3.0, Qwen Image 3.0 Pro, GPT Image 2.5 Flare, GPT Image 2.5 Sunburst, GPT Image 2, Wan Image 2.7 Fast, Qwen Image 2.0 Pro, Wan Image 2.7 Pro, MiniMax Image 01 Live) (as of 2026-10-18), behind one Beatra sign-in; no keys from individual model providers to manage.
• You decide what gets paid for — Paid renders run only when you ask for that exact render or approve its card, which shows the live credit estimate.
• Direction before rendering — the skill plans, directs, and reviews the work, then renders it on Beatra.
• Files you can verify — every file under skills/ matches the release archive on cdn.beatra.ai byte for byte, checked by SHA-256 before each push.
• Updates you control — no self-updater; update with the tool you installed it with.
• Runs in your agent — Claude Code, Cursor, Codex, Windsurf, Cline, OpenClaw.

What you get

• Plan the listening order first — Organize chapters and natural segment breaks before narration begins, keeping each part easy to identify and review.
• Cast for the whole book — Choose one available narrator voice for long-form comfort, then keep the selected pace and pronunciations consistent across chapters.
• Pilot before the full batch — Hear one representative chapter, compare the voice and pacing, and view the estimate for the remaining work.

Use cases

• Novel and serial narration — Carry a familiar narrator voice and agreed readings across dialogue, exposition, recurring characters, and later chapters.
• Nonfiction audiobooks — Prepare names, numbers, terms, and chapter structure so complex source text becomes easier to listen to in sequence.
• Course narration — Turn ordered lessons into chapter audio with stable delivery and focused review of technical pronunciation.
• Audiobook sample chapters — Create a meaningful pilot for narrator, pace, pronunciation, and format review before expanding production.

FAQ

What do I need to start?

Bring final readable text for at least one representative chapter, the intended language or dialect, chapter order, and any important pronunciation notes.

Can I hear a sample before narrating the whole book?

Yes. The workflow starts with a representative pilot, then shows the remaining chapter count and current price estimate before you decide whether to continue.

Will every chapter use the same narrator voice?

The selected narrator voice and narration style carry across the book, with listening review keeping pronunciation and chapter-to-chapter delivery consistent.

What does this workflow deliver?

It turns final readable text into ordered chapter audio with one consistent narrator, organized for editing, translation review, multi-cast mixing, M4B assembly, mastering, and publishing.

Updates and security

Since the 2026-10 release, this skill contains no self-updater: it runs only the files you installed and never replaces them on its own. Update it with the tool you installed it with — npx skills update ai-audiobook-narration or gh skill update ai-audiobook-narration. Details: references/updates-and-security.md inside the skill.

License

MIT-0 — free to use, modify, and redistribute, including commercially. No attribution required. Same terms as these skills carry on ClawHub.

Links

• Website — https://beatra.ai?utm_source=github&utm_medium=flagship&utm_campaign=ai-audiobook-generator-skill
• Docs — https://docs.beatra.ai?utm_source=github&utm_medium=flagship&utm_campaign=ai-audiobook-generator-skill
• Console — https://console.beatra.ai
• For AI agents — https://beatra.ai/llms.txt (index) · https://beatra.ai/llms-full.txt (every skill in one file)