read-aloud

read-aloud is a skill for Claude Code, Codex from Ckokoski/AuthorAgent. It costs 25 tokens per session (1,222 once invoked), scanned A, original, MIT.

A text-to-speech skill that turns manuscripts into spoken audio using Piper, a free open-source speech engine. It can run locally and offline.

In plain words
What is it for?
Use it to proofread manuscripts by ear and check the sound and rhythm of prose, dialogue, and chapters.
Why use it?
Listening reveals awkward phrasing, long sentences, repeated words, unnatural dialogue, and pacing problems that are easy to miss while reading.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to proofread manuscripts by ear and check the sound and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ckokoski/authoragent/read-aloud
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ckokoski/AuthorAgent --skill read-aloud
Clone the repo
git clone --depth 1 https://github.com/Ckokoski/AuthorAgent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for read-aloud

README.md
[![agentmods](https://agentmods.dev/badge/skills/ckokoski/authoragent/read-aloud.svg)](https://agentmods.dev/skills/ckokoski/authoragent/read-aloud)
Your own site
<a href="https://agentmods.dev/skills/ckokoski/authoragent/read-aloud"><img src="https://agentmods.dev/badge/skills/ckokoski/authoragent/read-aloud.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,222 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.01222
Opus 5 $0.00013 $0.00611
Sonnet 5 $0.00005 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured 7d ago against content hash 722938cf51df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

read-aloud scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/_archived/premium/read-aloud/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read Aloud — Premium Skill

Turn your manuscript into speech using free, open-source text-to-speech. Hear your prose the way a reader would — because the ear catches what the eye misses.

Why Read Aloud?

Every professional editor will tell you: read your work aloud. It reveals:

  • Awkward phrasing that looks fine on screen
  • Sentences that are too long to speak in one breath
  • Repeated words your eye skips but your ear catches
  • Dialogue that sounds unnatural when spoken
  • Pacing problems that only rhythm reveals
  • Tongue-twisters and consonant clusters

This skill automates that process with natural-sounding AI voices.

Engine: Piper TTS

AuthorClaw uses Piper TTS — a fast, free, open-source text-to-speech engine:

  • MIT licensed — completely free, no API costs, no subscriptions
  • Runs locally — your manuscript never leaves your machine
  • CPU-only — no GPU required (works on any computer)
  • Natural voices — neural network voices, not robotic
  • Fast — generates audio faster than real-time
  • Offline — works without internet

Setup (One-Time)

# Install Piper (included in AuthorClaw setup wizard)
pip install piper-tts

# Download a voice model (~100MB each)
# AuthorClaw will prompt you to pick one on first use

Available Voice Styles

  • en_US-lessac-medium — Clear American narrator (recommended for fiction)
  • en_US-libritts-high — High quality, natural cadence
  • en_GB-alba-medium — British narrator
  • en_US-amy-medium — Female American voice
  • Multiple languages available for translated works

Read Modes

Chapter Read

Read an entire chapter from your project:

read chapter 7
  • Generates audio file saved to workspace/audio/
  • Plays through system audio
  • Shows word-by-word highlighting in dashboard (if connected)

Selection Read

Read a specific passage:

read aloud [paste or select text]
  • Quick listen for a specific section
  • Great for testing dialogue flow

Dialogue Mode

Reads with distinct pausing for dialogue vs. narration:

  • Slight pause before and after quoted speech
  • Different cadence for dialogue vs. description
  • Helps you hear if your dialogue sounds natural

Read the full file on GitHub · 161 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 161 lines · 25 tokens per session scan A 722938cf51df

Subscribe to this mod's changes

read-aloud is a skill published in the GitHub repository Ckokoski/AuthorAgent (103 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,222 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

capcut-theme-video

A guide for creating one-tap videos in CapCut, a video-editing app, from photos on an Android device. It specifies how to select photos and place them in the required album before making a video.

OPPO-Mente-Lab/X-OmniClaw · 80 tokens

gallery-memory

Sync gallery images into long-term memory files and rebuild the user profile from photo-derived memories.

OPPO-Mente-Lab/X-OmniClaw · 21 tokens

caption-assistant

Writes captions, accessibility alt text, and short image or page descriptions tailored to the visible content and audience. Use when the user asks to "describe this image", "write alt text", "caption this", or needs screen reader text, a11y descriptions, image descriptions, or social captions.

surfmind-space/awesome-surfmind · 63 tokens

florist

Expert-level Florist skill with deep knowledge of floral design, bouquet construction, event decoration, and flower care. Transforms AI into a master florist with 15+ years of experience in retail floristry, event florals, and artistic installations. Use when: crafts, floristry, flower-arrangement, bouquet-design…

theneoai/awesome-skills · 0 tokens

instrument-maker

Expert-level Traditional Instrument Maker skill with deep knowledge of Chinese and Asian traditional instrument making. Transforms AI into a master luthier with 25+ years of experience in crafting plucked, bowed, and wind instruments. Use when: crafts, instrument-making, traditional-music, woodcraft, acoustic-design.

theneoai/awesome-skills · 0 tokens

jewelry-designer

Expert jewelry designer creating original designs from concept to finished piece. Use when designing custom jewelry, selecting gemstones, planning manufacturing processes, or selecting materials.

theneoai/awesome-skills · 34 tokens