speak

speak is a skill for Claude Code from shreyas-s-rao/claude-code-narrator. It costs 59 tokens per session (254 once invoked), scanned A, original, MIT.

A command for having the narrator read specified text aloud immediately. The narrator is a text-to-speech feature for coding-assistant responses.

In plain words
What is it for?
It is for reading user-provided text or a short summary of the assistant's latest action aloud, even when the regular narrator setting is off.
Why use it?
It allows one response or passage to be spoken without changing whether narrator output is normally enabled.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the narrator plugin — 6 skills, 6 commands, 3 hooks shipped together

Good fit It is for reading user-provided text or a short summary of the assistant's latest action aloud, even when the regular narrator setting is off.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add shreyas-s-rao/claude-code-narrator
Claude Code
/plugin install narrator

Made for: Claude Code.

Or install narrator, the plugin that ships this one along with the rest of its 6 skills, 6 commands, 3 hooks.

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 speak

README.md
[![agentmods](https://agentmods.dev/badge/skills/shreyas-s-rao/claude-code-narrator/speak/github.svg)](https://agentmods.dev/skills/shreyas-s-rao/claude-code-narrator/speak)
Your own site
<a href="https://agentmods.dev/skills/shreyas-s-rao/claude-code-narrator/speak"><img src="https://agentmods.dev/badge/skills/shreyas-s-rao/claude-code-narrator/speak/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for speak

Your own site · 80×15
<a href="https://agentmods.dev/skills/shreyas-s-rao/claude-code-narrator/speak"><img src="https://agentmods.dev/badge/skills/shreyas-s-rao/claude-code-narrator/speak.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 254 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 $0.00059 $0.00254
Opus 5 $0.00030 $0.00127
Sonnet 5 $0.00012 $0.00051
Haiku 4.5 $0.00006 $0.00025

Measured 10d ago against content hash 2a85c7b4e852, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

speak 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 10d 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/speak/SKILL.md · 31 lines

What it actually says

On-Demand Speech

Speak text aloud on demand, regardless of whether narrator is currently enabled.

Usage

If the user provides specific text to speak, pipe it directly:

echo "TEXT_TO_SPEAK" | bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/speak.sh" --force

If the user does not provide specific text, summarize the last action or response and speak that summary:

echo "SUMMARY_TEXT" | bash "${CLAUDE_PLUGIN_ROOT}/hooks/scripts/speak.sh" --force

The --force flag bypasses the enabled check, allowing speech even when narrator is turned off.

Important

  • Always use --force for on-demand speak requests
  • Keep spoken text concise -- summarize if the text is very long
  • Ensure Kokoro is installed before attempting to speak (check with python3 -c "import kokoro")
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. 10d ago First seen · 31 lines · 59 tokens per session scan A 2a85c7b4e852

Subscribe to this mod's changes

speak is a skill published in the GitHub repository shreyas-s-rao/claude-code-narrator (26 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 254 once invoked, about $0.0003 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

sitrep-panel

Keep a live local HTML report updated as you work on a task — a status board, a running "what's happening now" narrative, screenshots, and a newest-first log — served on localhost so the user can watch progress in a browser tab instead of reading the transcript. Use when the user invokes /sitrep-panel, asks for a…

dbl8005/sitrep-panel · 101 tokens

a11y-audit

Dedicated WCAG 2.2 AA/AAA accessibility audit across 10 dimensions (A1-A10) covering semantic HTML, keyboard navigation, ARIA patterns, color contrast, forms, images/media, responsive/zoom, motion/animation, reading/content, and legal compliance. Goes far beyond surface-level design-review checks with deep…

greglas75/zuvo · 147 tokens

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", or "vs best practices".

martineserios/thebrana · 37 tokens

whisperx-transcribe

Transcribes local audio/video files (meetings, interviews, podcasts, lectures, recorded calls) into a clean, speaker-labeled Markdown transcript using WhisperX, so an LLM can read and reason about a long recording without processing raw audio itself. Use this whenever the user gives you a video/audio file path (mp4…

abubakarsiddik31/whisperx-transcribe · 194 tokens

gemini-audio-tts-music

Generate music (Lyria 3) or synthesize speech (Gemini TTS, single or multi-speaker). Use for soundtracks, voiceovers, demo narration, notification sounds, or audio branding.

azmym/gemini-plugin · 42 tokens

gemini-image-gen

Generate images using Gemini's native image generation (Nano Banana) or Imagen 4. Use for UI mockups, hero images, product shots, infographic frames, or any visual content creation task.

azmym/gemini-plugin · 39 tokens