session-tts

A Claude Code add-on that reads responses and progress updates aloud using a different Japanese voice for each session on Apple Silicon Macs.

In plain words
What is it for?
Use it for spoken responses, progress narration, and adjustable text-to-speech volume during Claude Code sessions.
Why use it?
It lets you follow the coding agent without constantly watching the terminal, including while tasks change stages.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add lacolaco/claude-plugins
agentmods
npx agentmods add plugins/lacolaco/claude-plugins/session-tts
Clone the repo
git clone --depth 1 https://github.com/lacolaco/claude-plugins

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

session-tts 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 yesterday.

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.

session-tts/.claude-plugin/plugin.json · 12 lines

What it actually says

{
  "name": "session-tts",
  "description": "Read Claude Code responses aloud locally with a different Japanese voice per session. Instructs Claude to deliver mid-turn progress narration via a synchronous Bash call into the say adapter, plus a TodoWrite hook that nudges narration at task transitions. Permission prompts include the workspace name. ON by default; configurable via SESSION_TTS_ENABLED and SESSION_TTS_VOLUME env vars in settings.json; /session-tts:tts and /session-tts:volume for runtime overrides. Engine and models are managed automatically. Apple Silicon only.",
  "version": "0.12.0",
  "author": {
    "name": "Suguru Inatomi"
  },
  "repository": "https://github.com/lacolaco/claude-plugins",
  "license": "MIT",
  "keywords": ["tts", "voice", "japanese", "session", "macos", "apple-silicon"]
}
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. yesterday First seen · 12 lines scan A 4c35f26cfba1

Subscribe to this mod's changes

session-tts is a plugin published in the GitHub repository lacolaco/claude-plugins (5 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.