skills.rest
MDGrey33
MDGrey33COMMUNITY
Explore all skills by this author →
WebsiteGitHub

say-it

Speak markdown, files, or inline text aloud using Kokoro text-to-speech.

2|Updated Feb 23, 2026
Search Tags:#claude code#text-to-speech#tts#voice synthesis#kokoro#audio playback
One-click install
npx skills add https://github.com/MDGrey33/memnyx --skill say-it
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: say-it
Source: https://github.com/MDGrey33/memnyx/tree/main/.claude/skills/say-it
Command: npx skills add https://github.com/MDGrey33/memnyx --skill say-it

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns written content into spoken audio so you can listen to responses, files, or notes instead of reading them on screen.

Core Features & Use Cases

  • Local text-to-speech playback: Uses Kokoro for offline speech generation without sending content to external services.
  • Flexible input handling: Speaks the latest response, a selected section, a file path, or inline text.
  • Voice and pacing control: Supports different voices and cleans markdown-style text so the spoken output sounds natural.
  • Use case: A user asks to hear a long explanation while multitasking, and the Skill reads it aloud in the background.

Quick Start

Ask the say-it skill to read the latest response aloud after the Kokoro voice stack is installed.

Frequently Asked Questions about say-it

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I hear Claude Code responses aloud instead of reading them?▼

You can hear Claude Code responses aloud by using offline text-to-speech playback that converts markdown, files, or inline text into spoken audio for local listening.

Can I generate speech locally from markdown files without sending data to external services?▼

Yes, local text-to-speech generation uses Kokoro voice tooling to convert markdown files into spoken audio entirely offline without sending content to external services.

What do I need to set up before using text-to-speech in Claude Code?▼

You need to install the Kokoro voice stack before asking the Skill to read responses, selected sections, or user-provided text aloud for local audio playback.

Does text-to-speech playback work in the background while I continue coding?▼

Yes, background playback is supported so you can listen to long explanations or notes aloud while multitasking and continuing to work in Claude Code.

How does offline voice synthesis handle markdown formatting for natural speech?▼

Offline voice synthesis cleans markdown-style text before processing so the spoken output sounds natural and avoids reading formatting syntax aloud.

Can I choose different voices for text-to-speech playback?▼

Yes, simple voice selection is supported alongside voice and pacing control, allowing you to choose different voices for local offline text-to-speech playback.

Related Skills

Explore More Content & Communication Skills→
malue-aimalue-ai
36

kokoro-tts

Generate local text-to-speech audio with Kokoro TTS engine.

Official
Intermediate
WarrenZhu050413WarrenZhu050413
7

generating-tts

Generate and play multilingual text-to-speech audio with adjustable voices and speeds.

Community
Intermediate
elevenlabselevenlabs
412

text-to-speech

Convert text into natural-sounding speech using ElevenLabs voice AI.

Official
Intermediate
freire19freire19

sherpa-onnx-tts

Convert text to WAV audio offline using sherpa-onnx.

Community
Basic