speak

Convert input text to spoken audio using the Kokoro TTS engine.

Updated Feb 22, 2026

Search Tags:#audio #tts #speech #kokoro #read aloud

Ready to run

npx skills add https://github.com/rahulrajaram/rahulskills --skill speak-rahulrajaram

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: speak
Source: https://github.com/rahulrajaram/rahulskills/tree/main/skills/speak
Command: npx skills add https://github.com/rahulrajaram/rahulskills --skill speak-rahulrajaram

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires kokoro_voice, and includes scripts (resource) components.

What problem does it solve?

This Skill allows you to have text read aloud using an AI-powered Text-to-Speech (TTS) engine, making information more accessible and engaging.

Core Features & Use Cases

Spoken Output: Converts provided text or the last AI response into audible speech.
Customizable Voice: Uses the Kokoro TTS engine with a specific voice ('af_heart').
Use Case: Have the AI read out important meeting summaries, complex instructions, or creative writing pieces.

Quick Start

Use the speak skill to read the following sentence out loud: "Hello, this is a test of the text-to-speech skill."

Frequently Asked Questions about speak

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

FAQPage Schema

How do I read text aloud from an AI response using text-to-speech?▼

To read text aloud, this Skill converts input text or the AI's last conversational response into spoken audio using the Kokoro TTS engine. It synthesizes the provided arguments into audible speech for immediate playback.

Can I use Kokoro TTS to convert custom text into speech?▼

Yes, you can use Kokoro TTS to convert custom text into speech by passing your specific text as an argument. The Skill processes the provided input and generates synthesized audio output using the 'af_heart' voice.

What do I need to install to generate spoken audio from text?▼

To generate spoken audio from text, you need the 'kokoro_voice' Python library installed. This dependency is required for the Skill to execute text-to-speech synthesis and audio playback successfully.

Does the text-to-speech engine support different voices?▼

The text-to-speech engine currently uses a specific customizable voice named 'af_heart' from the Kokoro TTS engine. The metadata does not indicate support for switching to other voice profiles at this time.

What is the best way to have meeting summaries read out loud?▼

The best way to have meeting summaries read out loud is to pass the summary text as an argument to this Skill. It leverages the Kokoro TTS engine to synthesize the text into audible speech for playback.

Are there limitations when using Kokoro for read aloud tasks?▼

A limitation of using Kokoro for read aloud tasks is the dependency on the 'kokoro_voice' Python library for synthesis and playback. Additionally, it appears to be restricted to a single voice profile, 'af_heart', based on current configurations.