speak

Convert text to speech using edge-tts neural voices with macOS say fallback.

116|56|Updated Jan 18, 2026
One-click install
npx skills add https://github.com/Soul-Brews-Studio/oracle-skills-cli --skill speak
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: speak
Source: https://github.com/Soul-Brews-Studio/oracle-skills-cli/tree/main/src/skills/speak
Command: npx skills add https://github.com/Soul-Brews-Studio/oracle-skills-cli --skill speak

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This skill solves the need to read text aloud by converting text into spoken audio.

Core Features & Use Cases

  • Text-to-speech using edge-tts neural voices with optional macOS fallback
  • Voice customization via --voice, --thai, --female, and --list
  • Cross-platform usage (edge-tts on supported systems, macOS say as fallback)

Quick Start

/speak "Hello world" /speak --thai "สวัสดีครับ" /speak --voice "en-GB-RyanNeural" "Hi" /speak --mac "Hello"

Frequently Asked Questions about speak

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

FAQPage Schema
How do I convert text to speech from the command line?

Convert text to speech from the command line by passing a text string to the CLI, which processes it using edge-tts neural voices or macOS say as a fallback to generate spoken audio.

Can I use edge-tts for text-to-speech on macOS?

Yes, edge-tts for text-to-speech is supported on macOS alongside the native macOS say fallback, allowing cross-platform voice synthesis with customizable language, voice, and rate options via CLI flags.

How do I select a specific neural voice or language for speech synthesis?

Select a specific neural voice or language for speech synthesis by applying CLI flags like --voice with a specific voice name such as en-GB-RyanNeural, or --thai for Thai language text output.

Do I need edge-tts installed to use this text-to-speech skill?

You do not strictly need edge-tts installed to use this text-to-speech skill, as it supports macOS say as an automatic fallback for generating spoken audio when edge-tts is unavailable.

How can I list available voices for text-to-speech synthesis?

List available voices for text-to-speech synthesis by passing the --list flag to the CLI, which queries the underlying edge-tts or macOS say engine to return all supported voice options.

Why does my text-to-speech fallback to macOS say instead of edge-tts?

Text-to-speech falls back to macOS say instead of edge-tts when the edge-tts dependency is not installed or unavailable on your system, ensuring audio output continues using the native macOS voice synthesis engine.