tts-say

Unify macOS say and ElevenLabs sag through a single command-line interface.

3|2|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/yoonhwan/ai-feature-pack --skill tts-say
Or copy as Structured Prompt for Agentβ–Ό
Please help me install this Agent Skill.
Skill: tts-say
Source: https://github.com/yoonhwan/ai-feature-pack/tree/main/feature-pack/tts-say/skill
Command: npx skills add https://github.com/yoonhwan/ai-feature-pack --skill tts-say

SYSTEM DOCUMENTATION & REQUIREMENTS

πŸ’‘ This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Using separate command-line tools for macOS built-in text-to-speech and ElevenLabs cloud TTS requires learning two different command sets and managing separate configurations, which creates unnecessary friction for developers and content creators who need quick, reliable voice output.

Core Features & Use Cases

  • Unified TTS Interface: Single tts-say command that works with both macOS say and ElevenLabs sag, no need to switch between tools or remember different syntax.
  • Persistent Configuration: Save default engine, voice, language, and audio settings once, then use them across all TTS requests without repeating flags.
  • Common Use Cases: Get audio alerts for build/test completion in development workflows, generate TTS audio files for content, list and select voices across both engines, and integrate voice output into AI agent and vibe-coding workflows.

Quick Start

Use the tts-say skill to speak the text "λΉŒλ“œκ°€ μ™„λ£Œλ˜μ—ˆμŠ΅λ‹ˆλ‹€" aloud using your default configured TTS engine.

Frequently Asked Questions about tts-say

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

FAQPage Schema
How do I use a single command for text-to-speech on macOS and ElevenLabs?β–Ό

To unify text-to-speech on macOS and ElevenLabs, you can use a single CLI command that wraps both the built-in macOS say and ElevenLabs sag engines, eliminating the need to learn separate command syntaxes.

Can I save default voice and language settings for CLI text-to-speech?β–Ό

Saving default voice and language settings for CLI text-to-speech is supported through persistent configuration, allowing you to store your preferred engine, voice, and audio settings once for all future requests.

How do I get audio notifications for build or test completion on macOS?β–Ό

You can get audio notifications for build or test completion on macOS by integrating a CLI text-to-speech command into your development workflow to speak completion alerts aloud.

What's the best way to generate multilingual TTS audio files from the command line?β–Ό

Generating multilingual TTS audio files from the command line is best handled by a unified CLI that supports cross-engine voice discovery and audio file export across macOS and cloud platforms.

Does the tts-say command support both real-time playback and audio file export?β–Ό

The tts-say command supports both real-time audio playback and audio file export, applying to developer workflows and content creation pipelines requiring consistent voice output.

Can AI agents use a single interface for consistent voice output across local and cloud TTS?β–Ό

AI agents can achieve consistent voice output across local and cloud TTS engines by using a unified command-line interface that applies automatic engine selection and cross-engine voice discovery.