sag

Convert text to natural-sounding speech via ElevenLabs with a mac-style say UX.

9|2|Updated Mar 12, 2026
One-click install
npx skills add https://github.com/hongmaple0820/agent-academy --skill sag-hongmaple0820
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/hongmaple0820/agent-academy/tree/main/skills/others/sag
Command: npx skills add https://github.com/hongmaple0820/agent-academy --skill sag-hongmaple0820

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables expressive, high-quality speech output by interfacing with ElevenLabs TTS and providing a mac-style say UX for smooth, natural audio playback to AI agents.

Core Features & Use Cases

  • Voice selection & playback: choose from ElevenLabs voices and render natural speech for agent responses.
  • API-key driven: authenticates via ELEVENLABS_API_KEY or SAG_API_KEY to access TTS.
  • Delivery controls: supports basic pronunciation tweaks and pacing for clear narration.

Quick Start

Speak a sample text to generate audio with sag.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I convert text to natural-sounding speech using ElevenLabs?

To convert text to natural-sounding speech using ElevenLabs, you provide your text and an API key to generate high-quality audio output with selectable voices for expressive playback.

Do I need an ElevenLabs API key to generate voice audio?

Yes, you need an API key to generate voice audio. You must provide either an ELEVENLABS_API_KEY or a SAG_API_KEY to authenticate your text-to-speech requests and access playback features.

Can I select different voices for text-to-speech playback?

Yes, you can select different voices for text-to-speech playback. The system supports choosing from various ElevenLabs voices to render natural speech tailored for agent responses and narrations.

What is the best way to add expressive voice output to an interactive assistant?

The best way to add expressive voice output to an interactive assistant is using a mac-style say UX interface that supports natural audio playback, voice selection, and basic pronunciation pacing controls.

Does text-to-speech with ElevenLabs support pronunciation tweaks and pacing controls?

Yes, text-to-speech with ElevenLabs supports pronunciation tweaks and pacing controls. These delivery modifiers allow you to adjust pacing and pronunciation for clear, expressive narration.