sag

Generate speech from text using ElevenLabs TTS with local playback.

Updated Feb 16, 2026
One-click install
npx skills add https://github.com/RobbyMo81/assistantrobby --skill sag-robbymo81
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/RobbyMo81/assistantrobby/tree/main/skills/sag
Command: npx skills add https://github.com/RobbyMo81/assistantrobby --skill sag-robbymo81

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Sag provides high-quality ElevenLabs text-to-speech with local playback, delivering a native macOS-style voice experience for applications and assistants.

Core Features & Use Cases

  • Local playback of ElevenLabs voices from plain text input.
  • Voice selection and adjustable delivery cues to tailor expressiveness.
  • Quick previews and integration hooks for apps, chatbots, and assistants.

Quick Start

Speak a phrase to hear it rendered locally with sag.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I generate speech from text using ElevenLabs TTS on macOS?

You can generate speech from text on macOS by providing a plain text prompt, which the Skill renders using ElevenLabs TTS. It plays the resulting audio locally, delivering a native macOS-style voice experience without requiring external playback software.

Do I need an API key to use ElevenLabs text-to-speech with local playback?

Yes, an API key is required for ElevenLabs text-to-speech local playback. You must configure either an ELEVENLABS_API_KEY or a SAG_API_KEY environment variable to authenticate the TTS requests and render audio locally.

Can I select different voices and adjust delivery cues for ElevenLabs TTS?

Yes, you can select different voices and adjust delivery cues for ElevenLabs TTS. The Skill supports voice selection and effects tags, allowing you to tailor the expressiveness of the generated audio for quick prompts and audio previews.

What is the best way to add voice responses to a macOS-inspired assistant?

The best way to add voice responses to a macOS-inspired assistant is to use a TTS Skill with integration hooks for apps and chatbots. It renders ElevenLabs audio locally from plain text, maintaining a native user experience across applications.

Does ElevenLabs text-to-speech work across different apps on macOS?

Yes, ElevenLabs text-to-speech works across different apps on macOS. The Skill provides a macOS-inspired UX with integration hooks, enabling quick voice responses and audio previews to be generated and played locally within various applications and assistants.