sag

Convert text to natural local speech via the sag command-line tool.

Updated Apr 24, 2026
One-click install
npx skills add https://github.com/frankhli843/gemmahermes --skill sag-frankhli843
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/frankhli843/gemmahermes/tree/main/skills/sag
Command: npx skills add https://github.com/frankhli843/gemmahermes --skill sag-frankhli843

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ElevenLabs text-to-speech with a mac-style say UX enables quick, natural-sounding audio generation on local machines, making voice-enabled demos and accessibility workflows effortless.

Core Features & Use Cases

  • Real-time TTS playback via sag CLI with ElevenLabs voices.
  • Local audio output for demos, accessibility prompts, and voice-enabled UIs.
  • Use Case: Narrate tutorials, read UI prompts aloud, or prototype voice personas in a desktop app.

Quick Start

Speak a sample sentence to hear it spoken aloud.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I generate natural text-to-speech audio on macOS using a command-line interface?

You can generate natural text-to-speech audio on macOS by using a command-line interface that invokes the sag tool to process text and play realistic ElevenLabs voices locally on your machine.

Can I use ElevenLabs TTS voices locally with a macOS-style say command?

Yes, you can use ElevenLabs TTS voices locally with a macOS-style say command by running the sag CLI, which integrates environment-key access and local playback for immediate audio output.

What do I need to set up before using sag for text-to-speech on macOS?

Before using sag for text-to-speech on macOS, you need to configure your ElevenLabs environment key access and ensure your local machine supports command-line audio playback integration.

How does local speech playback integration work for accessibility tools and UI demos?

Local speech playback integration works for accessibility tools by invoking the sag CLI to convert text prompts into natural ElevenLabs audio, enabling real-time voice output within desktop applications.

What is the best way to prototype voice personas for a desktop app on macOS?

The best way to prototype voice personas for a desktop app on macOS is using the sag CLI to generate realistic ElevenLabs text-to-speech audio, providing immediate local voice playback for UI testing.

Are there limitations when using sag CLI for text-to-speech on macOS?

The sag CLI for text-to-speech on macOS is limited to local playback environments and requires valid ElevenLabs environment-key access to generate natural audio output successfully.