sag

Convert text to natural speech using ElevenLabs TTS with voice selection.

1|1|Updated Jan 22, 2026
One-click install
npx skills add https://github.com/kelinfoxy/EZ-Homelab --skill sag-kelinfoxy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/kelinfoxy/EZ-Homelab/tree/main/docker-compose/ez-assistant/skills/sag
Command: npx skills add https://github.com/kelinfoxy/EZ-Homelab --skill sag-kelinfoxy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

sag provides an accessible, local text-to-speech solution using ElevenLabs voices, enabling quick generation of natural-sounding audio without external services for demos, accessibility, and automation.

Core Features & Use Cases

  • Voice selection across ElevenLabs models and variants
  • Local audio generation with a simple CLI for quick demos and automation
  • Easy integration into apps, dashboards, or narration tasks with pronunciation and pacing controls

Quick Start

Run sag with a sample text to generate speech.

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 speech using ElevenLabs voices from the command line?

You can convert text to speech by running sag with your text, which uses ElevenLabs TTS to generate natural-sounding audio locally. It requires an API key and supports multiple voices and model variants.

Does text-to-speech with ElevenLabs require an API key to generate audio?

Yes, generating text-to-speech audio with ElevenLabs requires an API key. sag uses this key to access natural-sounding voices and handle voice selection, pronunciation adjustments, and basic SSML-style cues.

Can I adjust pronunciation and pacing for automated narration in apps?

Yes, you can adjust pronunciation and pacing for automated narration. sag supports voice selection across ElevenLabs models and includes basic SSML-style cues for controlling speech output.

What is the best way to add accessibility aids using natural-sounding TTS?

The best way to add accessibility aids is using a local text-to-speech solution like sag. It provides a simple CLI for quick demos and generates natural-sounding audio without external services.

Are there limitations to using local text-to-speech for quick demos and automation?

Local text-to-speech for quick demos handles basic SSML-style cues and pronunciation adjustments. It requires an ElevenLabs API key and supports multiple voices, but complex SSML features may be limited.

How does Mac-style say CLI compare to other text-to-speech tools for app integration?

The sag tool provides a Mac-style say UX powered by ElevenLabs TTS, offering natural-sounding voices and easy integration into apps or dashboards. Other text-to-speech tools may lack this simple CLI interface and voice variant selection.