sag

Convert text to speech via the ElevenLabs API with local audio playback.

Updated Feb 4, 2026
One-click install
npx skills add https://github.com/lehalpaul/agents --skill sag-lehalpaul
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/lehalpaul/agents/tree/main/skills/sag
Command: npx skills add https://github.com/lehalpaul/agents --skill sag-lehalpaul

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a text-to-speech (TTS) solution using ElevenLabs, offering a user experience similar to the macOS 'say' command for local audio playback.

Core Features & Use Cases

  • ElevenLabs TTS Integration: Leverages ElevenLabs for high-quality voice generation.
  • Local Playback: Outputs audio directly for immediate listening.
  • Voice Customization: Supports various ElevenLabs models and voice IDs.
  • Pronunciation & Delivery Control: Allows for fine-tuning speech with pronunciation rules and special audio tags.
  • Use Case: Generate spoken responses for an AI assistant, create audio versions of text content, or provide voice feedback in a conversational agent.

Quick Start

Use the sag skill to speak the phrase "Hello there" with the default voice.

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 for local audio playback?

To convert text to speech, the sag Skill sends text to the ElevenLabs API and outputs audio directly for immediate local listening. It functions similarly to the macOS 'say' command but leverages ElevenLabs models for high-quality generation.

Do I need an ElevenLabs API key to generate voice audio with this text-to-speech tool?

Yes, an ElevenLabs API key is required for authentication to perform text-to-speech synthesis. You must provide this key to access ElevenLabs models and generate customizable voice output.

Can I customize the voice delivery and pronunciation in ElevenLabs text-to-speech?

You can customize ElevenLabs text-to-speech delivery by selecting various voice IDs and applying special audio tags. The tool also supports pronunciation rules to fine-tune the expressive speech output.

What is the best way to generate spoken responses for an AI assistant using ElevenLabs?

The best way to generate spoken AI assistant responses is using a Skill like sag to pass text to the ElevenLabs API. It provides local audio playback and supports customizable voice models for conversational feedback.

Does the sag text-to-speech Skill support different ElevenLabs models?

Yes, the sag text-to-speech Skill supports various ElevenLabs models and voice IDs. This allows you to choose specific voice profiles for your speech synthesis and local audio playback needs.