sag

Convert text to speech via ElevenLabs with a macOS-style command-line interface.

93|20|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/seedprod/openclaw-prompts-and-skills --skill sag-seedprod
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/seedprod/openclaw-prompts-and-skills/tree/main/.claude/skills/sag
Command: npx skills add https://github.com/seedprod/openclaw-prompts-and-skills --skill sag-seedprod

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a convenient way to convert text into speech using ElevenLabs' advanced TTS technology, mimicking the familiar user experience of macOS's 'say' command.

Core Features & Use Cases

  • Text-to-Speech Conversion: Generate natural-sounding speech from text input.
  • Voice Customization: Select from various ElevenLabs voices and models for different speech styles.
  • Pronunciation and Delivery Control: Fine-tune speech output with pronunciation rules and special audio tags for emphasis and emotion.
  • Use Case: Generate voice responses for a chatbot, create audio versions of articles, or add voiceovers to presentations.

Quick Start

Use the sag skill to say "Hello there" in a 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 from the command line?

You can convert text to speech by using ElevenLabs TTS technology through a macOS-style command line interface. This allows you to generate natural-sounding speech from text input and supports local playback and audio file generation.

Do I need an ElevenLabs API key to generate text-to-speech audio?

Yes, an ElevenLabs API key is required for authentication and service access to perform text-to-speech conversion. You must provide this key to utilize the various speech models and customization options available.

Can I customize voices and speech delivery when using text-to-speech?

Yes, voice customization allows you to select from various ElevenLabs voices and models. You can fine-tune speech output with pronunciation rules and special audio tags to control emphasis and emotion for different speech styles.

What is the best way to create audio versions of articles or voiceovers for presentations?

Using a macOS-style say command interface with ElevenLabs TTS provides a convenient way to generate voiceovers for presentations or audio versions of articles. It enables natural-sounding speech generation and local audio file output.

Does the macOS say command interface support different ElevenLabs speech models?

Yes, the macOS-style command-line interface supports various ElevenLabs speech models and customization options. This allows you to select different voices and fine-tune pronunciation and delivery for your specific text-to-speech needs.