sag

Generate text-to-speech audio via ElevenLabs with local playback.

Updated Jan 20, 2026
One-click install
npx skills add https://github.com/Team-Hireal/RealChat --skill sag-team-hireal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/Team-Hireal/RealChat/tree/main/openclaw/skills/sag
Command: npx skills add https://github.com/Team-Hireal/RealChat --skill sag-team-hireal

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a command-line interface for generating text-to-speech audio using ElevenLabs, with a user experience similar to the macOS say command, enabling local playback of generated speech.

Core Features & Use Cases

  • Text-to-Speech Generation: Convert written text into natural-sounding speech using ElevenLabs voices.
  • Voice Customization: Select specific voices and control pronunciation and delivery rules.
  • Use Case: Quickly generate audio pronunciations for new vocabulary, create voiceovers for short video clips, or provide spoken feedback on documents without leaving the terminal.

Quick Start

Use the sag command 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 generate text-to-speech audio from the command line using ElevenLabs?

You can generate text-to-speech audio from the command line by running the sag command with your desired text. It uses ElevenLabs models to synthesize speech and plays it back locally, providing a terminal-based TTS experience.

Can I customize the voice and pronunciation for speech synthesis in the terminal?

Yes, you can customize voice and pronunciation for speech synthesis by passing command-line arguments and environment variables. This allows you to select specific ElevenLabs voices and control delivery rules directly from your terminal session.

Does this text-to-speech tool work like the macOS say command?

Yes, this text-to-speech tool is designed to work like the macOS say command. It provides a similar user experience by enabling quick, local playback of generated ElevenLabs speech directly from the command line without leaving the terminal.

What is the best way to create voiceovers for short video clips using TTS?

The best way to create voiceovers for short clips using TTS is through command-line speech synthesis. This Skill converts written text into natural-sounding speech using ElevenLabs voices, allowing rapid audio generation for spoken output.

Do I need an ElevenLabs API key to generate speech with this command-line tool?

Yes, you need an ElevenLabs API key to generate speech with this command-line tool. The tool synthesizes text-to-speech audio using various ElevenLabs models, which requires authenticating your requests to their TTS service via environment variables.