sag

Convert text to speech via ElevenLabs API with local playback.

Updated Feb 10, 2026
One-click install
npx skills add https://github.com/cogpy/clawcog --skill sag-cogpy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/cogpy/clawcog/tree/main/skills/sag
Command: npx skills add https://github.com/cogpy/clawcog --skill sag-cogpy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a seamless way to convert text into speech using ElevenLabs, mimicking the familiar "say" command experience on macOS.

Core Features & Use Cases

  • Text-to-Speech: Generate high-quality audio from text using ElevenLabs voices.
  • Local Playback: Play the generated audio directly on your system.
  • Voice Customization: Select specific voices and control pronunciation and delivery.
  • Use Case: Have your AI assistant read out important notifications or summaries in a natural-sounding voice.

Quick Start

Use sag to speak the phrase "Hello there" using 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 voices on macOS?

You can convert text to speech using ElevenLabs voices by running the sag command, which mimics the native macOS say experience. It generates high-quality audio using the ElevenLabs API and plays it back locally on your system.

Can I select specific voices and adjust pronunciation for text-to-speech generation?

Yes, you can select specific voices and adjust pronunciation for text-to-speech generation. The Skill supports voice selection, pronunciation adjustments, and delivery nuances through command-line arguments and environment variables.

How does local audio playback work for generated ElevenLabs speech?

Local audio playback works by integrating the ElevenLabs API for voice generation with local command-line tools for audio output. After generating the speech from text, the Skill plays the audio directly on your system.

Do I need an ElevenLabs API key to use this text-to-speech command?

Yes, you need an ElevenLabs API key to use this text-to-speech command. The Skill integrates with the ElevenLabs API for voice generation, which is accessed through environment variables configured on your local system.

What is the best way to have my AI assistant read out notifications in a natural voice?

The best way to have your AI assistant read notifications in a natural voice is using the sag command. It leverages ElevenLabs text-to-speech models to generate high-quality audio and plays it locally, mimicking the familiar macOS say user experience.

Does this text-to-speech tool support different ElevenLabs models for voice synthesis?

Yes, this text-to-speech tool supports different ElevenLabs models for voice synthesis. You can control the voice generation process and select specific models through command-line arguments and environment variables.