sag

Generates ElevenLabs text-to-speech audio with macOS-style CLI and voice customization options.

5|Updated Feb 2, 2026

Search Tags:#text-to-speech #macos #audio generation #elevenlabs #tts #voice synthesis

Ready to run

npx skills add https://github.com/0xHoneyJar/loa-beauvoir --skill sag-0xhoneyjar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/0xHoneyJar/loa-beauvoir/tree/main/skills/sag
Command: npx skills add https://github.com/0xHoneyJar/loa-beauvoir --skill sag-0xhoneyjar

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a convenient way to generate text-to-speech audio using ElevenLabs, mimicking the user-friendly experience of macOS's built-in 'say' command.

Core Features & Use Cases

ElevenLabs TTS Integration: Leverages ElevenLabs for high-quality voice synthesis.
Local Playback: Audio is generated and can be played back locally.
Voice Customization: Supports selecting specific voices and adjusting pronunciation.
Use Case: Quickly generate voice responses for your AI assistant, create audio snippets for presentations, or convert text documents into spoken word.

Quick Start

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

To generate ElevenLabs text-to-speech audio, this Skill uses a macOS-style 'say' command experience, passing text via CLI arguments to synthesize speech and play it back locally.

Can I customize the voice and pronunciation for ElevenLabs TTS generation?▼

Yes, you can customize ElevenLabs TTS voice synthesis by selecting specific voices and adjusting pronunciation through CLI arguments and environment variables.

Does ElevenLabs voice synthesis support SSML tags for expressive speech?▼

Yes, ElevenLabs voice synthesis supports SSML-like tags for expressive speech, allowing you to control pronunciation and generate nuanced audio snippets.

What is the best way to mimic the macOS say command for high-quality TTS?▼

To mimic the macOS 'say' command with high-quality audio, this Skill wraps ElevenLabs voice synthesis to provide a familiar, user-friendly CLI experience for local playback.

Can I use ElevenLabs text-to-speech to convert text documents into spoken word locally?▼

Yes, you can use ElevenLabs text-to-speech to convert text documents into spoken word, generating audio locally for presentations or AI assistant responses.

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

Yes, generating text-to-speech audio with ElevenLabs requires configuring your API key via environment variables to authenticate the voice synthesis requests.