sag

Play ElevenLabs TTS locally with a macOS-style say command.

Updated Mar 22, 2026
One-click install
npx skills add https://github.com/MaxSaiets/myOpenCL --skill sag-maxsaiets
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/MaxSaiets/myOpenCL/tree/main/openclaw/skills/sag
Command: npx skills add https://github.com/MaxSaiets/myOpenCL --skill sag-maxsaiets

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables local, high-quality text-to-speech using ElevenLabs with a macOS-style say UX, reducing integration friction for voice-enabled demos and accessibility features.

Core Features & Use Cases

  • Local playback of ElevenLabs TTS voices for quick demos and user-facing experiments.
  • API key based authentication with support for ELEVENLABS_API_KEY or SAG_API_KEY, voice selection, and pronunciation adjustments.
  • Use Case: Build a voice-enabled assistant or narrated tutorial that speaks text aloud in your app.

Quick Start

Speak a sample text to sag and hear it spoken back immediately.

Frequently Asked Questions about sag

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use ElevenLabs text-to-speech locally with a macOS say command UX?

You can enable local playback of ElevenLabs TTS with a macOS-style say UX by using the sag CLI binary, which requires setting your ELEVENLABS_API_KEY or SAG_API_KEY for authentication and allows optional voice selection.

What do I need to integrate ElevenLabs TTS voice output into my local application?

To integrate ElevenLabs TTS voice output, you need the sag CLI binary, a valid ELEVENLABS_API_KEY or SAG_API_KEY for authentication, and optional configurations for voice selection and pause controls to enable local playback.

Can I customize the voice when using ElevenLabs text-to-speech for application demos?

Yes, ElevenLabs text-to-speech playback supports voice customization and pronunciation adjustments, allowing developers to select specific voices when building voice-enabled assistants or narrated tutorials.

Does macOS say-style text-to-speech require an API key to function?

Yes, an API key is required for authentication to enable local ElevenLabs text-to-speech playback, specifically utilizing either the ELEVENLABS_API_KEY or the SAG_API_KEY environment variables.

Why use a CLI tool for ElevenLabs TTS instead of direct API integration?

Using a CLI tool reduces integration friction by providing a seamless macOS-style say UX, enabling quick local playback for voice-enabled demos and accessibility features without building complex direct API integrations.