sag

Convert text to speech via ElevenLabs API with local audio playback.

375|38|Updated Dec 2, 2025
One-click install
npx skills add https://github.com/CraftOS-dev/CraftBot --skill sag-craftos-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/CraftOS-dev/CraftBot/tree/main/skills/sag
Command: npx skills add https://github.com/CraftOS-dev/CraftBot --skill sag-craftos-dev

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 for local playback.

Core Features & Use Cases

  • ElevenLabs TTS Integration: Leverages ElevenLabs for high-quality voice generation.
  • Local Playback: Audio is played directly on your machine.
  • Customizable Voices and Pronunciation: Supports various models, voice IDs, and pronunciation rules for tailored output.
  • Use Case: Generate voice responses for your AI assistant, create audio versions of documents, or add spoken elements to your projects.

Quick Start

Use the sag skill to say "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 convert text to speech using ElevenLabs on macOS?

You can convert text to speech using ElevenLabs on macOS by invoking the sag command, which mimics the native 'say' command UX for local audio playback while leveraging ElevenLabs' advanced voice generation models.

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

Yes, you need an API key to use ElevenLabs text-to-speech. You must set either the ELEVENLABS_API_KEY or SAG_API_KEY environment variable in your local system before executing the voice generation command.

Can I select different voice models for text-to-speech generation?

Yes, you can select different voice models for text-to-speech generation. The skill supports various ElevenLabs models including eleven_v3, eleven_multilingual_v2, and eleven_flash_v2_5, alongside custom voice IDs and pronunciation normalization.

Does ElevenLabs text-to-speech support SSML tags for expressive delivery?

Yes, ElevenLabs text-to-speech supports SSML-like tags for expressive delivery. This allows you to control the pacing, tone, and emotional inflection of the synthesized speech beyond standard text input.

What is the best way to play ElevenLabs voice generation locally?

The best way to play ElevenLabs voice generation locally is using a command-line tool that directly outputs audio to your machine. This skill handles local audio playback natively after fetching the generated speech.