sag

Convert text into synthetic speech using the ElevenLabs API.

6|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/me2Doc/friendlyclaw --skill sag-me2doc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/me2Doc/friendlyclaw/tree/main/body/skills/sag
Command: npx skills add https://github.com/me2Doc/friendlyclaw --skill sag-me2doc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires sag.

What problem does it solve?

This skill bridges the gap between text-based AI responses and expressive, human-like audio output, allowing for natural voice-based interactions.

Core Features & Use Cases

  • ElevenLabs Integration: Provides direct access to high-quality, expressive TTS models including v3 and flash variants.
  • Voice Customization: Supports custom voice IDs, emotional tagging, and prosody control through simple text markers.
  • Use Case: Use this to generate professional-grade voiceovers for presentations or to provide audible, character-driven responses during a chat session.

Quick Start

Use the sag skill to generate an audio file named greeting.mp3 that says hello in a calm 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 high-fidelity speech using ElevenLabs?

To convert text to high-fidelity speech using ElevenLabs, this skill processes your input text and synthesizes expressive audio via the ElevenLabs API, requiring the sag CLI tool to execute the generation.

Do I need an ElevenLabs API key to generate synthetic voice audio?

Yes, you need a valid ELEVENLABS_API_KEY environment variable configured for authentication to successfully generate synthetic voice audio through this skill's ElevenLabs integration.

Can I customize voice styles and emotions for text-to-speech output?

You can customize text-to-speech output by specifying custom voice IDs and applying emotional tagging and prosody control using simple text markers within your input text.

What is the best way to generate professional voiceovers for presentations?

The best way to generate professional voiceovers for presentations is using this skill to access high-quality, expressive TTS models like v3 and flash variants, outputting studio-grade audio files.

Does the sag tool work without installing any external dependencies?

No, the sag tool does not work without external dependencies; it explicitly requires the sag CLI tool installed locally to bridge text-based AI responses with human-like audio output.