sag

Convert text to speech via the sag CLI with ElevenLabs voices.

2|1|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/zhangziliang04/moltbot_deepseek --skill sag-zhangziliang04
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/zhangziliang04/moltbot_deepseek/tree/main/skills/sag
Command: npx skills add https://github.com/zhangziliang04/moltbot_deepseek --skill sag-zhangziliang04

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a simple setup to convert text into speech using ElevenLabs via sag, enabling quick audio playback locally.

Core Features & Use Cases

  • Convert text to speech with ElevenLabs voices using the sag CLI for fast prototyping and testing.
  • Supports multiple voices and tone adjustments, allowing for expressive audio demos and automated responses.
  • Use case: create audio samples for product demos, accessibility features, or voice-enabled assistants in development.

Quick Start

Speak a short message using sag to hear it spoken locally.

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 for local playback?

You can convert text to speech for local playback by running the sag CLI with your text input. The skill sends the request to the ElevenLabs API and automatically plays the resulting audio locally on your machine.

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

Yes, an API key is required to use ElevenLabs text-to-speech with sag. You must configure either an ELEVENLABS_API_KEY or a SAG_API_KEY in your environment to authenticate and process voice generation requests.

Can I adjust pronunciation and tone when generating audio with sag?

Yes, you can adjust pronunciation and tone when generating audio with sag. The skill exposes specific configuration options through the sag CLI, allowing you to control the expressiveness and delivery of the generated voice models.

Does sag support multiple voices for text-to-speech demos?

Yes, sag supports multiple voices for text-to-speech demos. You can select different voice models through the CLI to test various outputs, making it suitable for product demos, accessibility features, and automated audio responses.

What are the limitations of using a CLI for text-to-speech generation?

The main limitation of using a CLI for text-to-speech generation is that it is designed for basic prototyping and testing. It lacks a visual interface, relying entirely on terminal commands to manage voice models, pronunciation, and local playback.