sag

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

32|9|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/DotNetAge/mindx --skill sag-dotnetage
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/DotNetAge/mindx/tree/main/skills/sag
Command: npx skills add https://github.com/DotNetAge/mindx --skill sag-dotnetage

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Converts text into natural-sounding speech locally using ElevenLabs voices, enabling offline or on-device TTS without relying on cloud-only solutions.

Core Features & Use Cases

  • Local TTS: generate audio on your machine with high-quality ElevenLabs voices.
  • Voice versatility: switch between multiple voices and styles to fit context.
  • Command-line friendly: integrates with sag CLI for quick playback or file export.

Quick Start

Run sag "你好" to synthesize and play audio locally.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I generate natural-sounding speech locally using text-to-speech?

Generate natural-sounding speech locally by running the sag CLI to convert text into audio with ElevenLabs voices. This on-device TTS process requires the ELEVENLABS_API_KEY and outputs audio for immediate playback or file export.

What is on-device TTS and when do I need it for my applications?

On-device TTS converts text into speech on local hardware without relying on cloud-only solutions. You need it for apps, chatbots, accessibility tools, and demos requiring offline audio generation and immediate voice playback.

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

Yes, you need the ELEVENLABS_API_KEY to use this on-device text-to-speech functionality. The key allows the local sag CLI to authenticate with ElevenLabs and generate high-quality audio using supported voices.

Can I switch between different voices and styles for TTS audio generation?

Yes, you can switch between multiple voices and styles for TTS audio generation. The tool supports SSML variations to fit your specific context, allowing versatile voice output for chatbots or accessibility tools.

How do I quickly synthesize and play text-to-speech audio from the command line?

Quickly synthesize and play TTS audio from the command line by running sag followed by your text. The CLI processes the input locally and outputs the generated audio for immediate playback on your machine.

Does on-device voice generation work offline without cloud-only solutions?

On-device voice generation using ElevenLabs voices enables local TTS without relying on cloud-only solutions. However, synthesizing audio still requires the ELEVENLABS_API_KEY for authentication during the generation process.