sag

Convert input text into speech via ElevenLabs TTS with local playback.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/liutao96/skill --skill sag-liutao96
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/liutao96/skill/tree/main/sag
Command: npx skills add https://github.com/liutao96/skill --skill sag-liutao96

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

SAG provides a quick and self-contained way to convert text into natural-sounding speech using ElevenLabs TTS with local playback, eliminating the need for external services for small to medium tasks.

Core Features & Use Cases

  • Local playback of generated speech with on-device processing.
  • Voice customization and model parameters accessible via CLI.
  • Suitable for voice responses, demos, accessibility prompts, and podcast-like snippets.

Quick Start

Speak a sample sentence using sag to verify local TTS playback.

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 natural-sounding speech locally using ElevenLabs TTS?▼

You can convert text to natural-sounding speech locally by using this Skill to process input text via ElevenLabs TTS and play the resulting audio on your device. It requires an ELEVENLABS_API_KEY or SAG_API_KEY for voice synthesis.

Can I customize the voice selection and model parameters for text-to-speech generation?▼

Yes, you can customize voice selection and model parameters for text-to-speech generation through CLI commands and environment variables. This allows you to tailor the voice synthesis output to fit specific audio response or podcast snippet needs.

Do I need an external service to play generated TTS audio on my device?▼

No, you do not need an external service for playback because this Skill provides local playback of generated speech with on-device processing. It handles the audio generation and playback self-contained for small to medium tasks.

What is the best way to generate accessibility prompts from text on a Mac?▼

A reliable way to generate accessibility prompts from text is using a TTS tool that offers local playback and natural-sounding voice synthesis. This Skill handles on-device audio generation, suitable for accessibility prompts and voice responses.

Does this text-to-speech tool work without an internet connection?▼

No, text-to-speech generation requires an internet connection to communicate with the ElevenLabs API for voice synthesis. However, the playback of the generated speech is processed locally on your device.