sag

Generate ElevenLabs text-to-speech audio and play it locally via CLI.

Updated Apr 3, 2026
One-click install
npx skills add https://github.com/BEIRUX/agent-skills --skill sag-beirux
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/BEIRUX/agent-skills/tree/main/sag
Command: npx skills add https://github.com/BEIRUX/agent-skills --skill sag-beirux

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a simple CLI interface to convert text into ElevenLabs-quality speech and play it locally, removing the need to manually call APIs or stitch playback workflows together.

Core Features & Use Cases

  • CLI-first TTS: Generate and play audio from text using the sag command-line tool for fast previews and voice replies.
  • Voice and model selection: Choose expressive, stable, or fast models and set default voices via environment variables or flags.
  • Pronunciation and delivery control: Use normalization, language hints, and inline audio tags to control pacing, emphasis, and characterful deliveries.
  • Use Case: Produce quick character voice responses for chatbots or generate narration previews for demos.

Quick Start

Use sag to generate and play an ElevenLabs voice saying Hello there locally.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I generate ElevenLabs text-to-speech audio and play it locally from the command line?

You can generate ElevenLabs text-to-speech audio and play it locally by using the sag CLI tool to convert text input into speech directly from your terminal. It handles both API generation and local audio playback in a simple workflow.

What do I need to use ElevenLabs TTS for quick voice replies and narration previews?

To use ElevenLabs TTS for voice replies, you need an ElevenLabs API key configured via the ELEVENLABS_API_KEY or SAG_API_KEY environment variable, along with the sag CLI installed on a system with local audio playback support.

Can I choose different voices and models for text-to-speech generation in the CLI?

Yes, you can choose expressive, stable, or fast models and set default voices for text-to-speech generation using environment variables or command-line flags when running the sag CLI tool.

How do I control pronunciation, pacing, and emphasis in ElevenLabs speech synthesis?

You control pronunciation, pacing, and emphasis in ElevenLabs speech synthesis by applying text normalization, language hints, and inline audio tags within your input text to achieve characterful deliveries.

Is there a simple CLI tool for generating chatbot character voice responses without manual API calls?

The sag CLI provides a simple interface to generate character voice responses for chatbots by converting text into ElevenLabs-quality speech and playing it locally, removing the need to manually call APIs or stitch playback workflows together.