sag

Convert text to speech with ElevenLabs TTS and local playback.

Updated Apr 5, 2026
One-click install
npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill sag-balic-ai-ml-r-d-resources
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents/tree/main/packages/skills/skills/sag
Command: npx skills add https://github.com/balic-AI-ML-R-D-Resources/eliza_autonomous_agents --skill sag-balic-ai-ml-r-d-resources

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

sag enables quick, local text-to-speech generation using ElevenLabs, removing the need to rely on external services for basic audio output.

Core Features & Use Cases

  • ElevenLabs TTS with local playback for instant audio output.
  • API-key driven configuration and voice selection for customized narration.
  • Use Case: convert chat responses or prompts into spoken audio for demonstrations or accessibility.

Quick Start

Use sag to convert a short text into spoken audio that plays back immediately.

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 locally using the ElevenLabs API?

Convert text to speech locally by running the sag CLI with an ElevenLabs API key to generate audio output for immediate playback. It enables command-line voice generation without relying on external web services for basic narration.

What is command-line text-to-speech generation used for in interactive assistants?

Command-line text-to-speech generation is used to convert chat responses or prompts into spoken audio for interactive assistants, accessibility features, and media narrations. It provides instant local playback of dynamically generated voice output.

Do I need an ElevenLabs API key to use the sag CLI for voice generation?

Yes, an ElevenLabs API key is required to use the sag CLI for voice generation. The API-key driven configuration authenticates your requests and enables customized voice selection for local audio playback.

Can I select different voices for text-to-speech output via command line?

Yes, sag supports voice selection for customized narration via command line. You can configure different ElevenLabs voices through the API-key driven settings to generate tailored text-to-speech audio output for your specific use case.

What's the best way to integrate text-to-speech into local CLI workflows?

The best way to integrate text-to-speech into local CLI workflows is using sag for command-line integration with ElevenLabs TTS. It satisfies requirements for dynamic audio generation, voice selection, and instant local playback within terminal environments.

When should I not use local CLI text-to-speech for audio generation?

You should not use local CLI text-to-speech when your project requires complex audio editing, multi-track mixing, or visual interfaces rather than simple command-line integration. Sag is designed for basic, instant local playback rather than advanced audio production workflows.