sag

Convert text to natural-sounding speech via ElevenLabs TTS for local playback.

117|8|Updated Jan 20, 2026
One-click install
npx skills add https://github.com/geezerrrr/motive --skill sag-geezerrrr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/geezerrrr/motive/tree/main/Motive/Resources/Skills.bundle/sag
Command: npx skills add https://github.com/geezerrrr/motive --skill sag-geezerrrr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Use sag to convert text into natural-sounding speech for local playback, enabling expressive voice output within desktop workflows.

Core Features & Use Cases

  • Voice-enabled prompts: Generate spoken feedback from natural language, with configurable voices.
  • Local playback: All audio is produced and played back on-device, preserving privacy.
  • Model notes & prompts: Support for voice selection, prompts, and style hints to shape delivery.

Quick Start

Speak a string of text using sag to hear it played 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 on macOS?

To convert text to speech on macOS, this Skill uses ElevenLabs TTS to generate natural-sounding audio and plays it back locally. You provide the text, select a configurable voice, and the audio output is played directly on your device.

Do I need an API key to generate audio with ElevenLabs TTS?

Yes, generating audio with ElevenLabs TTS requires an API key. You must configure either an ELEVENLABS_API_KEY or a SAG_API_KEY in your environment to authenticate the text-to-speech requests and produce natural-sounding speech.

Can I customize voices and delivery style for text-to-speech playback?

Yes, you can customize voices and delivery style for text-to-speech playback. The Skill supports configurable voice selection, prompts, and style hints to shape the delivery of your generated spoken feedback and narrated content.

Does text-to-speech audio processing happen locally or in the cloud?

Audio playback happens locally on your macOS device, preserving privacy. The text-to-speech generation is handled by ElevenLabs, but the resulting audio is produced and played back on-device within your local desktop workflows.

What is the best way to get spoken feedback for local desktop workflows?

The best way to get spoken feedback for local desktop workflows is using a text-to-speech Skill that converts natural language into audio. This tool applies voice selection and local playback to generate expressive voice prompts without leaving your desktop.