sag

Generate natural-sounding speech from text using ElevenLabs TTS for local playback.

Updated Feb 3, 2026
One-click install
npx skills add https://github.com/joeleung0122/testing --skill sag-joeleung0122
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/joeleung0122/testing/tree/main/skills/sag
Command: npx skills add https://github.com/joeleung0122/testing --skill sag-joeleung0122

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ElevenLabs TTS is available locally to convert text into natural-sounding speech for on-device playback, enabling responsive voice interactions without relying on external services during runtime.

Core Features & Use Cases

  • Local playback of ElevenLabs TTS voices for on-device applications and assistants.
  • API key handling with ELEVENLABS_API_KEY (preferred) or SAG_API_KEY, and support for default voices.
  • Voice selection and model variant notes to control expressiveness and speed.
  • Pronunciation and delivery rules guidance to adjust pacing and pronunciation in generated speech.
  • Quick-start tips for testing on a local machine.

Quick Start

Try sag "Hello there" to hear ElevenLabs TTS 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 locally using ElevenLabs TTS?

Local text-to-speech with ElevenLabs requires setting the ELEVENLABS_API_KEY or SAG_API_KEY environment variable. Once configured, the system authenticates requests to generate natural-sounding audio for on-device playback.

Can I select different voices and control expressiveness for ElevenLabs text-to-speech?

Voice selection and model variant controls allow you to adjust expressiveness and speed in ElevenLabs text-to-speech. You can also apply pronunciation and delivery rules to fine-tune pacing in the generated speech.

Do I need an API key to generate natural-sounding speech on my local machine?

Generating natural-sounding speech locally requires an ELEVENLABS_API_KEY or SAG_API_KEY. The system integrates with environment variables to securely handle API authentication for on-device audio playback.

What's the best way to test ElevenLabs TTS for accessibility and chat-like scenarios?

Testing ElevenLabs TTS for accessibility and chat-like scenarios is best achieved through local playback with a mac-style say UX. This enables responsive voice interactions without relying on external services during runtime.

How do I configure pronunciation rules for text-to-speech generation?

Pronunciation rules are configured by applying delivery guidance to adjust pacing in generated speech. The system supports pronunciation and delivery rules to control how text translates into natural-sounding audio.