sag

Converts text to speech via ElevenLabs API with local playback.

3|1|Updated Feb 23, 2026

Search Tags:#voice #audio generation #elevenlabs #tts #speech synthesis

Ready to run

npx skills add https://github.com/SeanHogg/coderClaw --skill sag-seanhogg

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/SeanHogg/coderClaw/tree/main/product/skills/sag
Command: npx skills add https://github.com/SeanHogg/coderClaw --skill sag-seanhogg

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a convenient way to convert text into speech using ElevenLabs' advanced TTS technology, mimicking the familiar "say" command experience on macOS.

Core Features & Use Cases

Text-to-Speech Conversion: Generate natural-sounding speech from text input.
Voice Customization: Select from various ElevenLabs voices and apply specific speaking styles.
Local Playback: Audio is played directly on your machine.
Use Case: Get instant voice feedback on code explanations or receive spoken notifications without needing to read text on screen.

Quick Start

Use the sag skill to speak the phrase "Hello there" using the default voice.

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 from the command line?▼

You can convert text to speech using ElevenLabs by passing your text string to generate audio, which is then played locally on your machine through a macOS-style 'say' command interface. This requires setting the ELEVENLABS_API_KEY environment variable for authentication.

Can I use different ElevenLabs models for text-to-speech generation?▼

Yes, ElevenLabs text-to-speech generation supports various models for expressive, multilingual, or fast speech synthesis. You can select from available ElevenLabs voices and apply specific speaking styles to customize the audio output.

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

Yes, you need an ELEVENLABS_API_KEY environment variable configured for authentication to use ElevenLabs TTS conversion. Without this API key set in your local environment, the speech synthesis process cannot authenticate or generate audio.

What is the best way to get spoken audio feedback for text on macOS?▼

The best way to get spoken audio feedback is using a macOS-style 'say' command interface that converts text to speech with ElevenLabs. This provides natural-sounding voice generation and plays the audio directly on your local machine without needing to read text on screen.

Does ElevenLabs speech synthesis support pronunciation normalization and voice customization?▼

Yes, ElevenLabs speech synthesis supports pronunciation normalization and voice character customization. You can select from various ElevenLabs voices, apply specific speaking styles, and adjust settings to generate expressive or multilingual speech output.

Can I use ElevenLabs text-to-speech for local audio playback?▼

Yes, ElevenLabs text-to-speech conversion supports local audio playback directly on your machine. After generating speech from your text input, the audio is played locally rather than being saved to a file or streamed to an external service.