sag

Generate ElevenLabs text-to-speech audio with macOS-style say UX from the command line.

Updated Jan 29, 2026

Search Tags:#accessibility #cli #voice #text-to-speech #macos #elevenlabs #tts

Ready to run

npx skills add https://github.com/DharambirAgrawal/Personal-Assistant --skill sag-dharambiragrawal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/DharambirAgrawal/Personal-Assistant/tree/main/skills/sag
Command: npx skills add https://github.com/DharambirAgrawal/Personal-Assistant --skill sag-dharambiragrawal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

sag provides ElevenLabs text-to-speech output with a native macOS-style say UX, enabling quick, locally playable audio from textual input.

Core Features & Use Cases

Voice playback: Generate natural-sounding speech from text using ElevenLabs voices.
CLI integration: Drive TTS from scripts or commands for automation and accessibility workflows.
Use Case: Convert meeting notes into audio summaries for quick review or create spoken prompts for demos.

Quick Start

Speak a simple message using sag to hear it spoken aloud.

Frequently Asked Questions about sag

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

FAQPage Schema

How do I use ElevenLabs text-to-speech from the macOS command line?▼

You can use ElevenLabs text-to-speech from the macOS command line by utilizing a say-style CLI tool that requires a configured ELEVENLABS_API_KEY or SAG_API_KEY to render text into natural speech for local playback.

Can I automate text-to-speech voice generation in macOS shell scripts?▼

Yes, you can automate text-to-speech voice generation in macOS shell scripts by driving the CLI TTS tool, which follows macOS say UX conventions to convert text input into locally playable audio.

Does ElevenLabs TTS work natively with the macOS say command UX?▼

ElevenLabs TTS works natively with the macOS say command UX through a dedicated binary that mimics say conventions, enabling users to generate expressive speech using multiple ElevenLabs voices.

What API keys do I need to configure for local text-to-speech playback on macOS?▼

To enable local text-to-speech playback on macOS, you need to configure either an ELEVENLABS_API_KEY or a SAG_API_KEY, along with the required sag binary, to authenticate and render natural voice audio.

What is the best way to convert meeting notes into audio summaries on macOS?▼

The best way to convert meeting notes into audio summaries on macOS is using a CLI text-to-speech tool that applies ElevenLabs voice rendering to quickly generate spoken audio from text for review.

Can I use multiple voices for text-to-speech rendering in command-line automation?▼

Yes, you can use multiple voices for text-to-speech rendering in command-line automation, as the macOS say-style CLI supports selecting different ElevenLabs voices for expressive audio output.