sag

Convert typed text to speech via ElevenLabs TTS with a mac-style say UX.

202|36|Updated Jan 27, 2026

Search Tags:#cli #text-to-speech #elevenlabs #tts #api-key #voices

Ready to run

npx skills add https://github.com/adoresever/AGI_Ananas --skill sag-adoresever

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/adoresever/AGI_Ananas/tree/main/26.2.21openclaw-viking/skills/sag
Command: npx skills add https://github.com/adoresever/AGI_Ananas --skill sag-adoresever

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Translates typed text into natural-sounding speech using ElevenLabs TTS and a mac-style say UX, enabling quick audio previews without external tooling.

Core Features & Use Cases

Voice-focused text-to-speech synthesis with API key access and flexible voice selection.
Supports multiple voices and pronunciation tweaks for realistic delivery in demos, accessibility checks, or content previews.
Use case: generate short audio clips for product demos, documentation, or QA testing.

Quick Start

Synthesize a short greeting by running sag "Hello there" and listening to the result.

Frequently Asked Questions about sag

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

FAQPage Schema

How do I generate natural-sounding speech from text using a CLI tool?▼

Generate natural-sounding speech from text by running the sag CLI with your typed string, which uses ElevenLabs TTS to synthesize and play the audio locally.

Do I need an API key to use ElevenLabs text-to-speech for voice previews?▼

Yes, you need an ElevenLabs API key to use text-to-speech for voice previews. Configure the ELEVENLABS_API_KEY environment variable to authenticate synthesis requests.

Can I select different voices for text-to-speech synthesis in the terminal?▼

Yes, you can select different voices for text-to-speech synthesis in the terminal. The CLI supports flexible voice selection and pronunciation tweaks for realistic delivery.

What is the best way to test narration and voice prompts for product demos?▼

Test narration and voice prompts for product demos by running sag with your script text to quickly synthesize sample clips without needing external audio tooling.

Does the mac-style say UX support SSML tags for pronunciation adjustments?▼

The mac-style say UX supports optional SSML-like tags for pronunciation adjustments, allowing you to refine delivery and generate realistic voice clips for accessibility checks.

When should I not use ElevenLabs TTS for audio generation?▼

Avoid using ElevenLabs TTS for audio generation when working offline or without API access, as the synthesis mechanism requires network connectivity and valid API key authentication.