skills.rest
freire19
freire19COMMUNITY
Explore all skills by this author →
GitHub

sag

Generate ElevenLabs text-to-speech audio from prompts via CLI.

Updated May 8, 2026
Search Tags:#text-to-speech#elevenlabs#voice generation#pronunciation normalization#tts cli#audio delivery
One-click install
npx skills add https://github.com/freire19/Mythos --skill sag-freire19
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/freire19/Mythos/tree/main/skills/sag
Command: npx skills add https://github.com/freire19/Mythos --skill sag-freire19

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of quickly generating natural-sounding spoken audio from text so you can deliver messages as voice instead of plain writing.

Core Features & Use Cases

  • ElevenLabs text-to-speech via CLI: Create spoken audio from prompts and manage voices for different output styles.
  • Model and delivery controls: Choose stable/fast/expressive ElevenLabs models and tune pronunciation and normalization for clarity.
  • Expressive speaking markup: Add delivery intent (whispers, shouts, sings, laughter, etc.) and pauses for more engaging results.

Quick Start

Generate local ElevenLabs TTS audio for a line of text using your configured ELEVENLABS_API_KEY.

Frequently Asked Questions about sag

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

FAQPage Schema
How do I generate ElevenLabs text-to-speech audio from the command line?▼

You can generate ElevenLabs text-to-speech audio from the command line by providing a text prompt to the CLI, which requires an ELEVENLABS_API_KEY and outputs a local audio file for playback.

Can I add expressive delivery instructions like whispers or pauses to text-to-speech output?▼

Yes, text-to-speech output supports expressive speaking markup, allowing you to add delivery intents such as whispers, shouts, and pauses to create more engaging audio results.

Do I need an API key to use ElevenLabs voice generation via CLI?▼

Yes, ElevenLabs voice generation via CLI requires an API key. You must configure either an ELEVENLABS_API_KEY or a SAG_API_KEY in your environment before generating audio.

What's the best way to manage and select different voices for text-to-speech generation?▼

The best way to manage and select voices for text-to-speech generation is by using the provided CLI command to list available ElevenLabs voices, allowing you to choose the best match for your output style.

How do pronunciation normalization and delivery controls affect text-to-speech audio?▼

Pronunciation normalization and delivery controls tune the text-to-speech audio for clarity by allowing you to choose between stable, fast, or expressive ElevenLabs models and adjust how words are spoken.

Can I use ElevenLabs text-to-speech for accessibility and local playback workflows?▼

Yes, you can use ElevenLabs text-to-speech for accessibility and local playback workflows by generating spoken audio files from text prompts directly through the CLI.

Related Skills

Explore More Content & Communication Skills→
liutao96liutao96

sag

Convert input text into speech via ElevenLabs TTS with local playback.

Community
Intermediate
MOODMNKY-LLCMOODMNKY-LLC

sag

Generate natural text-to-speech audio via the ElevenLabs TTS API.

Community
Intermediate
spoonbobospoonbobo

sag

Convert text to speech via ElevenLabs with a macOS-style command-line interface.

Community
Intermediate
Team-HirealTeam-Hireal

sag

Generate text-to-speech audio via ElevenLabs with local playback.

Community
Intermediate