skills.rest
NJUxlj
NJUxljCOMMUNITY
Explore all skills by this author →
GitHub

sag

Convert text to speech using ElevenLabs TTS models with local playback.

Updated Feb 1, 2026
Search Tags:#text-to-speech#audio generation#elevenlabs#tts#voice synthesis#macos say
One-click install
npx skills add https://github.com/NJUxlj/openclaw --skill sag-njuxlj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sag
Source: https://github.com/NJUxlj/openclaw/tree/main/skills/sag
Command: npx skills add https://github.com/NJUxlj/openclaw --skill sag-njuxlj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a seamless way to convert text into speech using ElevenLabs' advanced TTS models, with a user experience similar to macOS's built-in 'say' command.

Core Features & Use Cases

  • Text-to-Speech Conversion: Generate natural-sounding speech from text using various ElevenLabs models.
  • Voice Customization: Select specific voices and control pronunciation and delivery with special tags.
  • Use Case: When you need to have a message read aloud in a specific character voice, like a "crazy scientist," this skill can generate the audio with appropriate tags and pacing.

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 models?▼

To convert text to speech using ElevenLabs models, you provide your text and an ElevenLabs API key for authentication. The Skill then generates natural-sounding speech and outputs an audio file for local playback.

What's the best way to generate audio in a specific character voice like a crazy scientist?▼

The best way to generate character voice audio is by using special pronunciation and delivery tags. These tags control pacing and delivery, allowing the ElevenLabs TTS to accurately produce specific character voices like a crazy scientist.

Which ElevenLabs TTS models can I use for voice synthesis?▼

Supported ElevenLabs TTS models include eleven_v3, eleven_multilingual_v2, and eleven_flash_v2_5. You can select from these models to perform voice synthesis based on your specific language or processing speed requirements.

Do I need an ElevenLabs API key to generate audio files locally?▼

Yes, you need an ElevenLabs API key to authenticate your requests. The Skill integrates with your API key to access the TTS models and generate the audio files that are then played back locally.

Can I use this text-to-speech tool as an alternative to the macOS say command?▼

Yes, you can use this tool as an alternative to the macOS say command. It provides a similar user experience for local playback but leverages ElevenLabs' advanced TTS models to generate higher-quality, natural-sounding speech.

Related Skills

Explore More Content & Communication Skills→
lemonlqflemonlqf

sag

Convert text to speech using the ElevenLabs TTS engine with customizable voice options.

Community
Intermediate
Soul-Brews-StudioSoul-Brews-Studio
116

speak

Convert text to speech using edge-tts neural voices with macOS say fallback.

Official
Intermediate
simplefarmer69simplefarmer69
2

sag

Generate speech from text using ElevenLabs TTS with a macOS-style command-line interface.

Community
Intermediate
cogpycogpy

sag

Convert text to speech via ElevenLabs API with local playback.

Official
Intermediate