ElevenLabs Voice Synthesis
Generates high-quality ElevenLabs text-to-speech audio with a simple macOS-style command-line interface.
The sag skill integrates ElevenLabs' state-of-the-art text-to-speech capabilities directly into the Claude environment, providing a user experience inspired by the classic macOS 'say' command. It enables developers and users to quickly generate expressive audio from text, offering fine-grained control over voices, emotional delivery tags like [whispers] or [excited], and advanced model selection. This tool is particularly useful for adding character-driven voice responses to AI interactions, testing TTS outputs, or automating audio content creation within a terminal-based workflow.
Key Features
01Emotional delivery control using audio tags like [whispers], [shouts], and [sarcastic]
0283 GitHub stars
03Customizable pronunciation and delivery rules with normalization and language bias
04MacOS-style 'say' syntax for intuitive CLI voice generation
05Full support for ElevenLabs v3 expressive models and v2.5 high-speed models
06Local audio playback and file export capabilities for seamless integration
Use Cases
01Automating the generation of high-quality audio content for documentation or tutorials
02Testing and previewing ElevenLabs voice configurations directly from the CLI
03Creating character-driven voice responses for AI assistants and roleplay