Sag ElevenLabs Text-to-Speech
Generates high-quality ElevenLabs audio responses using a Mac-style command-line interface for expressive text-to-speech.
The sag skill integrates ElevenLabs text-to-speech capabilities directly into the Claude Code environment, allowing users to generate expressive audio from text using various models and voice profiles. It supports advanced features like emotional tags, pronunciation overrides, and the ability to output media files for interactive voice responses, making it an ideal tool for developers building voice-enabled applications or those wanting a more immersive assistant experience through natural-sounding AI voices.
Key Features
01Advanced delivery control using tags like [whispers], [laughs], and [excited]
02Seamless ElevenLabs API integration for high-fidelity speech synthesis
03Automatic normalization options for handling numbers, units, and URLs
048,364 GitHub stars
05Support for multiple models including eleven_v3 (expressive) and eleven_flash_v2_5 (fast)
06Mac-style 'say' UX for familiar and intuitive command-line interaction
Use Cases
01Generating professional voice-overs for applications or content directly from the terminal
02Automating the creation of localized audio assets for software documentation or tutorials
03Prototyping interactive AI personalities with specific emotional tones and delivery styles