Generates high-quality ElevenLabs text-to-speech audio with expressive controls and Mac-style CLI simplicity.
This skill integrates the sag CLI tool with Claude, enabling developers to generate human-like audio using ElevenLabs' advanced models directly within their workflow. It allows Claude to perform text-to-speech tasks, utilizing various voices and expressive tags like whispering, shouting, or laughing. With support for multiple models including eleven_v3 and eleven_flash_v2_5, users can fine-tune pronunciation, add dramatic pauses, and automate audio creation for character-driven responses, accessibility features, or application demos.
主な機能
0111 GitHub stars
02Support for multiple models including high-speed Flash and multilingual v2
03ElevenLabs API integration for professional-grade text-to-speech generation
04Mac-style 'say' UX for intuitive command-line audio playback and saving
05Fine-grained control over pronunciation, pacing, and speech normalization
06Expressive v3 audio tags for emotions including whispering, shouting, and laughing
ユースケース
01Prototyping and debugging ElevenLabs speech patterns and pronunciation directly from the terminal
02Creating character-specific voice responses for interactive AI personas
03Automating the generation of high-quality audio assets for applications or presentations
