Sag Text-to-Speech
Generates high-quality AI voice synthesis using ElevenLabs with a familiar Mac-style command interface.
The Sag skill integrates ElevenLabs' state-of-the-art text-to-speech capabilities directly into the Claude Code environment, allowing for instant audio generation and local playback. It supports various ElevenLabs models, including the expressive v3 and low-latency Flash versions, while providing specialized syntax for emotional cues like whispering, shouting, or laughing. This skill is ideal for developers building voice-enabled applications, creating accessible content, or adding distinctive personality to AI interactions through custom-voiced responses.
Características Principales
01Customizable pronunciation rules, hyphenation, and text normalization for technical terms.
02Advanced audio control using v3 tags for emotions like whispering, shouting, and laughing.
03Direct integration for generating and saving voice-reply media files for external use.
0431 GitHub stars
05Instant ElevenLabs TTS generation with local playback support.
06Support for multiple ElevenLabs models including v3, Multilingual v2, and Flash 2.5.
Casos de Uso
01Enabling Claude to provide immersive, personality-driven audio responses using specific character voices.
02Generating high-quality voiceovers for software demonstrations or documentation directly from the terminal.
03Testing and refining speech synthesis parameters and pronunciation for ElevenLabs-based applications.