ElevenLabs Voice Synthesis (sag)
Integrates ElevenLabs text-to-speech capabilities into Claude Code for high-quality audio generation and expressive playback.
The sag skill enables Claude to generate expressive, human-like audio using ElevenLabs' state-of-the-art text-to-speech models directly from the command line. It provides a Mac-style 'say' interface, allowing users to quickly convert text to audio, manage custom voices, and control delivery styles with emotional tags like whispers, shouts, or sarcasm. This skill is particularly useful for developers building voice-enabled applications, creating high-quality audio content, or adding auditory feedback to automated AI workflows.
主要功能
0118 GitHub stars
02Customizable voice IDs and pronunciation rules with phonetic respelling
03Automated voice character generation for specialized personas
04Support for ElevenLabs v3, Multilingual v2, and Flash models
05Local audio playback and MP3 export with a simple CLI interface
06Expressive delivery tags for emotions like [whispers], [shouts], and [laughs]
使用场景
01Creating high-quality voiceovers for documentation, demos, and presentations
02Providing auditory feedback and status alerts during complex coding tasks
03Generating expressive audio responses for voice-based AI agents