Automates text-to-speech workflows to generate high-quality audio, manage voice libraries, and monitor usage within Claude Code.
This skill integrates ElevenLabs' advanced text-to-speech capabilities directly into Claude Code via the Composio MCP. It enables developers to programmatically generate natural-sounding audio from text, browse and select from an extensive library of voices, and manage subscription credits seamlessly. Whether you are producing voiceovers, creating accessible content, or building voice-enabled applications, this skill provides the tools to handle everything from model selection to low-latency audio streaming and historical record retrieval.
主な機能
01Subscription and credit monitoring to manage usage limits effectively
02Real-time audio streaming for low-latency playback delivery
03Historical audio retrieval for re-downloading previous generations
04Extensive voice library browsing with filtering by gender, accent, and use case
05High-fidelity text-to-speech generation with support for multiple models
0611 GitHub stars
ユースケース
01Building accessibility tools that convert documentation into natural speech
02Automating voiceover production for marketing videos and tutorials
03Developing interactive AI agents with low-latency verbal communication
