ElevenLabs TTS Tool

About

This skill provides a professional-grade command-line interface for ElevenLabs text-to-speech synthesis, allowing developers to seamlessly integrate high-quality AI voices into their local environments and automation pipelines. It enables full control over speech generation, including the ability to play audio directly or save to various file formats, while supporting advanced features like emotional expression tags and SSML pause control. Beyond synthesis, the tool offers robust utilities for managing ElevenLabs subscription quotas, exploring dozens of premium voices with detailed filtering, and comparing model characteristics to optimize for latency or quality.

Key Features

• Precise speech pacing management through SSML break tags for natural-sounding pauses.
• 0 GitHub stars
• Text-to-speech synthesis with support for direct audio playback and multiple file formats.
• Extensive voice and model discovery with filtering by gender, age, accent, and quality.
• Advanced emotion and delivery control using v3 model audio tags like happy, excited, or whispered.
• Integrated subscription tracking to monitor character usage, limits, and historical trends.

Use Cases

• Integrating professional text-to-speech capabilities into shell-based workflows and pipelines.
• Automating the generation of high-quality voice-overs for content creation and audiobooks.
• Implementing audible notifications for build successes or failures within Claude Code hooks.