When to use

• When you need to convert text to speech locally (no API keys)
• When you need to generate audio from long documents (books, articles)
• When you need seamless audiobook rendering without pop artifacts
• When you need fast offline TTS rendering (20-50x real-time)

kokoro-tts-tool Skill

Purpose

This skill provides access to the kokoro-tts-tool CLI for local text-to-speech synthesis using the Kokoro-82M model. Runs entirely on-device with ONNX runtime, optimized for Apple Silicon.

When to Use This Skill

Use this skill when:

• Converting text to speech without cloud APIs
• Generating audio from markdown/text documents
• Creating audiobooks from long-form content
• Needing 60+ voices across 8 languages