Audio Judge

Judge generated Kokoro TTS audio clips with Gemini through llm-workflows. Use when the user asks whether synthesized speech sounds good, intelligible, whispery, corrupt, or acceptable, or when comparing PyTorch reference clips against Core ML / Swift pipeline output.

mattmireles Updated 78 repo stars

File contents

mattmireles/kokoro-coreml commit 665d4d341e

Frequently asked questions

npx get-skill add mattmireles/audio-judge