audio-judge

Community

Automate audio quality assessment of TTS outputs with Gemini

Authormattmireles
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The Skill addresses the issue of evaluating the audio quality of synthesized speech outputs, enabling efficient decision-making regarding TTS acceptability, intelligibility, and comparison with reference clips.

Core Features & Use Cases

  • Automated Audio Assessment: Quickly assesses the quality of audio clips generated from text-to-speech synthesis.
  • Reference Comparison: Enables side-by-side comparisons between synthesized and reference audio clips.
  • Use Case: For a new version of a text-to-speech software, the Skill can automatically check if the audio output matches expectations compared to the standard or previous versions.

Quick Start

To judge the quality of the generated TTS audio, run 'node scripts/run-audio-judge.mjs --clip coreml=/path/to/synthesized_audio.wav --baseline-label reference'.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: audio-judge
Download link: https://github.com/mattmireles/kokoro-coreml/archive/main.zip#audio-judge

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.