AI Blocks › Build and ship software
Audio quality metric picker
Give it a sound file. Get loudness, noise and speech quality scores with the right metric chosen.
Audio quality metric picker is a free AI skill for the job "Build and ship software". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · BSD 2 Clause licence · Made by MathWorks · Level: advanced
Made by MathWorks. See the original on GitHub; we copied it as it is, with its licence.
What it does
The right way to measure a sound, chosen before any maths is done. Say what you care about: loudness, background noise, speech clarity or room echo. The AI picks the proper MATLAB Audio Toolbox function and standard. It does not write its own version. It covers loudness, roughness, speech scores like STOI and ViSQOL, noise ratings, broadcast loudness in LUFS, reverb time and tones. It asks questions before it computes. It shows how to calibrate with your microphone's sensitivity and how to convert units. It also fixes common mistakes, such as asking for a function that does not exist. PESQ requests are sent to other options. You need MATLAB.
You give it
- Your sound file or recording details
- What you want to measure
- Microphone sensitivity (optional)
- The standard you must meet (optional)
You get
- The right function and standard for the goal
- Calibrated MATLAB code
- Scores for loudness, noise or speech quality
- Unit conversions
Use it when
- You need to check a broadcast file meets loudness rules.
- A speech recording sounds muffled and you want a number for it.
- An office's noise level has to be rated against a standard.
- You have a microphone's datasheet and need correct sound levels.
How to use it
- Add it to your AI once: download it and add the folder to Claude, ChatGPT or Codex as a skill.
- Ask for the job in your own words. Your AI opens the skill when it fits.
- It works best when your AI can run MATLAB with Audio Toolbox.