audio-quality

logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.

Variations of L1 SNR Loss function for training audio source separation machine learning models

Unofficial PyTorch implementation of "Moises-Light: Resource-efficient Band-split U-Net For Music Source Separation"

Collection of community-made presets for PulseEffects tailored for TUXEDO laptops.

MicLock fixes bad Mac Bluetooth headphone sound quality by preventing AirPods, Sony WH-1000XM and other headsets from becoming the default microphone.

The code for the MAPSS measures for source separation evaluation (ICLR, 2026)

Repository for subjective and objective evaluation of source separation algorithms

k6 extension for SIP/VoIP load and functional testing: scripted subscribers call each other through the PBX, with RTP, one-way audio detection, voice quality scoring and call recording

Stop AI slop

Bulk upgrade your music library from lossy to lossless FLAC via Soulseek and SLSKD

best stereo plugin for better discord

Desktop audio spectrum analyzer: spectrograms, an automated lossless/transcode verdict, whole-library audit with a persistent cache, duplicate detection and folder diffs by acoustic fingerprint, encode comparison, and integrity/loudness checks. Avalonia / .NET.

Seekbar for foobar2000 that shows the whole track as a spectrogram, waveform, live spectrum or loudness map, with standards-compliant measurements (EBU R128 loudness, true peak, DR)

Create a Dolby.io Frontend Application To Display Waveform With Wavesurfer.js And Interactive Elements Using Konva In SolidJS

A pure Python implementation of Google's ViSQOL (Virtual Speech Quality Objective Listener) for objective audio/speech quality assessment.

CLI-first deterministic audio/video quality gate. Catches corrupted, invalid, or low-quality media before it reaches humans.

Sonaris, the audio quality analyzer for Windows: loudness (EBU R128), true peak, dynamics, spectrum and stereo measurement, with delivery checks and evidence reports.

Hallucination detection for voice agents — the independent audit layer for your STT, TTS, and full-duplex pipeline.