Node.js implementation of the MFCC audio speech analysis algorithm.

MFCC — mel-frequency cepstral coefficients (FFT → mel triangles → log → DCT-II)

MFCC-based lip-sync library using WASM and WebAudio based on uLipSync

Structural segmentation — Foote checkerboard novelty over MFCC self-similarity (Foote 2000)

Node.js implementation of the MFCC audio speech analysis algorithm.

A MFCC-based LipSync plugin for Unity using Job and Burst Compiler

A WASM implementation of MFCC using KissFFT and libmfcc

Audio processing, such as pitch detection, fft, mfcc and converting AMR NB/WB to Wave PCM data.

MFCC-based lip-sync library using WASM and WebAudio based on uLipSync

Local speaker-dependent voice command recognition for atypical speech via template matching (DTW over MFCC fingerprints), with per-command confidence + effectiveness metrics and an eco->cloud router. Stores only numeric fingerprints, never raw audio.

A MFCC-based LipSync plugin for Unity using Job and Burst Compiler. Forked to add ASIO low-latency audio input on Windows.

Audio similarity — distance metric between recordings

Calculation of sound parameters

Browser-native audio analysis engine: musical timing, BPM/beat tracking, spectral features, and intelligent loop detection

Mel-frequency triangular filter bank

An audio node/processor for real-time audio-driven viseme detection and lip-sync in browsers.

Spectral features — umbrella for @audio/spectral-* atoms (centroid, spread, flatness, rolloff, flux, slope, crest, zcr)

Audio music segment detection library - Automatically detect music segments from WAV audio files

Client-side SDK for Entros Protocol: sensor capture, TBH generation, ZK proof construction

React components and hooks for VRM AI avatars