Production-grade Expo native module wrapping loqa-voice-dsp for audio DSP analysis (FFT, pitch detection, formants, HNR, H1-H2)

Extract formant features such as frequency, power, energy, and bandwidth of formants at syllable or word level from audio sources in a web browser using WebAudio API.

A set of fast primitives for entirely client-side formant detection.

AudioWorklet pitch-shifting with LPC-based formant preservation

PSOLA (Pitch-Synchronous Overlap-Add) pitch shift — pitch-synchronous grains for monophonic voice

Parallel formant filter bank

LPC source-filter pitch shift — repitched excitation residual through the unmodified all-pole vocal-tract filter

WSOLA (Waveform-Similarity Overlap-Add) pitch shift — similarity-search OLA variant

OLA (Overlap-Add) pitch shift — simplest stretch+resample baseline

Hybrid pitch shift — runs phase-lock + WSOLA in parallel, crossfades by transient confidence

Peak-locked phase vocoder (Laroche-Dolson) pitch shift

Sampler-style pitch shift — sinc-interpolated fractional-stride resample (no time preservation)

Canonical phase vocoder (Bernsee/SMB) pitch shift

Transient-aware phase vocoder pitch shift with attack preservation

Library for handling data caching for React Native with expo-cache-manager

The whole synthesizer in one file of C — 270 KB of wasm on the audio thread. A Strudel-compatible engine that does not glitch.

Production-grade voice biometric authentication library with advanced signal processing and anti-spoofing

A synthesizer for whistled speech.

Production-grade Expo native module for audio DSP analysis (FFT, pitch detection, formant extraction, spectral analysis)