Modular Voice Studio download

Modular Voice Studio is an open-source, ultra-low-latency, node-based digital signal processing (DSP) environment engineered specifically for voiceover artists, streamers, podcasters, broadcast engineers, content creators, and audio purists.

Built from the ground up with C++20 and the JUCE 8 framework, Modular Voice Studio combines the visual flexibility of a modular synth rack with studio-grade vocal processing. Build custom audio routing chains in real time with zero phase artifacts, deep-learning noise suppression, surgical spectral correction, and immersive 3D binaural positioning.

Features

Real-Time Modular DSP Canvas: Freely connect and route unlimited vocal processing modules with dynamic cable physics and zero internal latency.
AI-Powered Noise Suppression: Integrated deep-learning RNNoise neural network for eliminating background fan, AC, and room hum without robotic artifacts.
Linkwitz-Riley LR4 Crossover (24 dB/oct): 3-way frequency splitting (Low/Mid/High) for zero-phase multi-band processing and summing.
Comprehensive Vocal Suite: 7-Band Parametric EQ with RTA, VCA/Optical Compressor, True-Peak Limiter, Saturation, Aural Exciter, and Vocal Doubler.
Interactive 3D Binaural Spatial Audio: Realistic Cartesian 3D room simulation with listener head-tracking and multi-band spatial positioning.
Transparent Dynamic De-Esser: Surgical multi-band spectral sibilance suppression targeting harsh consonants (s, sh, ch, z).