VoiceGate - Noise Reduction
Professional Speech Restoration
VoiceGate is a Machine-Learning based audio plug-in which can be used to reduce noise from speech and vocal recordings in real-time. An artificial neural network has been trained on more than 100 hours of audio data to learn the characteristics of human speech. The plugin can automatically adapt to a variety of different noise types and lets you easily control the amount of noise reduction you need.

"VoiceGate is a fast, powerful tool that has saved a lot of takes without interrupting my workflow."
Jay Rose, CAS

DEEP NEURAL NETWORKS
continuously improving algorithm
The underlying algorithm will be continuously improved. If you stumble upon some speech or noise data on which it does not work as expected let us know and send us the audio material to mail@accentize.com. We will include it in the training procedure and the next version will work even on those signals.
HIGHLY OPTIMIZED
efficient computation
Artificial Neural Networks are known to require lots of computational ressources. However, the VoiceGate algorithm is highly optimized to run efficiently also on average workstations in real-time!
ALGORITHM SELECTOR
optimized for different use-cases
Choose between different algorithms using the Algorithm Selector feature. In addition to the default algorithm, you can download newly available algorithms easily to your machine and use the best processing option for every noise scenario you are dealing with.
SPECIFICATIONS
Supported samplerates: 44.1kHz,48kHz,88.2khz,96kHz,192kHzSupported channel layout: Mono/Stereo
Plugin formats: AAX, VST3, AU



MINIMUM SYSTEM REQUIREMENTS
Windows 7 (64-bit), 4 GB RAM, Dual-Core CPU 2GHzMax OS X 10.12, 4 GB RAM, Dual-Core CPU 2GHz
An active internet connection is required for starting in Trial Mode (always) and activating (just once).
Compatible DAWs
Cubase, Nuendo, ProTools, Reaper, Ableton and more...



