AUTO-ADMIN: Non-MP3, WAV, OGG, SoundCloud, YouTube, Vimeo, Twitter and Facebook links in this post have been protected automatically. Once the member reaches 5 posts the links will function as normal.
Clear Voice Live is a real-time AI voice processor built for live sound. One plugin insert per vocal channel handles four tasks simultaneously: denoise, dereverb, feedback prevention and debleed.
Instead of gating, notching or static EQ, the engine separates voice from everything else in the signal spectrally, frame by frame. Feedback buildup, room reverb, HVAC noise, console fan rumble, crowd bleed and stage spill from drums or monitors get pulled out continuously while the voice passes through clean. This works mid-phrase with no gating behavior or audible switching.
Two processing modes: SOFT for transparent everyday cleanup, HARD for difficult rooms with heavy bleed.
Key specs:
0.0 ms internal latency, 0 ms PDC reported to host
VST3 (Windows), VST3 + AU (macOS, Universal Binary, Apple-notarized)
Windows installer is code-signed
48 / 96 / 192 kHz sample rates
Mono or stereo
GPU-accelerated on Windows via DirectML
~80 MB RAM per instance
Tested in Fourier Audio transform.engine and Waves SuperRack
Voice-only processing. Trained on speech and singing, not useful on instrument channels.
Per-seat licensing, not per-machine. One offline license file, no activation server, no machine binding. Install on all your own machines, one in use at a time per license. No subscription.
Free beta access. Sign up before June 30 and get 21 days of use from your first plugin load. Beta subscribers receive a launch discount code, valid for one month after launch.
https://clearvoice.live (https://clearvoice.live)