Sonible Releases smart:deess

US The first AI de-esser to combine phoneme detection with advanced spectral de-essing. 30/10/23

sonible has released smart:deess, which they describe as a step forward in de-essing and plosive removal technology. A spokesperson told us, "Thanks to the artificial intelligence powering its detection and spectral processing shaping the respective phonemes rather than just 'turning them down', smart:deess delivers more natural results."

Here's more details direct from sonible...

smart:deess tackles both sibilance and plosives at once, making it an essential tool for solving the two most common problems in vocal recordings. Thanks to its AI-powered processing, the plugin has only to be loaded on a track for it to start fixing a vocal recording in a way that's tailored precisely to the source audio's characteristics. smart:deess also provides a wide range of options for customizing its shaping strength and character.

What could AI possibly do to improve de-essing?
Quite a lot, actually! smart:deess identifies specific individual phonemes – S, Z, Sh, Ch, T, P... – in real time and determines the exact start and end point of each sibilance without users having to set a threshold.

With smart:deess, the entire sibilant is processed, rather than just its loudest peak, making the final result far more natural sounding. As each phoneme type is identified and processed independently, the result is as though the original recording had simply been better balanced.

Beyond conventional de-essers
Other de-essers are just automatic volume controls. smart:deess does contain a broadband component, but it also draws on additional spectral processing to shape and refine harsh sounds. Use the Color controls to tune the sibilant character (soft, balanced or sharp) and achieve the desired balance without losing any edge. Dull and lisping sibilants can be revived and given new life by applying smart:deess' spectral processing.

With smart:deess, we pulled out all the stops – our neural network technology and our unique spectral processing – to create a de-esser that is so much more than a standard tool. In some respects we went back to the roots of the initial function of a de-esser, however, smart:deess delivers more of everything – more reliability, more precision, more customizing and, most importantly, more natural results." Alexander Wankhammer, co-founder and CMO of sonible.

smart:deess key features

The most natural-sounding de-esser thanks to its AI technology

De-essing and plosive reduction in one tool

Real-time phoneme detection to identify sibilants and plosives

Harsh sounds can be shaped, rather than 'just turned down,' via spectral processing

Processes the entire sibilant from start to finish, without the need to set a threshold

Handles different phonemes – S, Z, Sh, Ch, K, T, P – each with distinct processing

Will automatically "re-ess" to improve any 'dull' and 'lisping' phonemes

Huge range of options for customizing the processing

Pricing and Availability:
smart:deess is now available at an introductory price of € 89,- (reg. € 129,-) until December 1, 2023.
All prices are inclusive of VAT. Personalized upgrade pricing is available for existing sonible customers.

More information: