smart:deess

The content-aware de-esser

Where other de-essers just reduce volume, smart:deess automatically detects and reduces harsh sibilance with precision. Get smooth, natural vocals without tedious frequency hunting.

€129.00

Try

Thomann

4.5 / 5

Audio Deluxe

5 / 5

Plugin Boutique

Based on 116 ratings

4.9 / 5

Instinctual sibilance
and plosive removal

The content-aware approach

Simply tackling sibilance and plosives

smart:deess analyzes the signal’s actual content – not just the level of one frequency band – before it decides what to do. As soon as you load the plugin on a channel, smart:deess builds a ‘voiceprint’ of the input voice signal and starts balancing any sibilants and plosives that are present. Your job then is to review the analysis and refine the results. smart:deess allows you to spend time on getting the sound you want, rather than correcting the sound you don’t want.

The power of AI

Looking deeper than ever before

smart:deess identifies specific individual phonemes – S, Z, Sh, Ch, T, P… – in real time, determining the exact start and end point of each sibilance without you having to set a threshold. The entire sibilant is then processed, rather than just the loudest part, making the final result far more natural sounding. Each phoneme type is identified and processed independently, an “Ess” is treated differently than a “Ch”, which is treated differently than a “T”. The result is as though the original recording had simply been better balanced.

Advanced spectral processing

Shape and refine

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 at a deeper level. Use the Color controls to tune the sibilant character (soft, balanced or sharp) and achieve the desired balance without losing edge. What’s more, dull and lisping sibilants can be revived and given new life by applying smart:deess' spectral processing.

This video is hosted by YouTube. Loading it means accepting marketing cookies.

Voices of the industry

Press & Review

White Sea Studio

English

Logic Pro Life

English

Jonas vom Recording-Blog

Folia Soundstudio

Audio Toolshed

Eric Kauffmann

Arkitek

Mixing with Mike

Supercy

MixbusTV

Higuera Producciones

Mix Artistry Official

English

nueko - music magazine

The Note Music Story

Gearspace

Junya Watanabe

SaiRecords

Audio Plugin Guy

Reaper Brasil

Oli Beaudoin

The full package – including smart:deess

Bundles

€399.00

smart:bundle

Six intelligent audio plug-ins for EQ, compression, limiting, reverb, gating and de-essing. Speed up everyday mixing with cutting-edge processing.

Try Add

€599.00

Studio Bundle

Complete sonible audio plug-in collection for mixing, mastering and metering. Get intelligent processing and specialist tools for your whole workflow. Save 54% by buying the bundle.

Try Add

€249.00

vocal:bundle

Get three AI-powered tools for perfect vocals – EQ, de-essing and reverb. Shape tone, control sibilance and add space for polished vocals with a faster workflow. Save 36% by buying the bundle.

Try Add

Why does smart:deess need to analyze the signal before processing it?

When de-essing, smart:deess analyzes the signal’s actual content – not just the level of one or multiple frequency bands – to make decisions. Since each person has their own voice characteristics, smart:deess asks you to playback some audio to learn a short vocal fingerprint. This vocal fingerprint – we also call it voiceprint – is like a fingerprint of the vocal characteristics of the analyzed person. Once a voice has been analyzed, smart:deess adapts its internal processing to match the observed characteristics.

When working with a new speaker or singer, you should therefore always re-analyze the signal to make sure that the processing adapts accordingly.

Can I use smart:deess to reduce the harshness of instruments like Hi-Hats?

smart:deess was not designed to reduce the harshness of instruments. Unlike conventional de-essers, smart:deess does not simply look at the signal energy in specific frequency regions - but the plug-in actually identifies the exact position of individual sibilants (e.g. S, Z, SH, CH, ...) and plosives (e.g. P, T, K, ...). Obviously, this detection of phonemes only works for voice and smart:deess will not be able to detect and process any (meaningful) phonemes in instruments.

Can I use smart:deess on a full mix?

smart:deess was designed to work on individual vocal or speech tracks and on vocal busses. As the plug-in tries to identify different phonemes in real-time, the detection quality decreases with the amount of "non voice content" in a signal. While the detection may still work for relatively simple mixes or recordings with some cross-talk or noise, smart:deess will typically have a hard time identifying individual phonemes in full mixes.

Does smart:deess have a processing latency?

Yes. As smart:deess uses a neural network to identify different phonemes, the plug-in needs a look ahead of approximately 70ms to perform this real-time detection. That means that the plug-in cannot be used in live situations when zero-latency processing is needed.

See all FAQs

Voices of the industry

Testimonials

– Alex Solano

Immersive Audio Specialist | Alex Pro Mix

– John Nathaniel

Producer, composer & mixer

Download Manual (PDF)

AI-powered detection of S, Z, Sh, Ch, T and P sounds
Automatic voiceprint creation
Threshold-free sibilance processing
Spectral de-essing
Dedicated plosive processing
Full-phoneme processing instead of peak-only reduction
Independent processing for different phoneme types
Sibilant Color control: Soft, Balanced and Sharp
Adjustable Suppression and Shaping

smart:deess

Instinctual sibilance
and plosive removal