Hush Pro: an AI-powered AudioSuite plugin for dialogue repair

[Ian Sampson]

Hi everyone!

 

Back in March I posted about my app Hush, which uses machine learning on Apple Silicon to remove noise and reverb from spoken audio.

 

A lot of folks asked me to make an AudioSuite plugin to speed up the workflow in Pro Tools — so I did. It’s called Hush Pro, and comes with a bunch of new features designed specifically for audio post-production. The plugin includes two separate modes — or sub-plugins — that use the same engine under the hood but support different workflows. Hush Mix lets you rebalance dialogue, noise, and reverb with a mixer-style UI, previewing the results in real time. Hush Split renders all three elements as separate clips for more fine-grained, non-destructive edits.

 

The Pro version delivers even cleaner audio than the standalone Hush app, with better handling of outdoor ambience, highly reflective rooms, overlapping voices, and non-verbal sounds like laughter. Under the hood, the plugin uses a new, more powerful AI model, taking advantage of the faster GPU on M-series Pro, Max, and Ultra chips. The model will continue to evolve with future updates — so if you find a type of voice or noise that it struggles with, let me know and I can very likely improve it.

 

Other plugin formats (AU and VST) are in the works too. They’ll be free updates for Pro users, whenever they’re available.

 

Compatibility

Besides Pro Tools, you’ll also need an Apple Silicon Mac and macOS Monterey or Ventura. (Hush Pro doesn’t officially support macOS Sonoma yet, and I recommend against updating until Apple has ironed out a few wrinkles.)

 

Price & Availability

Check out the website for more info, a quick video demo, and a 21-day free trial. The full version is $249, or $179 if you’re upgrading from the original app. A one-time purchase includes minor updates and bug fixes (up to version 1.x). No DRM (iLok, license key, etc.): just a simple installer. Both single-user and multi-seat licenses are available.

 

If you have any questions, feel free to post them here or shoot me an email at ian@hushaudioapp.com.

 

Thanks!
Ian

 

[The Documentary Sound Guy]

That demo sounds very impressive!  Not a post guy myself, but it's useful to know what capabilities are out there.

If I had an Apple or ProTools, I'd try it out for sure.

[BAB414]

How well does it work for dramatic/emotional scenes? Any uncanny valley?

[Werner Althaus]

I'm still running ProTools 11.3.2 on a RADAR Studio workstation and I can't (and don't want to) upgrade due to the RADAR folks strongly discouraging updating to a higher Windows OS ( It's running a stripped down version of 8.1)

Will Hush Pro work with my old ProTools version and windows OS?

[Ian Sampson]

1 hour ago, BAB414 said:

How well does it work for dramatic/emotional scenes? Any uncanny valley?

 

It should work pretty well! It’s trained to handle dynamic vocal sounds (so laughter, sobbing, etc.) as well as ordinary speech. And it’s purely subtractive, filtering out unwanted sounds — it doesn’t re-synthesize or re-generate the voice, so low risk of sounding robotic or falling into the uncanny valley.

 

35 minutes ago, Werner Althaus said:

Will Hush Pro work with my old ProTools version and windows OS?

 

Unfortunately no — at the moment, Hush Pro only works on macOS.

[humbuk]

Does it work better than Clarity by Waves?

[BAB414]

How long until we're out of jobs? 😅

[Ian Sampson]

11 hours ago, humbuk said:

Does it work better than Clarity by Waves?

 

I’m biased of course, but I’ve A/B-ed the two extensively and Hush Pro has significantly fewer artifacts on pretty much all the examples I tested. Of course, it may well depend on the material, so always good to demo with your own samples.

 

Clarity is pretty impressive for a real-time, CPU-based plugin. Hush Pro takes a different approach: it’s mainly an offline processor (with real-time previews supported in AudioSuite), which means it can look at the whole audio file at once and make better use of context. And it runs on the GPU, so it has way more processing power available. Obviously a non-starter if you need a real-time insert, but on sound quality alone it’s tough to beat.

 

4 hours ago, BAB414 said:

How long until we're out of jobs? 😅

 

Not anytime soon I hope 😛 As far as AI goes, Hush Pro is pretty limited in scope. It can’t make creative decisions (e.g. about how much noise and/or reverb to take out for a particular scene), and isn’t all that different from traditional NR, except that it sounds really transparent. And I haven’t heard/seen a single AI model yet that doesn’t make mistakes sometimes — so I expect we’ll need humans in the loop for a long time yet.

[inspire]

Hello, well done! It's nice to meet you here, I think you're the author of this App? For Windows, probably the version will never be planned in the future? You could offer your job to some larger companies to ensure that it is sustainable? This would give greater hope that your product will be taken care of if you no longer bother, wish or can't . How difficult it is to keep up with innovations, I think not easy. I have a plugin (Altiverb) and I see the danger here that you cannot keep up with the whole world renewal alone. On the other hand, it gives the uniqueity to be the only hard-maker in the world. Anyway, I will keep you thumb with this unique product.