Copy link to clipboard
Copied
With AI-powered Enhance Speech now in Premiere Pro (beta), you can magically remove noise and improve the quality of dialogue with one click, so it sounds as if it were recorded in a professional studio! We need your feedback to optimize this feature further through adding a comment below and completing a short survey.
Here’s how to use it:
Open the Essential Sound panel and select a clip containing speech in your sequence. Click on “Dialogue."
Then, just click the “Enhance” button. When processing is complete, you can adjust the amount of enhancement using the Mix Amount slider. This slider allows you to mix your raw audio with the enhanced audio, allowing natural background noise to come through.
What kind of recordings work well with Enhance Speech?
Audio that is recorded with a low-quality microphone (phones, online meetings, on-camera mics) tend to be improved with Enhance Speech. It does not always work well with:
How does it work?
The version of Enhance Speech within Premiere Pro (beta) is the same feature that has been available online via Adobe Podcast. However, Enhance Speech within Premiere Pro (beta) has been optimized to perform locally on your machine, allowing you to run Enhance Speech on an unlimited number of clips. Unlike Adobe Podcast’s service, no internet connection is required. The model is not trained on your usage.
As indicated in the name, this won’t work with music, sound effects, or ambient audio. And like most AI-powered features, it requires a performant system; processing times may vary. (See Premiere Pro’s recommended hardware specifications.)
Please check out our full FAQs for this feature for more details.
What we’d love to know from you:
AI models are evolving fast and voice recordings have many unique variables we can’t always predict in our testing. We need your feedback to learn more about how you’re using Enhance Speech so we can further optimize it for all types of voices.
How has this been helpful? Have you run into any enhancement issues that prevent you from using the feature? If you’ve run into performance issues, please tell us what kind of computer you’re using.
Complete this survey and leave us feedback below.
I installed the beta just to use this feature, but when I click enhance there is no progress bar at all and nothing happens. I can change the mix amount, but this has no effect. Even when rendering out a file there is no change to the audio. Anyone else run into this?
I'm in 24.1.0 Build 77 on a iMac running Ventura 13.5.1 (22G90).
Copy link to clipboard
Copied
Cool feature. Been playing around with old FDR speeches to see how it reacts to archival stuff. Pretty interesting results. Some limitations/feedback below:
Bug/Quirk
UI:
Copy link to clipboard
Copied
Would love to see the FDR speeches! Are you uploading them anywhere?
Copy link to clipboard
Copied
I can't figure out how to download the beta...it seems like it's been pulled or unavailable to me. I don't see a Beta apps tab in my creative cloud desktop app at all. There is a prerelease tab but the only option is for illustrator. What's going on here? Even when I click on the "Get the Premiere Pro (beta) app" button, it opens CC but gives me a blank screen...something has been changed since the article written on 10/10 https://helpx.adobe.com/premiere-pro/using/premiere-pro-beta.html
Copy link to clipboard
Copied
I installed the beta just to use this feature, but when I click enhance there is no progress bar at all and nothing happens. I can change the mix amount, but this has no effect. Even when rendering out a file there is no change to the audio. Anyone else run into this?
I'm in 24.1.0 Build 77 on a iMac running Ventura 13.5.1 (22G90).
Copy link to clipboard
Copied
Same. I even installed it on my Windows computer because Premiere said it needed OSX 14 to run better. It doesn't seem to do anything on Windows 10.
Copy link to clipboard
Copied
A technical question: If I am using the Enhance Speech feature and follow up by using the transcription feature in Premiere Pro for subtitles purpose; do I need to render and replace the original audio or will Premiere Pro know to transcribe from the 'Enhance Speech' audio?
Copy link to clipboard
Copied
Tested on build 6 (I think) and worked really nicely but running into constant problems with it on build 7. Either casues app to become very unstable or unable to create audio renders, not useable currently (at least on my machine!)
Copy link to clipboard
Copied
I like the new feature and the integration in Premiere.
But it seems there are a few things that need to be optimized. I have a recording which is not to bad, but after using the enhance feature some words are altered and sound totally different than before. Letters of a word are changed (for example like: Hello in Heko) especially when there is a break after a word. Sadly the words don't make sense, so this feature is not read to use.
Copy link to clipboard
Copied
I woud like to use it but after I analyze a track which takes a few minutes, when I go to cut the track Beta reanalyzes the track again. It makes the editing process impossible. It would make sense to me to analyze a track once in the beginning, then make your cuts but that doesn't seem possible with this beta.
Maybe enhance audio in Audition before importing into Premier?
Copy link to clipboard
Copied
Crashes as soon as I tag as "Dialogue." Three times out of three.
Copy link to clipboard
Copied
Nothing happening for my audio. 'Enhancing Speech' stays at 0%.
Copy link to clipboard
Copied
Impressionado com a praticidade na correção de áudio... este novo recurso veio para facilitar ainda mais as edições e o melhor de tudo é que as alterações sempre preservão a naturalidade da voz.
Copy link to clipboard
Copied
This feature is useless for russian\ukrainian or any other Slavic language since it adds an american accent to words (and even subsitutes slavic words to english ones sometimes) especially in those parts of the speech where the sound quality is worse. Seems like Adobe uses no slavic models of speech to train enchance speech Ai. So far this feature is useless for 400 000 000 people...
Copy link to clipboard
Copied
WOW! Played with this for 5 minutes on some very challenged dialogued.......Night and day difference. I'm ALL IN on this.
Copy link to clipboard
Copied
The Enhance Audio feature makes my audio, which is recorded both by an external mic and camera mic, sound like it's underwater if it's anywhere above 0.3. Tested with all sorts of different clips.
Copy link to clipboard
Copied
Hi,
Can anyone help me. I tried to use this feature on my Mac but if i tried to do anything else the whole mac would freeze (even just browsing on the web). I then tried this feature on a rubbish laptop which it worked i just had to leave it for several hours. I then moved the file back over to my Mac to finish editing, the enhanced speech however hasn't moved over and the subject sounds the same as originally.
Is there a way to move the enhanced speech across machines as the laptop is currently stuck on trying to prepare audio (8 of 201) which has taken 15 minutes.
My mac spec are: 3.8 GHz 8-Core Intel Core i7, AMD Radeon Pro 5500 XT 8 GB, 128 GB 2667 MHz DDR4
Laptop specs are: 11th gen i5, 8GB of ram.
Thanks
Copy link to clipboard
Copied
I'm unable to use enhance speech on a fairly standard stereo audio file. Does ES not support 96khz? Seems to be greyed out!
Windows 10
AMD 3960
256GB Ram
PrPro 24.2.1
Copy link to clipboard
Copied
Attempted to clean up some spoken word audio, not too noisy to begin with. The PP version was noticeably inferior to the clip uploaded to the podcast enhance model. Curious if this is performance related (M1 Max, 64gb RAM) or if they are different models. Waves Clarity Vx also outperformed the PP version of Enhance Speech.
Copy link to clipboard
Copied
I love the enhance speech feature to remove background noise, but it seems like the compression is set too high and it makes lower volume spoken words sound distorted and unnatural. Is there a way the compression can be adjusted manually?
Copy link to clipboard
Copied
Will you be fixing the bug with intel chip Macpros. Works great with the M chip, but locks the computer up if trying this feature on the intel chip.