Use assistive AI audio tools to polish your sound mix

Split overlapping voices, clean up noisy dialog, and generate a soundscape without leaving your timeline.

Published November 10, 2026

00:01

Introduction and meet Sarah John

[Sarah John]: If you ever had to record an interview or a podcast between multiple people with just one microphone, you know the pain of trying to edit that into something listenable.

I'm Sarah, and as someone who has dealt with that exact situation, I still have nightmares about working with all that crosstalk and background noise.

But now with Adobe's Enhanced Audio features, separating multiple voices on a single recording into separate editable tracks can be accomplished with the click of a button.

I'm going to show you how to not only do this, but also how to automatically clean up dialogue and create contextual sound effects and ambiance, all without leaving your Premiere timeline.

00:32

Split one recording into a separate track for each speaker

Today, we're working on a sample podcast episode that was recorded with one microphone in the same room with lots of variation in audio volume between the two speakers.

[Podcast Audio] [Lauren]: Hello, and welcome to our podcast about Adobe Premiere Audio Tools.

[Sarah]: I'm Sarah.

[Lauren]: And I'm Lauren, and we're really excited to talk to you about some new audio tools that are coming straight to Premiere.

[Sarah]: Let's clarify.

You're going to be talking about them because you're the expert.

[Lauren]: That is true.

That is true.

[Sarah]: I'm just here to listen and absorb all the information.

[Lauren]: Yeah.

Yeah, yeah, yeah, yeah.

[Podcast audio ends] [Sarah]: First things first, let's get the audio track separated out so we can start editing.

With the audio selected on the timeline, we're going to go up here to the Properties panel and select separate crosstalk.

A dialogue box will appear informing us how many credits this will cost us.

We'll go ahead and click Separate.

Premiere will now create the separated clips for us.

Three different clips will be created, one for each speaker and one for any background sounds.

Once the process is finished, we can work with the clips as normal.

[Podcast Audio] [Lauren]: In an interview.

[Sarah]: We're recording it in this case.

[Lauren]: Yeah.

[Sarah]: Not filming, 'cause why?

We don't need to.

Nobody needs to see what we look like right now.

[Lauren]: If it's got video, it's not a podcast.

That's how I feel.

[Sarah]: I mean I agree.

A lot of other people would maybe not.

[Lauren]: Yeah.

But anyway.

[Podcast audio ends] [Sarah]: The original clip will still be right here on the timeline, automatically muted but unchanged in case we need it again later.

Now, before we start trimming our clips down into what we want to use,

01:52

Clean up dialog and set the balance of voice, music, and ambience

we'll improve the sound quality with the Enhance Audio tool.

With a clip selected, we're going back to the Properties panel and toggle on the Enhance Audio effect.

Depending on the clip length and the internet connection, this can take some time, and the results will vary depending on the quality of the original clip.

It's still best practice to make sure we're recording the highest quality audio we can before we even disconnect the microphone.

Enhance Audio can make a good recording sound great and a rough one sound much better, but it can't work miracles.

Audio recorded on a potato in a wind tunnel will still sound like a potato, just a noticeably cleaner one after processing.

Once the clip is processed, we have access to all these different enhancement sliders.

We can adjust speech volume and clarity as well as change the amount of reverb on the speaker's voice.

We can also adjust different aspects of the sound coming from the background of the recording.

In this instance, these sounds were all separated out into the track down here, but if a clip was recorded in a louder environment, this would come in handy.

If there's music playing, we can make that louder or softer.

We can also change the volume of any sound effects and adjust how much ambient noise there is, such as the sound of a crowd, a running air conditioner, things like that.

03:06

Generate sound effects for a silent clip, one layer at a time

Another way we can work with audio in Premiere is to build out a soundscape from scratch right here on the timeline.

For example, we may have a video clip with no audio or audio that is unusable for whatever reason.

For these cases, we can click here to open the Generative Media tool and then drag underneath the clip that needs audio.

This stock clip needs some hockey game sound effects, so we're going to prompt it for the sound of multiple players ice skating, sticks handling the puck, the crowd cheering, and the goal horn going off when the goal is scored.

For this first effect, we entered the prompt, "Hockey players skating across an ice rink, hockey sticks handling the puck.

The player with the puck shoots and scores, and their team gathers to celebrate at the boards."

We're going to build each of these effects on their own track.

Every time the generation is complete, we'll have four different options to choose from.

If none of those are to our liking, we can adjust the prompt to give more direction and generate it again.

There can be some trial and error to this if it doesn't quite understand what we're asking for.

For example, here we asked for a hockey goal horn, and it gave us [car horn honks] something completely unlike an actual hockey goal horn.

A few tries later, "Deep train horn going off for five seconds" got us a sound effect that fits.

[Crowd cheering] [Train horn blaring] And there we go, a mini soundscape built right on the timeline, a great tool to have in a pinch.

Now that you've seen these audio tools in action, you have the option to put them to work for you in your own audio editing workflows.

Thanks for watching.

Note: Sample files provided are for practice purposes only. See terms.

What you’ll learn

Split one recording into a separate track for each speaker

Overlapping voices on a single microphone are hard to edit around. Select Separate Crosstalk in the Properties panel and Premiere creates a clip for each speaker and one for background sounds. The original stays muted and unchanged on the timeline.

Clean up dialog and set the balance of voice, music, and ambience

Turn on Enhanced Audio in the Properties panel, then adjust speech volume, clarity, reverb, music, sound effects, and ambient noise.

Generate sound effects for a silent clip, one layer at a time

Use the generative media tool to prompt for each sound on its own track. Every generation gives you four options to choose from.

Tip: Record the highest-quality audio you can. Enhanced Audio can make a good recording sound great and a rough one much better, but it can’t work miracles.

Instruction by: Sarah John
Adobe Stock Contributor: Dariia; Sukarman

Try these tutorials with Premiere Pro

Create and edit films and video.

View all plans

Cookie Settings

General information

Cookies are small text files stored by your web browser when you use websites. There are also other technologies that can be used for similar purposes like HTML5 Local Storage and local shared objects, web beacons, and embedded scripts. These technologies help us do things like remembering you and your preferences when you return to our sites, measure how you use the website, conduct market research, and gather information about the ads you see and interact with.

If enabled:

We can improve your experience by tailoring the site and the content to things we think might be of interest
We can better keep track of your preferences — like what language you prefer to use
We will better understand your likely interests so we can provide you more relevant Adobe ads and content on non-Adobe websites and in non-Adobe apps
It will help us improve the performance of our website and those of our partners who use the Adobe Experience Cloud

If disabled:

We won’t be able to remember you from session to session so the experience may not be tailored to your interests
You’ll still have access to the content of the site but certain features that depend on cookies may not function
You’ll still see ads, they just may not be as relevant to you

General information

Cookies are small text files stored by your web browser when you use websites. There are also other technologies that can be used for similar purposes like HTML5 Local Storage, web beacons, and embedded scripts. These technologies help us do things like remembering you and your preferences when you return to our sites, measure how you use the website, conduct market research, and gather information about the ads you see and interact with.

If enabled:

We can improve your experience by tailoring the site and the content to things we think might be of interest
We can better keep track of your preferences — like what language you prefer to use
We will better understand your likely interests so we can provide you more relevant Adobe ads and content on non-Adobe websites and in non-Adobe apps
It will help us improve the performance of our website and those of our partners who use the Adobe Experience Cloud

If disabled:

We won’t be able to remember you from session to session so the experience may not be tailored to your interests
We’ll still count your use of our site and services
You’ll still have access to the content of the site but certain features that depend on cookies may not function
You’ll still see ads, they just may not be as relevant to you

View transcript

What you’ll learn

Split one recording into a separate track for each speaker

Clean up dialog and set the balance of voice, music, and ambience

Generate sound effects for a silent clip, one layer at a time

Try these tutorials with Premiere Pro