Premiere (Beta)

Hey everyone! One of the oldest, most persistent things you've asked us for just landed in Premiere Beta 27.0 (Build 29): New Audio Stretching Modes.Here's the pain we're finally going after. If you've ever needed to re-time a line of dialogue or pull a music bed to fit, you know the drill. You change the speed or duration in Premiere, listen back, and it sounds like a chipmunk or a robot. So you give up, round-trip the clip out to Audition, get a clean render over there, and bring it back. Every single time. That detour has been the default for years, and it breaks your flow for what should be a two-second edit.This changes that. We're introducing new stretching modes that hold pitch through speed and duration changes without the artifacts and the processed, robotic quality you get today. Re-time the clip, keep the pitch, keep the character, and stay on your timeline the whole time.What's New?You now get a choice of stretching modes right inside the Speed/Duration workflow you already

Editors can now generate images in the context they need it. They can describe the image they need, guide the results further using reference frames pulled from their own footage, and generate images that match the look, subject, or composition already established in their edit all using Adobe Firefly or supported partner models. Select a range, choose your model, add optional reference frames, describe what you want, and Premiere inserts the generated image into your sequence.  Generating Images Select the Generative Media Tool from the Toolbar   Drag across any video track or double click a gap to select the duration you want to generate.      Select your model, select any reference images, enter your prompt and generate.   The Generative task bar supports Adobe Firefly Image Models and Partner models. The default model on the Generative task bar for Generate Image is Gemini 3.1 (Nano Banana 2)You can use multiple reference frames per generation. Input frames can be sampled from

We’re excited to introduce a new generative workflow in Premiere. The new Generative Media Tool lets you generate sound effects and video exactly where you need them, directly in your timeline.  Simply select a range in your timeline, describe what you want, and you can generate media directly into your edit. Whether you need missing ambience, a custom sound effect, b-roll, a cutaway or an establishing shot, you can stay focused on editing without switching applications. To add the visual context of your project, use the eyedropper to sample reference frames without leaving the timeline.   Generate Sound Effects in ContextNow you can generate custom sound effects directly in the Premiere timeline.Select any audio range, describe the sound you want, and generate multiple variations that match the duration of your selection.Need more control? You can use your voice to guide the timing and intensity of the sound effect, making it easier to create sound effects that feel natural in your ed

Hey everyone! We're excited to share a new addition that just landed in Premiere Beta 26.5.0 Build 66: iXML metadata right in your audio clip headers and source monitor. Production sound carries a wealth of metadata, and now you can see it without leaving the timeline or the source monitor.What's New?When your audio has iXML metadata, Premiere now surfaces it directly on the clip header. No more digging through panels or cross-referencing sound reports to know what you're looking at. The same metadata shows up in the source monitor too, displayed at the level of the channel labels, so you can make sorting and selection decisions before a clip ever hits your sequence. It's a global setting, so once you turn it on, it applies in the timeline and the source monitor.Where to find itThe control lives in Settings > Media, under a preference called Show iXML metadata in audio clip headers and source monitor. Flip it on to display the metadata across the timeline and source monitor and flip

Hey everyone! A new quality of life feature just landed in Premiere Beta 27.0 Build 39: color labels for timeline track headers. If you've ever wanted an at-a-glance way to tell your tracks apart on a busy timeline, this is for you.What's New?You can now assign a color label directly to any track header, video, audio, or caption track. It works just like clip labels: pick from any of your project's 16 label colors and apply it to the track itself. This colors just the track header, not the clips sitting on that track, so your timeline stays readable without re-labeling everything on it. Where to find itRight-click any timeline track header and choose a color label from your project's label colors. Click the swatch to toggle it off if you want the track back to no color, and click again to reapply a color. Track Header right-clic menuClick the swatch to toggle it off Why this mattersOn a timeline with a lot of tracks, it's easy to lose track of which is which, especially once you're jug

Hi everyone! As a dialogue editor, I've always chased the same thing: the tool that gets me the best-sounding result in the least amount of time, and the most control over my dialogue, whether I recorded it myself or it came back from set in whatever shape it happened to be in.For years, the answer meant reaching for a few different tools. One to make the voice sound better, another to wrestle down the background noise. And production audio is never just "speech." There's ambience, there's music, there are effects, all baked into the same recording, and that's exactly what makes cleaning it up so hard.This is where Enhance Audio comes to shine. In the same spirit as what we showed at MAX Sneaks last year, it hands you control over the ambience, the music, the sound effects, and the dialogue, and lets you rebalance every stem as much as you need. That's what makes it one of the most powerful noise reduction tools in Premiere today.For a couple of years now, the one thing you've told us

Hey everyone! We're excited to share a new dialogue tool that just landed in Premiere Beta 27.0 Build 39: Audio Leveling. It analyzes a dialogue clip and automatically writes volume keyframes that even out the level, so your dialogue sits at a consistent, balanced loudness without you drawing automation by hand.What's New?Audio Leveling listens to your dialogue clip and rides the volume keyframes for you. It detects where the level jumps too hot or drops too low, then lays down clip volume keyframes that attenuate the loud spots and lift the quiet ones toward a steady target. Instead of one static volume adjustment for the whole clip, you get moment-to-moment level balancing that follows the performance. And because the result is real keyframes on your clip, nothing is locked in. You can nudge, reshape, or remove any of them just like keyframes you drew yourself. Where to find itSelect a dialogue clip and you'll find Audio Leveling inside the Loudness module of the Essential Sound pane

Hey everyone! We're excited to share a new Firefly AI-powered audio feature that just landed in Premiere Beta [26.5.0 (Build 75)]: Separate Crosstalk.If you've ever shot a scene on a single mic – whether that's a boom, a phone, or just one lavalier on set – you know the moment: two people start talking at the same time, the mic can't tell the voices apart, and the only real fix is a re-record. Now Separate Crosstalk gives you a way to pull those overlapping voices apart, right inside your timeline! What's New?Separate Crosstalk is built for one specific moment: when two speakers talk over each other at the same time on a single recording – actual overlapping speech, not just two people who happen to be in the same scene. It works on mono and stereo clips and separates up to two overlapping speakers from that shared audio. This isn't full diarization and it isn't meant to split every speaker onto their own track across a whole project. It's meant to solve the crosstalk moment that today