Skip to main content
TeresaDemel
Adobe Employee
Adobe Employee
August 2, 2022
Question

Text Panel Enhancements (Part 2): Assemble Rough Cuts from Transcripts

  • August 2, 2022
  • 36 replies
  • 30185 views

As you saw in my earlier post about text panel enhancements, transcripts are becoming more central in editing workflows. Starting today in Premiere Pro (Beta) you can create rough cut edits from selected Text passages.

 

To start, you can generate transcripts of your footage in the background when you import your media. Alternatively, you can generate transcripts from the Text panel after your project has been created. Either way, the Sequence transcript panel dynamically syncs with your Timeline: as you make changes in your Sequence transcript, the Timeline will reflect your changes – and vice versa.

 

My colleagues and I created some starter footage for you, as well as a tutorial so you can try it out. If you tend to do all of your editing in a Sequence, follow the guidelines below and/or watch this tutorial. If you tend to do three-point (Source) editing, follow the guidelines below and/or watch this tutorial.

 

Sequence Editing Workflow

  • Download the four videos from the Five Questions video assets folder
  • Open Premiere Pro (Beta -23.0x006 or higher) and create a new project
  • In the Import screen
    • Import "Kerstin interview"
    • Turn on Automatic Transcription and make sure “Create new sequence” is checked. (Note: You can turn on and off automatic transcription in Preferences -> Transcription -> Automatically transcribe clips on import.)
    • Make sure language is set to English
    • Click "Create"
  • In Edit view, open the Progress Panel (Window -> Progress). This will allow you to see transcription progress.
  • The clip should be in your new sequence
  • Click on the Transcript tab in the Text Panel
  • Click “Transcribe sources.” This setting allows your Timeline and Transcript to stay in sync.
  • Use the Search box in the Transcript panel for the word "what." This will allow you to see where the questions are in the video 
  • For the first question, highlight everything from "I had a piece of that cake a while ago" until she says "Second question."  
  • Click the In/Out point at the top of the Transcript panel. You should see that section of the video highlighted with In/Out points in the Program Monitor
  • Delete the highlighted section using the "Extract" button in the Program Monitor.
  • Go through the rest of the transcript and cut it down to a simple Q&A highlights reel. Have Kerstin state the question and a simple answer, but delete extraneous information. For example, have her say her favorite karaoke song but exclude detail on what makes it a great karaoke song.  
    • If you wish to have Premiere automatically set In/Out points around any selected text, go to the dropdown menu in the text panel and select "Set In/Out around selections."
  • Play back your sequence. You should have one sequence with five questions and simple answers.
  • Play back your clip and check for any issues.
  • Try it with your own projects!

 

Three Point (Source) Editing Workflow

  • Download the four interview videos from the Five Questions video assets folder
  • Open Premiere Pro (Beta - 23.0x006 or higher) and import the four videos to your Desktop or other preferred folder
  • Create a new project 
  • In the Import screen
    • Check the boxes next to all four videos
    • Turn on Automatic transcription (Note: You can turn on and off automatic transcription in Preferences -> Transcription -> Automatically transcribe clips on import.)
    • Make sure “Create new sequence” is unchecked
    • Make sure language is set to English
    • Click "Create"
  • In Edit view, open the Progress Panel (Window -> Progress). This will allow you to see transcription progress.
    • Pro Tip: Set up your windows so that Text Panel, Source Monitor, and Program Monitor are side by side.
  • Create a new sequence (File-> New -> Sequence). Name the sequence "Karaoke"
  • Double-click on any clip in the Properties Panel
  • Click on the Transcript tab in the Text Panel
  • Click on the “Source” tab to keep the source transcript in view
  • Search the transcript for the word “karaoke.”
  • Select the question and answer and click the In/Out point at the top of the Transcript panel. You should see that section of the video highlighted in the Source Monitor
  • Use the Insert button in the Source Monitor (or comma (,) keyboard shortcut) to insert the selection into the timeline.
  • Do the same thing for the four remaining source clips
    • If you wish to have Premiere automatically set In/Out points around any selected text, go to the dropdown menu in the text panel and select "Set In/Out around selections."
  • Play back your sequence. You should have one sequence with five people answering the same question.
  • Switch to Sequence view in the Transcript tab
  • Click “Transcribe sources.” This setting allows your Timeline and Transcript to stay in sync.
  • If there are any extraneous words in your sequence, highlight those words and click the In/Out point at the top of the Transcript panel. You should see in/out points selected in your Timeline panel.
  • Delete the words and associated subclip with the Extract (apostrophe (‘) keyboard shortcut in the Program Monitor.
  • Play back your clip and check for any issues.
  • Try it with your own projects!

 

Stay tuned, because we have more coming this year

  • Document style text editing: Use Cmd+X/Cmd+V and Delete to edit your tracks from the Text panel.
  • Range selection: Select a sub-clip on a single track using text. We know that In/Out points + ripple delete affects all tracks in your sequence and deletion isn’t helpful if you have B-roll, music, etc.
  • Language detection: Set your language preferences in Preferences -> Transcription for now. The ability to detect language on import will reduce a click, and can be helpful when you are working on a project that includes multiple languages.
  • Search Source footage for key moments

 

We would love to hear from you

  • How is the performance of automatic transcription when you have hours of files? Please share your system specs + the number of hours of source footage you are transcribing.
  • When working with your own footage, are you mostly editing the Sequence Transcript, Source Transcript, or a mix of both?
  • Are there any moments where the UI or descriptions feel unintuitive?
  • How well do the timing of the cuts work?
  • For non-English languages: Are there any languages or dialect problems, e.g. problems selecting text, editing word boundaries, etc?

36 replies

New Participant
May 16, 2023

I already found a pretty serious bug with editing in the Text panel that's going to set me back an entire day of work....

 

I created a rough cut of an interview using the text panel.  I used the copy-paste feature in the text panel to move sound bites around and also moved stuff around manually in my timeline for micro-adjustments with the interview to clean it up.  

 

This interview was recorded using a separate audio recorder (Zoom H4N) that was synced with the camera in post.

 

The problem came when I moved the project file of this rough cut to a different external drive and then tried to reconnect or relink the media.  This new drive had the rest of the footage for this big project of which the interview will be a part of.  

 

However, when I went to reconnect my media of this rough cut, the audio data did not carry over properly.  Instead, at each cut point of the audio, it reverted to the very beginning of the full audio clip.  The video looks to be correct but now everything is unsynced.  I know this is the text panel update because the process of relinking footage on detailed edits I've done successfully hundreds of times over the last decade.

 

I suppose I never learned my lesson of updating Premiere in the middle of an important edit...It never really bit me before but I guess today is my lucky day...

Stan Jones
Community Expert
May 16, 2023

Tdaly,

 

Ouch. Are you working in the new Release version 23.4.0? Or a Beta version?

 

Were the synced audio clips merged with the video or synced by placement?

 

@nbechere @TeresaDemel 

 

Stan

 

 

 

New Participant
May 16, 2023

23.4.0.  The clips are synced by placement.  Video and Audio are still technically separate.

 

I just tried two things on the original project file before transferring it over to the new external drive again. 

 

None of this worked:

  • Grouping the Audio and Video on each edit point.  (Just tested it on the first few cut points)
  • Went to the Action tab in the Text Panel and created a "static transcript."
  • I wanted to try and delete the transcript entirely but don't see a way to do that.
alex azinheira
New Participant
May 16, 2023

Congratulations on this fantastic feature! For me it would be extreamly useful to be able to import an edited transcript and have premiere automate the rough cut from that edited text. This would allow me to collaborate with editors that made the questions and have a pretty good idea on how to structure the material. It would be a great upgrade!

JoshWeiss
Known Participant
May 12, 2023

Is it intentional that the transcriptions are skipping over filler words that people often use, like "um" and "uh"?

 

Inspiring
May 12, 2023

If it is intentional, there needs to be an switch to filter or not.  Those "ums" are really important when reading a transcript for editing.  They're not so important if exporting a transcript for publishing.

JoshWeiss
Known Participant
May 12, 2023

I agree, having the true transcription is important to me so that I know to cut out those words when possible. 

Participating Frequently
May 9, 2023

Hi! Is there a chance of adding a highlight function to the transcript window and then a way to export those highlights to a sequence? Would be so helpful! Thanks

Kes Akalaonu
Inspiring
May 9, 2023

Right now, you can mark an In and Out Point in the source monitor and either overwrite or insert those into a sequence or turned marked sections into subclips that can live in the project panel. Multiple selections would be nice though

Participating Frequently
May 11, 2023

Thanks so much for the extra info! I did not knwo you can make subclips! Can you point me to  how make subclips from text window? 

Participating Frequently
May 5, 2023

hi.  I'm using beta v 23.5.0.24 .   When marking in or out points on the text panel, those in and out points dissappear.  The only way for them to not dissappear is to mark directly on the source clip.  This makes text based editing more difficult. Hopefully it can be fixed. thank you

Participating Frequently
May 5, 2023

to be more specific, in and out points do work when marking them as you play the media directly from the text panel.  When it doesnt work is when you click on a word you want to jump to and mark.  The in OR out point you previously marked dissappears.  I checked to see if it was because i was marking out of chronological order, but that wasn't the case. 

Kerstin Ebert
Adobe Employee
Adobe Employee
May 5, 2023

Hi Gabriel!

When you work directly in the transcript, the In/Out points should be set automatically once you select text (one word or multiple words) via mouse click + drag across the word(s). The text within the In/out range should also get a dark blue highlight. Once you click somewhere else in the transcript, the In/Out range should be dismissed.

Is this what you are seeing?

New Participant
May 1, 2023

I've been testing the latest 23.5.0 and see something that could be addressed.  When I export a source transcript (that was automatically transcribed) to a .txt document, I can revise the content in a text editor and reimport that "corrected transcript" to the source.  This is great!  It gives the ability for the transcript to be proofread and corrected and then replace the original Premier-generated clip transcript.

 

However, I tried the same process from a Premiere transcribed sequence but Import Corrected Transcript is greyed out and unavailable.

If we can import a sequence's corrected transcript, that would be far more useful.  We always have our transcripts proofread.  If the proofer could fix any errors of the transcript, it would be a huge time saver when dealing with captions.  Ideally, the transcript that is imported is not considered "static" and still has the ability to alter as needed.  Hope you can implement this capability.

Stan Jones
Community Expert
May 2, 2023

Keith,

 

Here's the post that discusses the "Import corrected transcript":

https://community.adobe.com/t5/premiere-pro-beta-discussions/text-panel-enhancements-share-a-transcript-with-a-colleague-for-correction/m-p/13623956#M7102

 

I think it is actually more flexible. For example, if you create a static transcript in a sequence, and then open it in the SOURCE monitor, you will find that "Import corrected transcript" is active.  Also, once you create a static transcript, you will see in the 3 dot menu, an option to "Generate text-based editing transcript." When you do that for a sequence and look at it in the Source monitor, you also have the option to Import a corrected transcript.

 

Edit: I now believe that the last statement is incorrect. The "Generate text-based" just goes back to the source media transcripts, and still does not allow importing a correct transcript. You can export a transcript with the sequence timecodes and just the text from the parts of clips used in the sequence, but you can't correct and import that. Only static transcripts.

 

Stan

 

 

 

New Participant
April 28, 2023

Hey! Video Editor from Microsoft here. 

 

I love this feature and I'm just discovering and using it as today. I love both Lift and Extract. I would love to see a "Cut from both ends and lift to another channel" button. I know this may be weird, but in a team of several editors sometimes we prefer to see the selected clips like that and tag them with different colors for visibility. Also, I imagine a multiple selection in the future? So we can select various parts of the transcript and lift or extract them all at once? 

 

Hopefully I can work with a Spanish speaker soon, so I'll return with non-English bugs, if any.

 

Thanks for the great work! You're awesome. Cheers.

Participating Frequently
April 13, 2023

Issues with multiple tracks of audio and transcription gaps. 

 

Hi, I am workign with sequences with multiple tracks of audio. I have noticed that the sequence mode view of transcript (that compiles the multiple tracks) is missing large chuncks of the transcript. When I go to individual clips the transcription is there but in the sequence mode it is missing. I have people on seperate lavs so each of these clip transcripts is not complete. Is there any solve to this and have a combined transcript for the sequence while still having access to each individual audio track?

 

Thanks for any help in advance. 

Kerstin Ebert
Adobe Employee
Adobe Employee
April 14, 2023

Hi Andrew,

if clips with transcripts are overlapping on multiple audio tracks, only the transcript of the highest ranking track (e.g. V/A 1) is shown. Once there is a gap between clips on A1, the transcript on the next highest ranking track (e.g. A2) is shown for the length the gap. Hope that helps!

Best, Kerstin

Stan Jones
Community Expert
April 15, 2023

@Kerstin Ebert,

 

Very useful info. I'm playing with the issues presented in more than one thread about overlapping clips and multicam. I have discovered that when an audio track is muted it "turns off" that transcript. "Solo" on a lower-ranking track does not have the same effect. So, for example, when @Andrew27547008tt3t wants to see the transcript for a lower-ranking track, he can mute the higher-ranking tracks. (With more than 2 relevant tracks that would get tedious.)

 

Also, when there is a "static transcript," there is a new command in the overflow menu - "Generate text-based editing transcript..." I found this when once again thinking that we REALLY need a "delete transcript" option. But for this purpose, being able to return to the source transcripts works.

 

The dialogue for that option includes this: "Your existing sequence transcript will be replaced by a dynamic transcript that is sourced from the clips in your sequence." I wasn't sure what that meant, but it appears to (very quickly) revert to the source clip transcripts, as modified by the sequence. It does not combine transcripts from multiple tracks.

 

Edit: I'm on Build 23.4.0.48

 

Stan

 

 

Participating Frequently
April 6, 2023

Hi, Is there/ will there be a way to search keywords across all transcripts in a project? Thanks! 

 

New Participant
April 11, 2023

I would love that function!

New Participant
March 29, 2023

The text-based editing is a revolution that will save an incredible amount of time. As of now the quality of the norwegian transcription is of lesser quality than other services such as Jojo Transcribe (whisper based - https://apps.apple.com/no/app/jojo-transcribe/id1659864300?mt=12) If you open for import of .srt-files generated elsewhere I would started editing my podcasts in adobe premiere right away. 

Edzel Yago
New Participant
March 29, 2023

Wanted to add my interest to this feature.

 

The biggest hurdle for this workflow on my team's end is that the transcription requires more correction than it's worth. If my editors are editing by text, it needs to be accurate so they can leverage being able to skim the content with their eyes. If it's not accurate, they have to watch it and correct it, which takes more time/effort, a section might be skipped over because it looked like something it wasn't so they might as well just stick to editing the old fashioned way given our turn around times and volume of content (15+ videos a week).

 

We can generate transcripts/captions with greater accuracy (with caption suitable timing) but have no way to use this to help with the transcription that Premiere does. We're using Aloud's AI translation/dubbing platform and it has a function to use a corrected transcript to guide the recognition/transcription and a function to paste a transcript after the initial processing which then gets retimed.

 

If it weren't for the amount of corrections needed for the transcripts, I could definitely see the workflow saving my team of 12 editors a lot of time for the content that takes the greatest amount of time to edit (unscripted content).

D Graham Withers
Participating Frequently
October 16, 2023

Right with ya on this Edzel - as a long form documentary editor, mis-interpreted words across 10/100s of hours of footage mean the ultity is greatly deminished.

Allowing for "source media transcription" .srts to be imported would go a long way to making this feature game-ready for transcripts as well as translations.