Export separate tracks by speaker from single file
Tim Scarfe
Assuming I took in one audio file with mixed speakers and I ran the speaker detection and transcription -- I would then like to be able to export separate audio files for each speaker, this means in Premiere I can apply different levelling.
Tim Scarfe
Note that I now use zencaster to record separate audio channels for guests on my podcast, so I am good
Canny AI
Merged in a post:
Seperate speakers from one audio file into multiple
M
Mathias Andersen
When you have a recording with multiple speakers in a single audio file—such as from a Zoom call—it would be incredibly helpful to separate each speaker into individual audio files for easier editing. In Zoom calls, the audio quality often varies between participants, so the ability to isolate and edit each speaker separately would be highly beneficial.
Canny AI
Merged in a post:
Voices spliting
Avi Manager
Split into audio tracks (files) from one recording depending on the speaker's voice (1 source for 2 voices - into 2 resulting files each with a separate voice)
B
Berthold
+1 for this feature request!
I would be willing to book a Business Plan only for this feature. And the many other upvotes show that others would also benefit from it.
We often have one audio track with 2 speakers recorded in the same track (due to technical reasons of the interview situation, sometimes you cannot avoid it, e.g. street interviews, AI voice transcripts or someone just delivers the file like that). When I upload it, I see that Descript perfectly identifies the 2 speakers and even shows the audio wave form in 2 different colors.
I want to export them into 2 separate audio tracks, one per speaker, for further post-processing per speaker or even feed separate video avatars with the voices to turn them into an AI video podcast.
This should be easy to implement as the heavy lifting (identifying the speakers and mark the waves differently) is already done. I just need an export option to export each colour in the timeline separately.
Gunnar Andersen
BertholdI couldn't agree more. I use avatars and AI animation in my video podcasts so it is in this one tedious task that I spend most of my post-production time every week. This would be a game-changer for me.
Andrew Raskin
(Easier!) VARIATION ON THIS REQUEST: Export selected sequence tracks from a composition.
Like many here, I record speakers on separate tracks, which Descript turns into multi-track sequences, and I want to be able to export those edited sequence tracks out as separate audio files.
Right now, I have to go one by one into all the sequences in my composition, solo the track I want, export, then repeat for the others. How about just a popup allowing me to select sequence tracks to export?
This should be easier than the OP request, which would require separating a single recording into multiple tracks, which I'm guessing is tough when the voices overlap.
Canny AI
Merged in a post:
Create Individual Tracks from Isolated Speakers detected via Transcription
E
Emma Kingsley
In cases where one or more files in a multi-track recording are lost, corrupted or otherwise unusable, we should have a way to create a multi-track from a single-track backup and be able to isolate them
Kelly Cassidy
Can you make sure there is an update where people can separate multiple voices from 1 track? I don’t like when you have to download 2 files you have to edit a sequence.
Max Graham
Why on earth are people recording two voices onto one channel? Even zoom has an option for separate channel recording. If you're using an app or service that only allows one channel then consider switching. Seperating after the fact will never be as clean (as someone else highlighted below)
j
j1364641852
Max Graham: I think anyone that knows enough to want to do this, is probably not the one that recorded multiple speakers into 1 channel.
Max Graham
j1364641852: 🎯
Titus Studio
Max Graham: Welcome to the world of a sound engineer... you happen to work with a lot of different material, so every tool you can get helps... You could have the same argument against noise reduction. Why on earth are people using noisy mics, bad pre-amps and record in a noisy room? Well, it just happens and that's why it's great to have tools to fix that...
V
Vibrant Falcon
j1364641852 Agreed!
V
Vibrant Falcon
j1364641852 Agrred! this is my scenario. i cannot dictate how the file original is provided
Carlie Zak
I would LOVE this feature and would use it alot!
Adam Lieber
Ridiculous this is not a feature yet. App identifies separate voices, colour codes them but can't export as separate tracks.
Even bringing natively into reaper which is an export feature it doesn't split the files which are edited and split in Descript, it just outputs one long stereo track.
Please can you add this feature
S
Simon
Also this would allow stereo panning of the speakers to position them within a sound field.
Load More
→