61
Improve cross talk transcription
under review
Ryan Nantell
I find it pretty much impossible to fine tune the transcript/script when there's cross talk between host and guest. Seems mostly due to limitations of the "edit text" tool. I'm restricted from changing the speaker labels to accurately reflect who is saying what. Seems like making a "cross talk mode" would be ideal? Allows us to flag a section as full of cross talk and be given free reign with speaker labels, line breaks, etc.
Activity
Newest
Oldest
W. Curtis Preston
This definitely needs a more elegant solution. The only way I fix it now is to edit the sequence manually to remove the cross talk. And it's not exactly the smoothest editor. :)
Banter Savvy
a similar product called Sonix can handle this with relative ease, so it confuses the hell out of me that Descript can't handle it.....considering it already uploads files individually. Someone on the design-train decided compositions needed to attempt to transcribe all audio together instead of separately and it shat the whole program.
J
J Ojibwe
We need a way to re-trigger a 2nd transcription for a problematic section after fixing the cross talk in a sequence.
J
Jock Busuttil
+1 Even when I have individual speakers on separate tracks in a sequence, the speaker label assignment gets confused by cross-talk and tends to omit the transcript for that section entirely.
When this happens there are either no speaker labels at all, or incorrect speaker labels assigned to the tracks. The transcript indicates silence for several seconds, and any manual attempts to correct the transcription by adding the words being spoken usually makes the transcript worse by removing more sections of previously-detected transcript.

Isabelle Roughol 🇫🇷🇪🇺🇬🇧🇺🇸🇦🇺🇰🇭
Two ways this could be handled: Let us mark instances of cross talk and deactivate auto transcript on those parts. Let us humans handle it. Or on the whole file, give us options to manually deactivate/force transcribing. It seems like the app keeps trying to retranscribe on its own whenever I make an edit. That's super annoying.
Toggle Rat
What's frustrating for me is that often all the lines of text have their separate transcripts, but I can't make the dominant one come through. Trying to add the text manually doesn't automatically sync with the track that has the same words I'm manually entering, which is weird.
Isabelle Roughol 🇫🇷🇪🇺🇬🇧🇺🇸🇦🇺🇰🇭
+1 It's extremely frustrating that the software keeps trying to correct the changes I'm making. Human edits should always supercede.
C
Cathy Booth
I would love to be able to edit the cross talk better in Descript. As it is I'm using Ferrite on my iPad to pre-process before adding into Descript. Ferrite makes it really easy to delete or move cross talk.
Mark Bramhill
Part of this issue is also a design question — do you have a line break between parts of sentences that are woven together, or you put a whole sentence, then the next? The most elegant solution would be to model after scripts/screenplays, and have simultaneous dialog side-by-side. This would be very helpful for reading, editing, and generally making sense of our compositions.

Banter Savvy
Mark Bramhill: oh my god, yes. It's literally already built into transcript in every way but the doc itself. Great suggestion!
P
Petri
Track-changes would also help. The system changes some times the labels and lines and those can go unnoticed to the final production version.
If it's not possible to lock or get free reign sections would be nice at least to see what has been changed by the system since those changes do not happen instantaneously.
Load More
→