Q: Guys, When I transcript a half-hour video with just a single speaker, the transcription output has only one ...
single timestamp in the beginning and then comes a huge monster of a block of uninterrupted text without a single line break.
Makes it extremly hard to handle the text, locate specific pieces in the video etc.
Why are there not at least 'some' timestamps in the text?
When signing up you show a sample sound file and the transcription shows timestamps each 5 to 20 seconds.
How to reproduce that?
The subtitles on the other hand are too fragmented.
Thanks
Io_Amberscript
May 14, 2024A: Hi there,
Thank you for your question.
You should be able to break up the text block with the enter key. An automatic timestamp will then be added to the new text block.
I hope that helps!
FGCPLUSFrom reviews it's clear that just having a big block of text and then having to manually go through to locate where you want the breaks to be is very time consuming, but maybe the reviewers got it wrong so let me ask here instead of jumping to conclusions.
If we upload a video with a single speaker.
Will the text come out when transcribed as a single block of text i.e. if it's a 5 min video there will be 5 mins of text without any gaps at all. or will it be broken out by pauses etc.
If there's only 1 speaker (same as above use case) and we want to generate captions, will the captions be broken out into segments or just one big block of 5 mins text?
We currently use HappyScribe which is a tremendous tool and works well, we're just looking for other tools that we can invest in and this looks decent.
Looking forward to heaing from you so we can make an informed buying decision.
Thanks