- My goal: I am trying to extract zoom transcripts (which come in .vtt file format)
- Issue: How do I download and upload these files? Or, is there a workaround for this file format?
- Steps I've taken to troubleshoot: None
- Additional info: (Cloud or Self-hosted, Screenshots)
Hi @devri,
I do not believe that Retool has any built in tools for handling .vtt file format.
A likely work around would be to import and use a python library for handling such data.
I just found this library, let me know if that library has the functionality you need.
Hey @Jack_T - thanks for your response.
I have watched this video by Retool - https://www.youtube.com/watch?v=1ULVlh8mRx0, but it didn’t clearly explain how this is handled. Is there a more detailed resource - such as a blog post or guide - that explains the concepts covered in the video in more depth?
Thank you so much!
Ah I see, it looks like the video doesn't fully dive into what he does with the data response from the Zoom API.
Keanan mentioned to me that: "VTT just means it also has timecodes, like this
WEBVTT
00:00:00.500 --> 00:00:02.000
The Web is always changing00:00:02.500 --> 00:00:04.300
and the way we access it is changing
So in the past, I've either parsed it with code, or just passed the whole thing to an LLM and allowed it to look over the entire transcript."
I would imagine he used a python library such as webvtt-py as I mentioned able in a workflow block to read from the file to get the file's data into a string that could be passed to the LLM as was not downloading or uploading the files.
Also, check out Zoom's docs here on all the ways to get call transcripts.
As there could be other options for getting the data from a call transcript.
Is your goal to download the files to your machine, upload the files to a file storage system or pass it to an LLM?