I have a podcast transcript (9000 words) that I need to break into chunks for ChatGPT, so it can clean up those chunks (fix lots of typos, spelling errors, etc.).
I’ve tried following other guides on this, asked Grok, ChatGPT, Perplexity, etc. but they aren’t working for me. Nothing is producing multiple variables I can then use in the next OpenAI modules.
Any solutions?
P.S. Need this because the podcast deals with technical subject matter. If OpenAI knows the subject, it can fix those details. ChatGPT o1 could one shot that giant block of text, but there is no API automation for that and even o1 mini fails here.
Welcome to the Make community!
Yes, that is possible. You’ll need a minimum of six modules:
This is just an example. Your final solution may or may not look like this depending on your requirements.
To do this, you can try using the Text parser “Match pattern” module —
Finds string elements matching a fixed pattern (regular expression).
For more information, see https://www.make.com/en/integrations/regexp, and https://www.make.com/en/help/app/regexp in the help centre.
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
1 Like
