Hello, I am trying to transform audio into text with the following scenario:
However, I get the same error all the time: Chatgpt is not getting the correct file format. However I check the output of the http and looks fine to me:
This is the error I get from the chatgpt module:
I’m sure it’s quite a silly thing I am not seeing, I would really appreciate the help of the community.
thanks in advance!!
Hey @Rafa_Romero,
Based on what I found on the OpenAI community, this seems like it’s an issue with the API itself.
Apparently, there are quite a few issues with this model recognizing file formats.
I reconstructed your flow, and this seemed to have worked on my test runs:
It’s a quick and dirty solution. But seems to at least give the text output you’re looking for.
mmm thanks a lot, but it’s returning the same error message 
Yeah, I’m afraid it’s due to the OpenAI API not recognizing the file formats properly. You could experiment by replacing that m4a part with another file extension, and see if one of them works.
But it seems to be fairly unstable 
