Split Audio File to Transcribe with Whisper

Hello guys. I have a pretty cool automation to transcribe and summarize our daily dev standup meetings. Then this summary is stored in a Notion Database.
The thing is, most of the time they take a bit longer and the audio file that gets uploaded to Drive is larger than 25mb, so ChatGPT Whisper can’t transcribe it. I then get a DM and transcribe it manually with Assembly AI. That kind of defeats the purpose though, if I have to manually transcribe them.

So, the simple question is: Is there an integration that can split an audio file?. With that I could use 2 whisper modules and then add the summaries together.

If not, can you think of another way to do it? I’m already using the most efficient possible audio format. I know similar stuff has been asked, but the answer is not clear if there is one.


Hi @Jose_Manuel_Alcalde ,

There is something interesting here about audio file splitting, it may help you.


Hey @Philippe_Billet , thanks for your answer. I actually read that, but sadly it’s a tool to trim MP4 files. Not sure it’s able to trim purely audio files into 2, less of all other formats like OGG =(.
If it was able to split MP3, what module should I use?

Try to use 1001fx! function"cut audio file" it may help you

Hi @Jose_Manuel_Alcalde