Implement a breakdown of big files of audio

[grumpyp]

The OpenAI limits audio files to 25 mb max, so if I upload a file with 100 mb ~ 1hr podcast, it will break.

Implement a mechanism to break it down and index the chunks.

[MoistGoolem]

Just stumbled across this issue. Could another solution not be to compress the file instead of splitting it up? As stated in OpenAI documentation there might be issues with splitting the files into chunks if done mid sentence (like in a podcast). https://platform.openai.com/docs/guides/speech-to-text/longer-inputs

[grumpyp]

hey @MoistGoolem if that works, definitly - why not. I just tested it with a tool and that would potentially work. Feel free to try and open a PR.

Do you need something else to start working on it?

[grumpyp]

@MoistGoolem Hi, are you able to work on it? So I gonna assign you.

[MoistGoolem]

Sadly don't have time to work on the issue. I just wanted to propose an alternate solution 😊