Use Whisper to convert Audio to text files and then use chatGPT to summarize

[pszgit]

Is your feature request related to a problem? Please describe.
Problem - convert audio to text using Whisper Open AI where we can see speaker and with an option to see time stamp or not.

Describe the solution you'd like
Generate text file or MS word file with transcribed text

Describe alternatives you've considered
MS teams transcribe and generation of VTT file

Additional context
Add any other context or screenshots about the feature request here.

[pszgit]

request for an update on this please

[neo-anderson]

It would be awesome to have this feature. Is it possible to get the bare minimum working? Audio -> Transcription -> Summarize. Time stamps and speakers are nice to have.