Hi,
Sometimes I have some networking issues or the wrong model is used (e.g. duration over the limit of whichever API I'm using), would it be possible to add the ability to retry the transcription using the same audio? I end up having to copy paste the .webm somewhere and re-upload it... which is kinda weird 😅
Regards,
Florian
Hi,
Sometimes I have some networking issues or the wrong model is used (e.g. duration over the limit of whichever API I'm using), would it be possible to add the ability to retry the transcription using the same audio? I end up having to copy paste the .webm somewhere and re-upload it... which is kinda weird 😅
Regards,
Florian