To hear an audio file in a public space I need to have headphones or I have to wait until I can hear it.
Describe the solution you'd like
I would like to have the option to add an automatic transcription of the audio next to it. It could use vosk, whisper... I would like to be able to choose what model for vosk it should use
Describe alternatives you've considered
Downloading the file, and then use vosk on it to know what it says... But for long conversations it is not very practical.
Is your feature request related to a problem?
To hear an audio file in a public space I need to have headphones or I have to wait until I can hear it.
Describe the solution you'd like
I would like to have the option to add an automatic transcription of the audio next to it. It could use vosk, whisper... I would like to be able to choose what model for vosk it should use
Describe alternatives you've considered
Additional context
No response