aeneas VS SpeechRecognition

You could try aeneas. Syncabook apparently uses the afaligner library, which says that it was inspired by aeneas but uses FastDTW to find an approximation to the optimal warping path. This might make it slightly less accurate than aeneas.

Check out https://github.com/readbeyond/aeneas

In case you have let's say: a 20min entry from an audio book, and the sentences seperatly in a txt file and you want to cut the sentences out of the audio manually you can look at a tool like aeneas. If you still have to annotated all your data yourself i do not really know a tool for this :/

here's another solution: https://github.com/readbeyond/aeneas

Start and Stop Listening Example

There is a great library that has support not only with OpenAIs whisper but many others that also work offline. https://github.com/Uberi/speech_recognition

This is the library: https://github.com/Uberi/speech_recognition

It is python remote plugin that is a tin wrapper around speech_recognition package.

I am less familiar with speech recognition myself. I have implemented something similar many years ago, back when Google had a REST API that allowed you to upload audio and they would respond with the recognized words/sentence. I think they still have the same API available, though. They limited how much you could send, but for voice commands it was pretty solid. However, SpeechRecognition looks like a library worth trying out for this, as that seems like it could do offline processing depending on the underlying library. They also have some examples to look at.

SpeechRecognition

I found this one here

https://github.com/Uberi/speech_recognition/blob/master/reference/library-reference.rst this might help. I guess your best bet is to rtfm.