[feat] API for interacting with tts-studio

[accforgithubtest]

Cool project, thanks for creating it !

Any plans to implement any API that lets me send a (http/s?) request with a bunch of text and get an audio file as the output ?

Also keen to understand few more things about how this might possibly work if implemented -

1. Will there need to max text sizes per request, to make this work well in [small scale] self-hosted hardware ? (I mean raspberry pi's / 1L mini pc's)
2. If a large text is passed (e.g several pages of a book), will this project handle "splitting" the large text into smaller pieces / multiple internal requests and produce a single audio output file ?
3. If deployed via docker, I assume this is going to need a volume mount for saving the output files
4. There are differences in configurations / options depending on selected mode, this would need to be passed in via the request as well.
5. For large text, if it takes a while to generate the audio, how to correlate an request to a corresponding audio file ?

Keen to hear you thoughts. Cheers !