Why: Too many same things for same result with diffents code lines. From python land code & result was different from 1 speech service to an other.

Now, every speech service should use SpeechInterface and a common method will do the job to cache text and play it with AudioFile.

Added / moded :

- Security peer : Useful to store API keys inside the security service AES safe. You should never expose API keys anywhere.

- Abstracted Gui for swing

- Mimic & MarySpeech to audiofile

If tomorrow we want to add stuff it will be easier.

Ohh, any idea to change rate of audiofile ? Maybe by copy / remove bytes, but if there is already embedded solution for prosody tweak, it’s welcome.