Low latency TTS streaming on exisiting AI assistant project

I’m seeking someone who can master and perfect chunk blending in low latency streaming tts You must mainly handle the blending process as other dev will handle dividing and chunk queuing and timing processing Using things like: - cross faces - pauses - silence detection and removal - loud normalisation - anything else related to that Basically every chunk contains a sentence that needs to be joined with the next chunk. The two sentences need to blend well and sound like it’s whole. Requirements are you’ve done this before and results are excellent