We'd like to add a button that will play synthesis for an entire story. This might live in the TTS drawer.
There are some open questions about technical design, in particular how we want to handle awaiting synthesis API responses for each sentence / paragraph. e.g., should we wait until all synthesis responses come back before starting to play? Or some sort of wait-per-sentence / per-paragraph setup?
We'd like to add a button that will play synthesis for an entire story. This might live in the TTS drawer.
There are some open questions about technical design, in particular how we want to handle awaiting synthesis API responses for each sentence / paragraph. e.g., should we wait until all synthesis responses come back before starting to play? Or some sort of wait-per-sentence / per-paragraph setup?