We want to be able to produce videos with multiple phrases in the script and have the avatar interpolate at beginning and the end of each phrase so that we can manipulate the play order without the video looking jerky. As far as I can see the fluency option is only available at a whole video level so we would have to produce a video for each phrase (some of which would be very short) and edit them together into one video. Am I correct or is there a feature in the api to return the avatar to a default position after each phrase (Synthesia have this feature)? If not it would be a great feature for future development.
