We do not have such a feature for now. You need to render the voices separately and merge them using third-party software. We will try to implement this type in the future.
Or you can also use the merge function to combine different audios from multiple voices, as explained in the below screenshot.
Go to the Training section of Speechelo and check the Full Training Video.
It will show you how you can use the MERGE feature to combine different audios.
