Alright. Remember that it'll only use the vcv voicebank if you enter vcv style notes, otherwise it'd be exactly the same as the one you already had.
If you don't know how to enter vcv style notes, they are entered by entering the vowel sound of the previous note or a dash if there was no sound before it. For example, if you want her to sing 'konnichiwa', you'd enter
[- こ] [o ん] [n に] [i ち] [i わ] (plus an optional [a R] for a more natural end)
This can get tedious, so I'd recommend getting a cv to vcv converter like Iroiro to speed things up. The full, paid version of utau also has a built in cv to vcv function.
Once you have your vcv notes, select all notes and right click and then click on property. If the preutterance or overlap boxes are a dark grey, click clear. If the STP box is dark grey, double click it. Then click OK once you're done. Then, click the reset button in the upper right corner and then p2p3 and then acpt. Once you do that, your ust is fitted.