ESP32 project 03

I have a project where I have three toys equipped with ESP32 modules and a few servo motors which is controlled by PCA9685. I want to get connected to these toys via WIFI. Send them MP3 files so that they will play that and some data to PCA9685 to control the servo motors. The code in my phone will be written on Unity 3D. Basically I want to say something to my phone and the toy should say the same in another language I would select from a list. What the code should do is this: -I will say a word, program should use Google Speech recognition, turn it to text, translate to another language, TTS it and send to the toy to be played. Technically this part is fairly simple as I had done a similar project. That was in Android. Google has a very simple api for this. At the same time, if available, on my phone I want to see the picture or a small animation of the word. For example, if I say 'Dog' and have chosen 'German' as the final language, the selected toy should say 'Hund' and the phone should display an image or a small animation of a dog. If you have experience in Unity and ESP32 module, please reply and bid with A REAL BUDGET and realistic schedule. This is an educational student project. I don't have much time and budget so please keep both as reasonable as possible.