for application provide AI chatbot that using user's voice and face emotions $.$ where the user will communicate and talk with model, after that the voice of the user will be transformed into a text, the text will be processed in a certain way where it will trigger the application to send a prompt to the API, which will generate an answer as a text, and that text will be transformed into a speech $($using the text to speech library$)$ for example, let$$s say that the user said $($hi$)$ to the assistant. The assistant already knows the user$$s name and other information about him $($Mohammed$,$ is a chef...etc.$)$ That information was saved as variables in an early communication with the user and saved in a file. $1-$ The app will extract the text from the user voice. $2-$ then it will process that text into a prompt. $3-$ The current feeling of the user will be added to the prompt $($source is the video from the front camera$).4-$ then it will send the processed prompt to the API. this is an example processed prompt: $$Considering this information $($a person name is Mohammed, he works as a chef, he is sad$),$ this person said $$hi$$ to you, imagine the you and him are humans in a conversation, generate an answer to the thing that he said to you in a way that a normal human would answer.$5-$ The API will send an answer $($hi Mohammed! how was your day, what delicious dishes have you cooked today, and tell me what is bothering you$)6-$ Finally, that answer will be transformed into a voice using the text to speech model. make context diagram for the project