A chatbot is a conventional agent that is able to interact with users in a given subject by using natural language. The conversations in most chatbot are still using a keyboard as the input. Keyboard input is considered ineffective as the conversation is not natural without any saying and a conversation is not just about words. Therefore, this paper propose a design of a chatbot with avatar and voice interaction to make a conversation more alive. This proposed approach method will come from using several API and using its output as another input to next API. It would take speech recognition to take input from user, then proceed it to chatbot API to receive the chatbot reply in a text form. The reply will be processed to text-to-speech recognition and created a spoken, audio version of the reply. Last, the computer will render an avatar whose gesture and lips are sync with the audio reply. This design would make every customer service or any service with human interaction can use it to make interaction more natural. This design can be further explored with additional tool such as web camera to make the agent can analyze the user's emotion and reaction.