Whatsapp chat with voice and image recognition

I would like to develop a chat solution to interact with WhatsApp integrated with Google Dialogflow. This solution must recognize voice and images to be handled by speech-to-voice and OCR solutions. At that moment I need a simple solution, anticipating these recognitions and inputs, the dialogues and integrations will develop later. For development, it should contain all source codes and related documentation, as well as an indication of proprietary solutions, if involved in the proposed solution.