I would like to create a mobile app for IOS, which allows end-users to manage a dialog with a server either via textual chat or via voice commands. I see it organized in three screens: 1. log-in and authentication (username [email] /password). Only one 2. avatar selection (man / woman). Only once 3. main screen where we have an 'talking' avatar, the textual chat window and the mic button to speak. The dynamics is the following: Once the app is launched, the main screen is opened with a greeting by an avatar. A user gives a command (either via texting in a chat window or verbally, by pressing the mic button). In case of a voice command, it translated to a text, presented in the chat and sent to a server through provided API. Then a textual response coming from a server , reflected on a chat window, translated to speech and presented by the 'talking' avatar ------------------- highlights -------- I will get the full code + build instructions need to integrate some lipsync emulation few predefined avatars (man / woman) I will provide an API to use for authorization (during authentication a token will be received from the server and used for further communication) I will provide an API to use for text processing local text <-> speech translation you can use free opensource or to get my permission for a licensed one I've uploaded two samples of a main screen (just as reference) Might need similar app for Android as well