I’m creating a story-driven mobile adventure and want to make spoken dialogue the heart of the experience. Players will literally talk to the characters, have the game understand them, and watch every line flow out of perfectly synced lips. To make that happen I need a developer (or small team) who can bring together three AI capabilities: reliable voice recognition, real-time lip syncing, and responsive character interaction. Scope • Build the core game loop for iOS and Android in a mainstream engine such as Unity or Unreal—whichever you are most confident will handle mobile performance alongside AI calls. • Integrate on-device or cloud speech-to-text so the player’s voice triggers branching dialogue and puzzle events. • Generate matching facial animation on the fly; the lips must fit either pre-recorded or TTS lines without looking robotic. • Design a simple NPC showcase level that lets me test conversation flow, branching logic, and character emotional states. • Expose clean hooks so my narrative team can add new scenes, audio, and animations without touching core code. Acceptance I’ll consider the milestone complete when I can install an APK/IPA, speak to an NPC, see the mouth align with my words, and trigger at least two distinct dialogue paths based on recognized intent. If you’ve shipped anything with Azure Cognitive Services, Google Speech, Unreal MetaHuman lip sync, or similar tool-chains, tell me. I value clear, documented code and pragmatic advice on keeping latency low for real-time play.