I will interactive talking avatar for restaurant,ai driven webgl,arkit52,lipsync,rig3d

G
gidolla
G
gidolla
gidolla

About this gig

Greetings!

I will build an Interactive AI Character for restaurant brand. The avatar will appear on Web or screen/kiosk inside the restaurant and have real-time voice conversations with customers, especially college students with interaction that feel entertaining and natural not like a normal customer-service chatbot.


LLM/Conversational AI + Speech-to-Text + Text-to-Speech + Real-Time Avatar/Lip Sync + Personality/Guardrails + Restaurant Knowledge Base + Web/Kiosk Interface.


WHAT I OFFER:

  • AI-Powered Human Avatars
  • Realistic 3D avatars that can interact with users via text & voice
  • Lip-syncing and facial expressions (Using AI-driven facial tracking like DeepMotion or MediaPipe)
  • Customizable looks & personas for different use cases
  • Voice AI (TTS & STT)
  • Text-to-Speech (TTS) with lifelike AI voices (Amazon Polly, Mozilla TTS)
  • Speech-to-Text (STT) for real-time voice recognition
  • Voice cloning & accent customization for personal branding


DELIVERABLE:

  • Fully modeled, textured, and rigged AVATAR
  • Optimized GLB/glTF with animation
  • Editable Blender source file


Customer speaks Mo understands AI generates an in-character response Mo speaks the response with synchronized animation

Get to know gidolla

gidolla

3D INTERACTIVE AVATAR AND DIGITAL HUMAN DEVELOPER

  • FromColombia
  • Member sinceOct 2026
  • Languages

    English, Spanish, German
A skilled 3D AI avatar and digital human developer specializing in creating interactive, lifelike avatars and real-time 3D experiences. I bring 3D characters to life as intelligent, interactive AI avatars that can listen, speak, express emotions and respond to people in real time Proficient in Unity, Python and Blender and applying these skills to deliver engaging and responsive user experiences i have built AI tutors with MetaHuman and LLM-powered voice interaction, real-time talking avatar with microphone-driven lip sync and VRM/VTuber systems for live streaming and interactive applications