AI Assistant Details

AI Assistant Application

A powerful AI Assistant application that combines the capabilities of Gemini API, OpenAI GPT, and DALL·E to provide intelligent conversations, image generation, and voice interactions. Users can interact using text or live voice input, and the app responds with both spoken voice output and on-screen text for a seamless experience.

Core Features

Voice Input

Speak naturally — the assistant listens in real-time and processes queries instantly.

Text Input

Type messages directly for precise control and quick interactions.

Voice Output

AI responses are spoken back to the user for hands-free interaction.

On-Screen Responses

Every AI answer also appears as text on the screen for clarity.

AI Powered

Integrated with Gemini API and GPT models for natural, human-like responses.

Image Generation

Leverages DALL·E to generate AI-powered images from user prompts.

Tech Stack

Flutter (Dart)

Cross-platform framework for mobile and web.

Gemini API

Google’s AI model for advanced natural language understanding.

OpenAI GPT

Provides intelligent conversational AI responses.

DALL·E

Generates creative images based on user text prompts.

Speech-to-Text / TTS

Real-time voice recognition and AI voice responses.

Project Goals

This project is designed to showcase how AI can be integrated into everyday apps for seamless communication. The main goal is to combine real-time voice interaction, intelligent text conversation, and creative image generation into a single, user-friendly assistant.

This AI Assistant demonstrates my skills in integrating advanced AI models into cross-platform apps while delivering intuitive, real-time user experiences.

Project Information