It is an advanced AI voice assistant app built with Flutter, integrating OpenAI's GPT and DALL-E APIs to provide both text and image responses based on voice input.
- Voice input recognition
- Text-to-speech output for non-image responses
- Integration with OpenAI's GPT for text-based responses
- Integration with DALL-E API for image generation
- Automatic detection of image vs. non-image requests
- Dynamic response handling (text or image)
- Flutter SDK
- Dart
- OpenAI API key
-
Clone the repository and setup project
-
Create a
lib/secrets.dart
file and add your OpenAI API key:
const String openAIApiKey = 'your_api_key_here';
- Launch the app on your device.
- Tap the microphone icon to start voice input.
- Speak your query or request clearly.
- The app will process your input and determine whether you're requesting an image or a text response.
- For text responses, the app will use text-to-speech to read out the answer.
- For image requests, the app will display the generated image on the screen.
The app uses a modular architecture with the following key components:
- Voice Input Handler: Manages speech-to-text conversion
- Intent Classifier: Determines whether the user request is for an image or text response
- OpenAI GPT Client: Handles text-based queries and responses
- DALL-E Client: Manages image generation requests
- Text-to-Speech Engine: Converts text responses to speech
- UI Controller: Manages the app's user interface and response display