A web application that enables users to interact with an AI assistant through voice input. The app captures and transcribes voice inputs, processes them using AI models, and provides responses. Additionally, it records entire sessions for future reference.
- Voice Input: Capture user voice input using the browser's microphone capabilities.
- Speech-to-Text Transcription: Convert voice input to text using Browsers API transcription.
- Session Recording: Record entire interaction sessions, including voice inputs and AI responses.
- User Interface: Responsive and intuitive UI for seamless user experience.
- Responsive Design : The app is completely Mobile responsive as well.
- Toast Notifications: Provide real-time feedback to users for actions like recording start/stop, errors, video download etc.
- Frontend:
- Next.js
- SpeechRecognition media API for transcription.
- navigator.mediaDevices media API
- Node.js (v20 or above)
- npm
-
Clone the repository:
git clone https://github.com/Algoture/DomiLabs.git cd DomiLabs -
Install dependencies:
npm install
-
Run the application:
npm run dev
The application will be available at
http://localhost:3000.
- Open the application in your browser.
- Click on the Mic button to begin a session.
- Speak into your microphone; your voice will be captured and transcribed.
- The transcribed text will be processed by the AI model, and a response will be displayed.
- Click on the Send button to end the session.
- Session recordings will be saved in a .webm video and you can download it too.