Inspiration
Our team was inspired by the speed and large-scale access to AI, which can be used to solve many problems. However, many still prefer human-to-human connection so our team thought of a way to bridge the gap of AI and inter-people interactions to provide an optimal experience for a caller requesting call center operations.
What it does
Our application will use AI to assist call center operations with real-time audio transcription, AI analysis of the call and intelligent AI responses.
How we built it
- Frontend: HTML, CSS, JS, PYQT6
- Backend: Node.js, Express.js
- AI Services: OpenAI Whisper, Google Gemini API
- Audio Processing: SoundDevice
Challenges we ran into
- The program initially did not register any audio properly.
- Configuring the MongoDB database for our application was difficult due to a lack of experience with it.
Accomplishments that we're proud of
- We built a fully functioning desktop application in just one day.
- We successfully integrated the Google Gemini API and OpenAI Whisper into our application.
- We developed an intuitive and modern user interface.
What we learned
- We learned a lot about integrating APIs, such as OpenAI's Whisper and Google Gemini, into our projects.
- We learned about full stack development and all of the resources and programming knowledge to create a good desktop application.
What's next for RoboCop
- To expand this project from call-center operations to other industries in need, such as hospitals or industrial work settings.
Built With
- css
- express.js
- gemini
- html
- javascript
- node.js
- pyqt6
- shell
- socket.io
- tailwind
- twilio
- whisper
Log in or sign up for Devpost to join the conversation.