The Generative AI (GenAI) supported Note Takers App is an innovative tool designed to help users capture and organize notes from spoken conversations. This smart application uses advanced technology to record audio, convert speech into text, and then refine these notes using Generative AI like Google Germini and OpenAI GPT.

Users can choose to use the built-in speech-to-text function to convert their recorded lecture/meeting audio into text directly within their devices. In such case, users don't need to worry about sending the audio files to another place on the Internet. On the other hand in the case the users would like to use server-side speech recongition feature due to the built-in speech-to-text model is not always performing so well like a larger and mature open source model, the users also no need to worry about leaking any audio recording in the transit.

It is because the Note Takers project incorporates Public Key Infrasture (PKI), Secure Sockets Layer (SSL) and salted secured hash algorithm to propose, designe, and implement a privacy-protected and secure transmission mechanics and workflow that ensure:

• (1) the audio file's chunks transferring from the app to the server cannot be decrypted and the audio content cannot be interpreted by anyone else;
• (2) the stored chunks on the server waiting for speech-to-text process is protected and cannot be read besides the server itself;
• (3) the speech-to-text process on the server is a stateless process that transcribes chunks on-the-fly;
• (4) once a encrypted chunk is transcribed, the chunk is deleted from the server;
• (5) the stored text transcripts on the server is encrypted and protected so no one else in the world (even the server itself) other than the sender app can read; and,
• (6) once the server passes a stored encrypted transcript back to the app, the transcript is deleted from the server.

VIP Research Group's Note Takers app is perfect for anyone who needs to keep track of lectures, meetings, or any spoken content without manually writing down every word. The app ensures that all data, from audio files to text transcripts, is stored securely, using encryption and secure connections to protect user privacy.

This project combines various technologies to create a seamless note-taking experience. It includes features like audio recording from different sources, breaking audio into manageable parts, and converting these into text. Once the text is generated, the app employs Generative AI to enhance the content, such as summarizing key points or expanding on topics as needed. The app operates independently, handling tasks like audio processing and data storage without user intervention, making it a reliable tool for students, professionals, and anyone looking to enhance their note-taking capabilities.