AI powered Audio Transcriber
Paudel, Anushka (2025)
2025
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2025060921641
https://urn.fi/URN:NBN:fi:amk-2025060921641
Tiivistelmä
In today’s fast-paced digital world, audio content is everywhere from educational institutes and online lectures to interviews, medical procedures, podcasts and meetings. With the rapid growth of this content, the demand for accurate and accessible transcription tools has grown significantly. For students facing tight deadlines to go through lectures, for professionals who find manual note taking during meetings and interviews time consuming, or for anyone needing audio in written form an easier and faster solution is essential.
Traditional manual transcription is time consuming, labour-intensive. Existing tools are mostly behind paywalls or require technical skills, making it less accessible to everyday users, including students, journalists, and researchers. To address this challenge, this thesis presents the implementation of an AIPowered web-based application for audio transcription.
The application was developed with React on the frontend and Node.js/Express on the backend. It integrates Assembly AI, a widely used powerful speech recognition API to transcribe the audio. The aim was to develop a user-friendly, free, multilingual application that anyone can have access without requiring advanced skills or extensive software.
The research of the study led to a working AI-powered transcription web application .The final work includes complete file on GitHub ready for public to clone and use . The primary objectives were accomplished including easy access to audio upload , speech to text conversion and multilingual interface . In the future, the application could be integrated with features such as speaker identification and cloud storage platforms.
Traditional manual transcription is time consuming, labour-intensive. Existing tools are mostly behind paywalls or require technical skills, making it less accessible to everyday users, including students, journalists, and researchers. To address this challenge, this thesis presents the implementation of an AIPowered web-based application for audio transcription.
The application was developed with React on the frontend and Node.js/Express on the backend. It integrates Assembly AI, a widely used powerful speech recognition API to transcribe the audio. The aim was to develop a user-friendly, free, multilingual application that anyone can have access without requiring advanced skills or extensive software.
The research of the study led to a working AI-powered transcription web application .The final work includes complete file on GitHub ready for public to clone and use . The primary objectives were accomplished including easy access to audio upload , speech to text conversion and multilingual interface . In the future, the application could be integrated with features such as speaker identification and cloud storage platforms.