🎙️ Audio Transcription & Summarisation App
A practical AI application that converts spoken audio into written text and produces concise summaries through a simple web interface. It uses Whisper for transcription and OpenAI-powered summarization to turn recordings into clear, usable notes.
Designed for lectures, meetings, podcasts, and general voice recordings, the app supports common audio formats and saves both the transcription and summary as text files. Its lightweight workflow makes it a useful project for demonstrating how local speech processing and AI summarization can work together in one application.
✨ Key Features
- Transcribes uploaded audio into text
- Summarizes content into shorter notes
- Supports common audio file formats
- Saves outputs locally as text files
- Lets users adjust summary length
- Runs through a simple Flask interface
🔍 How It Works
An audio file is uploaded through the app, then Whisper processes the speech locally and produces a transcription. The transcription is passed to the summarization model, which creates a shorter version of the content for quick review.
🎯 Practical Uses
This project is useful for lecture notes, meeting summaries, podcast breakdowns, and spoken-content archiving. It is a clear example of how transcription and summarization can be combined in a simple but effective AI workflow.