Speech Summary Generator

Audio to text summary generator.

Comment

Inspiration

In the fast-paced world of virtual meetings, Meeting has become a cornerstone for collaboration. However, attendees often struggle with note-taking and maintaining focus while ensuring they're actively engaged. This Chrome Extension aims to enhance the Meeting experience by providing an automated solution for transcription meeting summaries. Offline meetings or talks could also be captured if microphone is turned on. It is great where privacy is a concern and the information shared in a meeting is confedential as it does make use of third party apps.

What it does

The goal of this project is to create a Chrome Extension that:

  1. Captures meeting audio both offline and online with microphone attached and turned on and converts it into real-time transcriptions using Speech Recognition.
  2. Generates a concise summary of the meeting after it ends.

How we built it

Technical Stack

Frontend

  • React.js: Used for building the user interface for the extension popup and settings.
  • Speech Recognition

  • Browser APIs: window.SpeechRecognition and webkitSpeechRecognition for capturing and transcribing audio in real time.

  • Audio Capture

  • Combines getUserMedia and getDisplayMedia APIs to capture microphone and tab audio simultaneously.

  • Processes the audio stream with the Web Audio API for smooth recognition.

Chrome Extension

  • Manifest V3: Defines permissions, background scripts, and content scripts.
  • Background Scripts: Handles global messaging and communication between the extension's popup and content scripts.
  • Content Scripts: Injects logic into Google Meet pages for audio capture and transcription.

Challenges we ran into

  1. Microphone and Audio Capture:

    • Balancing permissions for capturing both microphone and tab audio without user discomfort.Works better if earphones are attached to it.

  2. Speech Recognition Limitations:

    • Managing API errors like not-allowed and handling pauses in speech. ## Accomplishments that we're proud of

What we learned

Creating a chrome extension and integrating Gemini nano .

What's next for Speech Summary Generator.

Future Scope

  • Multi-language Support: Extend transcription to other languages.
  • AI Summarization: Use NLP techniques to generate more insightful summaries.

Built With

Share this project:

Updates