-
-
The initial interface a user sees when he opens the application.
-
The website after generating summary of an audio file which contains little information about chocolates.
Inspiration
With emergence of many audio files like audiobooks and podcasts; for gaining an overview of what is actually inside the audio without having to waste time on the complete audio, the AudioSummarizer summarizes the content within and provides key points about it.
What It Does
The AudioSummarizer takes in audio files over a range of extensions like .wav. It then sends this file to the backend, which does two things:
- Extract the text from audio.
- Summarize this text using Chrome built-in Summarizer API.
- Display the results to the user.
How We Built It
We built the AudioSummarizer using the following tech stack:
- Flask: Flask is used to run the Python file and create an API for it to integrate into the web application.
- speech_recognition Library: This library is used to extract the text from audio.
- HTML: HTML is used to create a user interface for users to upload their audio files and get a summary of it. -CSS : It is used to create a visually appealing interface for the users. -Chrome built-in API : Summarizer API by chrome built in APIs is used for the summarization. -Javascript : The functionalities like sending call for the API , analyzing and displaying the result to user is done by Javascript.
Challenges We Ran Into
- Finding an API/library to extract text from speech.
- Integrating Flask into the web.
- Setting up the Summarizer API.
Accomplishments That We're Proud Of
- Integrating the Flask app into the user interface and completing the application, which takes an audio file and provides its summary.
- Making a user-friendly interface with a color palette similar to Google's Gemini.
What We Learned
- How to use Chrome built-in APIs.
- How to integrate Flask with web applications.
- How to convert audio to text.
What's Next for AudioSummarizer
- This can be integrated with audiobook and podcast websites for users who want to gain an overview of them.
- Real-Time Summarization: Adding the ability to generate summaries for live audio streams.
- Improved Language Support: Expanding transcription and summarization capabilities to include more languages.
- Mobile App Development: Creating a mobile version for greater accessibility.
Log in or sign up for Devpost to join the conversation.