What it does
It converts the audio files into text using the AssemblyAI API and gives some other information about the audio too which can be used in a different way
How we built it
I created it using Python language. I used these libraries for the project - -> time -> os -> JSON -> requests -> pandas
Challenges we ran into
The challenges were to successfully print the text in a friendly format
Accomplishments that we're proud of
We can add our audio file via URL or FilePath, in both ways.
What we learned
Working with AssemblyAI API and how useful it can be for different projects.
What's next for Speech2Text-AssemblyAI
Using it in some web projects with proper integration and taking the full advantage of AssemblyAI API

Log in or sign up for Devpost to join the conversation.