Inspiration

There are so many people who are physically challenged and still likes to code. They face challenges in typing or they may get bored of giving work to hands.

What it does

The problem with the current speech to text apps is that they are not code syntax friendly. Our project solves this problem. It takes in the voice input from the user and outputs the code.

How we built it

We used Google's speech to text API to convert the recording. We replaced the programming language keywords with their corresponding symbols. This is done by taking from the predefined dictionary. We used C# for the backend conversion.

Challenges we ran into

Google’s speech to text sometimes didn’t recognize the correct pronunciation. so we had to do a lot of testing and optimization to get the desired output.

Accomplishments that we're proud of

We were able to convert the speech into text and use the predefined dictionary of keywords to replace keywords with their values.

What we learned

we learned how to use google cloud instances, ie using API calls and requests.

What's next for HandsFree Coding

For now, it takes the audio recording from the local storage and converts it into code. Further, we are thinking of taking the real-time recordings from the smart home devices like Google home etc. and supporting as many coding languages as possible.

Share this project:

Updates