What I am building
English is not my first language. After living in United States for more than 10 years, I can handle daily conversations fine. However, if there is one thing I still fear, it is those phone calls ๐. When the phone call conversation is mixed with background noises or the person speaks in accents/dialects that I am not familiar with, my listening skill collapses.
Sadly, I am not the only one. There are some people in my family who does not get exposed to English conversations everyday or learn English at educational institutions, like I did. They often ask me to make phone calls on behalf of them.
There are excellent tools like online dictionary and translation service (ie. AWS Translate) that they can utilize but that requires the person to multitask between using those tools and paying attention to the conversation at the same time.
So I propose to build a tool where you can:
- A user makes a phone call
- The conversation is transcribed in real time
- The transcribed text can also be translated in real time
- Those transcription & translation are visible to the user, in real time.
I see these could potentially benefit:
- Those who is more comfortable with reading than listening in English
- Those who face difficulty in hearing
Demo Link
TODO
Link to Code
TODO
How I built it (what's the stack? did I run into issues or discover something new along the way?)
TODO
Additional Resources/Info
TODO
Top comments (1)
This is a great idea! You can do real-time transcriptions on Twilio phone calls with Twilio Media Streams: twilio.com/blog/live-transcribing-...