If you haven't read the first series, please read that and come back here.
Let's continue from where we left of last time.
I'm really impressed by the speed at which the transcription is generated to match the speed of the game.
There can be a lot more done to make sure it's even more faster or we could also make it real-time or at least near real-time. But that's a task for another hackathon.
With that said below is the Live Demo that you can watch to see how the real-time transcription is working and at what speed we get the transcripts from the Deepgram servers.
YouTube Video 🎬
GitHub Repo
Santhoshkumard11
/
play-real-steel-boxing-with-your-audio
Get ready for the next phase of gaming!! Control things with your voice.
Play Real Steel Boxing with your voice 🔊🔊 - Real-time speech transcription with Deepgram
Totally inspired by Real Steel Movie and curiosity to build things.
Have you ever wondered how the voice recognition in the Noisy Boy from Real Steel movie works. For people who are new to Real Steel and haven't watched that movie yet. Watch at least the trainer and continue here I was wondering if I could do the same with Deepgram's real-time speech to text API.
The result of two day hustle and surprise!! surprise!! It just worked. ✨
Link to read the dev blog post 📑
Link to watch the YouTube Video 🎬
How to setup locally
-
Create a new virtual environment
py -m venv venv -
Install all the dependencies
pip install -r requirements.txt -
Change the controls and key mappings in the utils file according to the game (leave it as is for Real…
Conclusion ✨
The repo is public now so you guys can try building something on top of what I've done, would love to see what you're planning to go with this.
You don't really need a Flask application to run this, it's just for the demo purpose that I've used to show the power of Deepgram APIs.
You can read more about SDKs available for Deepgram here.
There are lot of example that you can look up to in the Use Case section, just to make yourself comfortable with the usage of real-time speech transcription or Deepgram APIs in general.
Happy Learning! 📑
PRs are welcomed and drop your suggestions in the comments.
Top comments (2)
This is super cool! Great job on your submission 👏🏻
Thanks, glad you liked it!