The developer combined Siri and the GPT-3 neural network and made a real smart voice assistant

Web developer Mate Marshalko spoke on Mediumhow he created a voice assistant based on Siri and the GPT-3 neural network.

The impressive thing is that he didn’t have to write any code to achieve this. Instead, he explained to GPT-3 what he wants to do, which is to transform the neural network into AI for smart home control. Marshalko asked her to interpret spoken English and provide an appropriate response in JSON format.

I described the types of requests, the exact structure of the response, and asked her to behave like a sentient AI, giving advice even on personal matters. I also provided some details about the time, location, devices, and rooms in the house. From this we will get a perfectly structured answer. And that’s all there is to programming!

Our example request was: “Just noticed I’m recording this video in the dark at the office. Can you do something about it?”

And we got the answer:

“action”: “command”
“location”: “office”
“target”: “light”
“value”: “enabled”,
“comment”: “I turn on the light for you.”,
“ScheduleTimeStamp”: “”

— Mate Marshalko

There were many such examples. In particular, the voice assistant, at its discretion, set the possible comfortable temperature in the bedroom.

Work demo:

Marshalko used the Siri command to turn it into a real HomeKit tool. Surprisingly, everything worked perfectly the first time. [9to5]

🤓 Want more? Subscribe to our Telegram.

Loading To bookmarks


Such Siri should have been originally.

  • Before

    First full trailer for ‘Scream 6’ starring Jenna Ortega released