The device incorporates a 3.5-inch RGB screen, microphone, and speaker. It allows interaction with different AI engines depending on how the information flow is configured and programmed.

You can create your own backend and use the device as an audio interface with your users, using different TTS/STT platforms. The connection with the different AIs you can use is made through each AI’s API.

The basic environment offered allows you to configure and test the device with the OpenAI Realtime API using your own API key.

In addition to the basic upstream and downstream audio streaming functionalities, our platform allows you to send images to be displayed on the screen (user information, logos, QR codes, etc.).

Thanks to this open environment, any developer can easily integrate it into their products, making the device behave as a voice assistant that understands and responds according to your own AI model or training. By enabling real-time image and audio transmission to the screen, you can create customized intelligent communication systems for business environments.

With this device, AI integration is no longer complex, and you won’t need to use the user’s mobile phone: our platform transforms the device into a universal interface between humans and machines.

Coding example:

POST /api/display/image
Content-Type: application/json
{
«destination_id»: «AB5932FF02»,
«image_format»: «jpg»,
«url»: «www.domain.com/image01.jpg»
}

POST /api/device/config
Content-Type: application/json
{
«destination_id»: «AB5932FF02»,
«brightness»: 85,
«volume»: 70,
«auto_sleep»: false,
«ui_mode»: «minimal»
}

POST /api/ai/engine
Content-Type: application/json
{
«engine»: «OpenAI»,
«model»:»gpt-realtime»,
«api_key»: «xxxxxxxx»,
«parameters»: {
«temperature»: 0.5,
«max_tokens»: 250
}
}