If we talk about personal assistants, the first thing that comes to mind is the one that we can find on our PC or cell phone, whether it is Siri, Bixby, Cortana, Alexa or the Google Assistant ( which has no proper name). These assistants are responsible for searching for information on the Internet to answer our questions in addition to being able to perform certain actions related to the device on which they are performed.
However, as they always say, imagination has no limits and if not, tell that to Manuel Ahumada who created his own virtual assistant based on Benderthe legendary cigar-smoking robot from the series Futurama.
When we say based on the character from the Futurama series, we mean he used both the voice (from the American version dubbed by John DiMaggio) and the head design. To carry out this project, much more complete than any other personal assistant, he used, of course, a Raspberry Pi and ChatGPT in addition to other AI platforms and, of course, a 3D printer to create the case .
A unique personal assistant
Ahumada has not only built a unique and very original personal assistant, but it is also much smarter than the rest of the personal assistants that can be found on the market (Siri has always made things very simple).
Interaction with personal assistants is limited to asking questions about any problem. Ahumada went much further since he also integrated facial recognition to track the person you are interacting with.
So that this assistant can interact visually and via voice commands, Bender sends questions to ChatGPT to obtain a response in text format, response which is transmitted Eleven laboratories to convert text to voice response with voice, pardon the redundancy, from John DiMaggio, who, as we mentioned above, is the person who nicknamed Bender in the United States.
The use of the camera is not limited to following the user, but can also be used to show objects and even videos so that it offers additional information with its characteristic sarcastic tone. To achieve this functionality, it uses OpenCV.
As we can see in the video above, by activating the recognition function, it is able to detect any type of content and offer information about it, whether it is books or even video games retro like Modified beast that Ahumada plays during the video.
Inside there is a Raspberry Pi 5 Connected to a microphone, a speaker, the camera and several motors are responsible for moving the eyes to give a greater feeling of realism. Unlike other projects created using a Raspberry Pi, the only information available to complete this project is the same that we shared in the article and which is also available in the video posted on YouTube that you can find above these lines.
You know, if you want create your own personal assistant, you only need a Raspberry Pi, ChatGPT to generate the answers, OpenCV to recognize and describe objects and Eleven Labs, so that your assistant has the voice of the celebrity you want. We can’t forget a 3D printer to be able to shape it.
