This is a very simple project and most of the parts are off the shelf. Hardware wise the monster’s body is made out of a plastic flowerpot; its mouth is a bit of wood that covers the top of the flowerpot; its eyes, two halves of a plastic sphere painted white with some felt for irises. And then whole thing is covered in some blue fake fur.
Electronics wise, a Raspberry Pi is running the show and handling the text-to-speech is an AIY Voice Hat. A servo fits inside the flowerpot to open and close the monster’s mouth. On the software end of things, a bit of Python has been written that waits for a bit of text, sends it off to the Voice Hat’s text-to-speech module and moves the servo to open and close the mouth. The scary part, connecting the monster to the internet, is done with remo.tv, which is some open-source code hosted on GitHub specifically for allowing control of robots over the internet.
This is a neat little project which is simple enough that kids could build one themselves. The instructions and the python script are up on the Instructables page, and you can see the monster in action at its page on remo.tv. Perhaps [8BitsAndAByte] could add a couple of these internet controlled robot arms to the monster to create a monster that could create some real havoc!
Cruising through the children’s hands-on activity zone at Maker Faire Bay Area, we see kids building a cardboard enclosure for the Chatterbox smart speaker kit. It would be tempting to dismiss the little smiling box as “just for kids” but doing so would overlook something more interesting: an alternative to data-mining corporations who dominate the smart speaker market. People are rightly concerned about Amazon Echo and Google Home, always-listening devices for online retail sending data back to their corporate data centers. In order to be appropriate for children, Chatterbox is none of those things. It only listens when a button is pressed, and its online model is designed to support the mission of CCFC (Campaign for a Commercial-Free Childhood.)
Getting started with a Chatterbox is much like other products designed to encourage young makers. The hardware — Raspberry Pi, custom HAT, speaker and button inside a cardboard enclosure — is conceptually similar to a Google AIY Voice kit but paired with an entirely different software experience. Instead of signing in to a Google developer account, children create their own voice interaction behavior with a block-based programming environment resembling MIT Scratch. Moving online, Chatterbox interactions draw upon resources of similarly privacy-minded entities like DuckDuckGo web search. Voice interaction foundation is built upon a fork of Mycroft with changes focused on education and child-friendliness. If a Chatterbox is unsure whether a query was for “Moana” or “Marijuana”, it will decide in favor of the Disney movie.
Many of these privacy-conscious pieces are open source or freely available, but Chatterbox pulls them all together into a single package that’s an appealing alternative to the big brand options. Based on conversations during Hackaday’s Maker Faire meetup, there’s a market beyond parents of young children. From technically aware adults who lack web API coding skills, to senior citizens unaware of dark corners of the web. Chatterbox Kickstarter campaign has a few more weeks to run but has already reached funding goals. We look forward to having a privacy-minded option in voice assistants.
The device is built around Google’s AIY Voice Kit, which consists of a Raspberry Pi with some additional hardware and software to enable it to process voice queries. [Liz] combined this with a Raspberry Pi camera and the Google Cloud Vision API. This allows WhatIsThat to respond to users asking questions by taking a photo, and then identifying what it sees in the frame.
It may seem like a frivolous project to those with working vision, but there is serious potential for this technology in the accessibility space. The device can not only describe things like animals or other objects, it can also read text aloud and even identify logos. The ability of the software to go beyond is impressive – a video demonstration shows the AI correctly identifying a Boston Terrier, and attributing a quote to Albert Einstein.
Artificial intelligence has made a huge difference to the viability of voice recognition – because it’s one thing to understand the words, and another to understand what they mean when strung together. Video after the break.