AI-powered chatbots are pretty cool, but most still require you to type your question on a keyboard and read an answer from a screen. It doesn’t have to be like that, of course: with a few standard tools, you can turn a chatbot into a machine that literally chats, as [Hoani Bryson] did. He decided to make a standalone voice-operated ChatGPT client that you can actually sit next to and have a conversation with.
The base of the project is a USB speaker, to which [Hoani] added a Raspberry Pi, a Teensy, a two-line LCD and a big red button. When you press the button, the Pi listens to your speech and converts it to text using the OpenAI voice transcription feature. It then sends the resulting text to ChatGPT through its API and waits for its response, which it turns into sound again through the eSpeak speech synthesizer. The LCD, driven by the Teensy, shows the current status of the machine and also provides live subtitles while the machine is talking.
To spice up the AI box’s appearance, [Hoani] also added an LED ring which shows a spectrogram of the audio being generated. This small addition really makes the thing come alive, turning it into what looks like a classic Sci-Fi movie prop. Except that this one’s real, of course – we are actually living in the future, with human-like AI all around us.
All code, mostly written in Go, is freely available on [Hoani]’s GitHub page. It also includes a separate audio processing library called toot that [Hoani] wrote to help him interface with the micophone and do spectral analysis. Anyone with basic electronic skills can now build their own AI companion and talk to it – something that ham radio operators have been doing for a while.
Continue reading “AI-Powered Speaker Is A Chatbot You Can Actually Chat With”
Electronics have been sent to some pretty extreme environments, but inside a living host is a particularly tricky set of conditions, especially if you don’t want to damage the organism ingesting the equipment. One step in that direction could be an edible battery cell. (via Electrek)
Developed by scientists at the Istituto Italiano di Tecnologia, this new cell is made from food additives and ingredients to skirt any nasty side effects one might experience from ingesting a less palatable battery chemistry like NiCd. A riboflavin anode is coupled with a quercetin cathode, both with activated carbon to increase conductivity. Encapsulated in beeswax and with a separator made of nori algae, the battery is completely non-toxic.
The cell generates a modest 0.65V with a max sustained current of 48 µA for 12 min, but it shows promise as a power source for ingestible medical sensors, even if it won’t be powering your next mobile Raspberry Pi project. This isn’t the first time we’ve seen edible electronics; check out this screaming chocolate rabbit or robots made of candy.
In our surface-mount age, it’s easy to be jaded about miniaturization. We pretty much expect every circuit to be dimensionally optimized, something that’s easy to do when SMDs that rival grains of sand are available. But dial the calendar back half a century or so and miniaturization was a much more challenging proposition.
Challenging, perhaps, but by no means unachievable, as [Helge Fyske (LA6NCA)] demonstrates with this ultra-compact regenerative vacuum tube receiver. It’s a companion to his recent “spy transmitter,” a two-tube radio built in — or on, really — an Altoids tin. The transmitter was actually a pretty simple circuit, just a crystal-controlled oscillator and an RF amplifier really, but still managed about 1.5 Watts output on the 80-meter ham band.
The receiver circuit ended up being much more complicated, as receivers do, and therefore harder to cram into the allotted space. [Helge]’s used a three-tube regenerative design, with one tube each devoted to the RF amp, detector/mixer, and audio amplifier stages. As in the transmitter, the receiver tubes are mounted on the outside of the box, with the inside crammed full of components. [Helge] had to be quite careful about component positioning, to prevent interstage coupling and other undesirable side effects of building in such close quarters.
Was it worth it? Judging by the video below, absolutely! We’ve rarely heard performance like that from even a modern receiver with all the bells and whistles, let alone from a homebrew design under such constraints. It sounds fantastic, and hats off to [Helge] for completing his spy radio suite in style.
Continue reading “Tiny Three-Tube Receiver Completes Spy Radio Suite”
A continuity tester, as found on most multimeters today, is a great tool for finding broken connections and short circuits. But once you’ve found a short, it’s up to you to figure out which part of the circuit it’s in – a tedious job on a large PCB with hundreds of components. [John Guy] aims to ease this task with a continuity tester that modulates the beeper’s tone according to the resistance measured in the circuit. Tracking down a short circuit is then simply a matter of probing multiple points along a track and observing whether the pitch goes up or down.
The circuit is based on a single AD8534 quad op amp chip. The first stage measures the voltage across the circuit under test in response to small current and amplifies it. The resulting signal is fed into a voltage-controlled oscillator (VCO) made from one op amp connected as an integrator and another working as a comparator with hysteresis. Op amp number four amplifies the resulting square wave and drives a speaker. A low-pass filter makes the sound a bit more pleasing to the ears by removing the higher notes.
[John] paid particular attention to the PCB design to make it easy to assemble despite having a large number of SMD components on a small board. He even placed a parts list on the rear silkscreen, so anyone can assemble it even without the accompanying documents. The resulting board can be placed in a laser-cut acrylic case, turning it into a neat handheld instrument that will definitely find a place in any engineer’s toolbox. Measuring resistance through sound is not as accurate as using a full four-wire setup with an ohmmeter, but will be much faster and easier if you just want to find that annoying solder bridge hiding somewhere on your board.
An old joke is that Emacs is a text editor with an operating system included, given that its extensibility and customization often goes far beyond traditional text editors. Part of its well-earned reputation comes from being built in Lisp which allows it to be expanded to do almost anything. Despite this in-joke in the community, though, you will still need an actual operating system to run it, but not much more than that.
This project uses User-Mode Linux (UML) as a foundation to load almost nothing other than an Emacs editor. UML is a virtualization technology that allows running multiple Linux kernel instances as separate virtual machines, so once the Linux environment is started and Emacs is compiled, the virtual machine can essentially boot straight into an Emacs environment. Some tools are needed outside of the Linux kernel like mount which allows the virtual file system to access the files needed to build Emacs, but as far as lightweight or minimalist Linux distributions go this one definitely gets at least an honorable mention.
While UML is virtualization software rather than a full-fledged Linux distribution, we would expect a similarly minimalist build could easily be done with something more hardware-based like Linux From Scratch. Emacs has been around for so long and had such a wide reach that it’s difficult to imagine a world without it. Even in more modern technology like browsers, knowing a little bit about Emacs can be an extremely powerful tool.
When you think of NASA, you think of high-stakes, high-cost, high-pressure engineering, and maybe the accompanying red tape. In comparison, the hobby hacker has a tremendous latitude to mess up, dream big, and generally follow one’s bliss. Hopefully you’ll take some notes. And as always with polar extremes, the really fertile ground lies in the middle.
[Dan Maloney] and I were thinking about this yesterday while discussing the 50th flight of Ingenuity, the Mars helicopter. Ingenuity is a tech demo, carrying nothing mission critical, but just trying to figure out if you could fly around on Mars. It was planned to run for five flights, and now it’s done 50.
The last big tech demo was the Sojourner Rover. It was a small robotic vehicle the size of a microwave oven that they hoped would last seven days. It went for 85, and it gave NASA the first taste of success it needed to follow on with 20 years of Martian rovers.
Both of these projects were cheap, by NASA standards, and because they were technical demonstrators, the development teams were allowed significantly more design freedom, again by NASA standards.
None of this compares to the “heck I’ll just hot-air an op-amp off an old project” of weekend hacking around here, but I absolutely believe that a part of the tremendous success of both Sojourner and Ingenuity were due to the risks that the development teams were allowed to take. Creativity and successful design thrives on the right blend of constraint and freedom.
Will Ingenuity give birth to a long series of flying planetary rovers as Sojourner did for her rocker-bogie based descendants? Too early to tell. But I certainly hope that someone within NASA is noticing the high impact that these technical demonstrator projects have, and also noting why. The addition of a little bit of hacker spirit to match NASA’s professionalism probably goes a long way.
As NFC chips proliferate, so do the antennas they require for operation, and since many NFC-enabled items are single-use, this means there’s an opportunity to put them to other uses. It’s an avenue pursued by [Brother-live], as he strips the antennas from spent metro tickets and gets experimenting.
The antenna in an NFC-enabled card is a flexible PCB laminated between the plastic outer layers, with the tracks forming a coil round the outside of it. Using some solvent the cards can be easily separated and the antennas retrieved. Once the chip has been removed they can be cleaned up and soldered to, allowing wires to be connected.
What can you do with an NFC antenna? Not a huge amount as you can see in the (Russian language, English subtitles) video below the break, but he tries it as a not-very-good heating pad, a power harvesting antenna from NFC readers, and perhaps most promisingly, as the coil of a moving-coil speaker. We’re not sure how much effort would be worth making on that last front, but we think with a bit of care there might be room for audible improvement.
If you’ve ever been tempted to have a look at an NFC card, it’s a subject we’ve covered before.
Continue reading “NFC Antennas Have Other Uses”