A DIY, Visual Alexa

Talking to computers is all the rage right now. We are accustomed to using voice to communicate with each other, so that makes sense. However, there’s a distinct difference between talking to a human over a phone line and conversing face-to-face. You get a lot of visual cues in person compared to talking over a phone or radio.

Today, most voice-enabled systems are like taking to a computer over the phone. It gets the job done, but you don’t always get the most benefit. To that end, [Youness] decided to marry an OLED display to his Alexa to give visual feedback about the current state of Alexa. It is a work in progress, but you can see two incarnations of the idea in the videos below.

A Raspberry Pi provides the horsepower and the display. A Python program connects to the Alexa Voice Service (AVS) to understand what to do. AVS provides several interfaces for building voice-enabled applications:

  • Speech Recognition/Synthesis – Understand and generate speech.
  • Alerts – Deal with events such as timers or a user utterance.
  • AudioPlayer – Manages audio playback.
  • PlaybackController – Manages playback queue.
  • Speaker – Controls volume control.
  • System – Provides client information to AVS.

We’ve seen AVS used to create an Echo clone (in a retro case, though). We also recently looked at the Google speech API on the Raspberry Pi.

Continue reading “A DIY, Visual Alexa”

Amazon Offers $2.5M To Make Alexa Your Friend

Amazon has unveiled the Alexa Prize, a $2.5 Million purse for the first team to turn Alexa, the voice service that powers the Amazon Echo, into a ‘socialbot’ capable of, “conversing coherently and engagingly with humans on popular topics for 20 minutes”.

The Alexa Prize is only open to teams from colleges or universities, with the winning team taking home $500,000 USD, with $1M awarded to the team’s college or university in the form of a research grant. Of course, the Alexa Prize grants Amazon a perpetual, irrevocable, worldwide, royalty-free license to make use of the winning socialbot.

It may be argued the Alexa Prize is a competition to have a chat bot pass a Turning Test. This is a false equivalency; the Turing Test, as originally formulated, requires a human evaluator to judge between two conversation partners, one of which is a human, one of which is a computer. Additionally, the method of communication is text-only, whereas the Alexa Prize will make use of Alexa’s Text to Speech functionality. The Alexa Prize is not a Turing Test, but only because of semantics. If you generalize the phrase, ‘Turing Test’ to mean a test of natural language conversation, the Alexa Prize is a Turing Test.

This is not the first prize offered for a computer program that is able to communicate with a human in real time using natural language. Since 1990, the Loebner Prize, cosponsored by AI god Marvin Minsky, has offered a cash prize of $100,000 (and a gold medal) to the first computer that is indistinguishable from a human in conversation. Since 1991, yearly prizes have been awarded to the computer that is most like a human as part of the competition.

For any team attempting the enormous task of developing a theory of mind and consciousness, here are a few tips: don’t use Twitter as a dataset. Microsoft tried that, and their chatbot predictably turned racist. A better idea would be to copy Hackaday and our article-generating algorithm. Just use Markov chains and raspberry pi your way to arduino this drone.

Retrofitting A Vintage Intercom To Run Amazon Alexa

The Amazon Echo is a pretty cool piece of tech: it lets you ask questions, queue up music, find out the weather, and more, without having to do anything but talk. But, the device itself is a bit pricey, and looks a little boring. What if you could have all the features of the Echo, but in a cool retro case and at a cheaper price?

Well, you can, and that’s exactly what [nick.r.brewer] did, using a ’50s intercom and a Raspberry Pi. He picked the vintage intercom up at an antique store for $20, and the Raspberry Pi Zero is less than $10. So, for about $30 (and some parts most of us have lying around) he was able to build a cool looking device with all of the capabilities of the Amazon Echo.

The hardware portion of the build was pretty straightforward, with the Raspberry Pi, a sound card, WiFi dongle, USB hub, and microphone all fitting nicely inside the case of the intercom. The software side of things is a little more tricky, but with a device like this it runs well with Amazon’s Alexa SDK. Of course, if you want to add more hardware features, that’s possible too.

Continue reading “Retrofitting A Vintage Intercom To Run Amazon Alexa”

When The Smart Hits The Fan

A fan used to be a simple device – motor rotates blades, air moves, and if you were feeling fancy, maybe the whole thing oscillates. Now fans have thermostats, timers, and IR remotes. So why not increase the complexity by making a smart fan with an IoT interface?

[Casper]’s project looks more like a proof of concept or learning platform than a serious attempt at home automation. His build log mentions an early iteration based on a Raspberry Pi. But an ESP8266 was a better choice and made it into the final build, which uses an IR LED to mimic the signals from the remote so that all the stock modes of the fan are supported. The whole thing is battery powered and sits on a breadboard on top of the fan, but we’ll bet that a little surgery could implant the interface and steal power internally. As for interfaces, take your pick – an iOS app via the SmartThings home automation platform, through their SmartTiles web client, or using an Amazon Echo. [Casper] mentions looking into MQTT as well but having some confusion; we’d suggest he check out [Elliot Williams]’ new tutorial on MQTT to get up to speed.

Continue reading “When The Smart Hits The Fan”

Retro Rotary Raspi Phone Rings Alexa

[MisterM] is a man after our own heart. He loves to combine the aesthetic of vintage equipment with the utility of new technologies. His latest venture is AlexaPhone, which marries the nearly instantaneous retrieval and computation power of Amazon’s Alexa voice service with the look and feel of a 1970s rotary phone. Best of all, there’s no need to spin the dial and wait for it to go whirring back around. AlexaPhone is ready to take questions as soon as the handset is lifted.

Questions are transmitted through a salvaged USB VOIP phone plugged into the Pi. The user must hang up the receiver in order to trigger the search. Once Alexa has an answer, the audio comes back through a small external amplified speaker with a USB-rechargeable battery. Since the hardware is a bit atypical for Alexa, [MisterM] had a bit of trouble at first trying to query the service with a physical button until he came across this AlexaPi code.

This phone is actually a reproduction of a classic BT Trimphone, which explains the asterisk and octothorpe on the dial.  The modern internals meant that [MisterM] could take advantage of the ribbon cable coming off of the receiver hook to trigger the Pi to send the query. Watch [MisterM]’s kids put Alexa through her paces after the break.

If this has you feeling nostalgic, check out this vintage Chromecast TV we covered recently or this old Russian radio reborn as a Bluetooth speaker.

Continue reading “Retro Rotary Raspi Phone Rings Alexa”

Roll Your Own Amazon Echo On A Raspberry Pi

Speech recognition coupled with AI is the new hotness. Amazon’s Echo is a pretty compelling device, for a largish chunk of change. But if you’re interested in building something similar yourself, it’s just gotten a lot easier. Amazon has opened up a GitHub with instructions and code that will get you up and running with their Alexa Voice Service in short order.

If you read Hackaday as avidly as we do, you’ve already read that Amazon opened up their SDK (confusingly called a “Skills Kit”) and that folks have started working with it already. This newest development is Amazon’s “official” hello-world demo, for what that’s worth.

There are also open source alternatives, so if you just want to get something up and running without jumping through registration and licensing hoops, you’ve got that option as well.

Whichever way you slice it, there seems to be a real interest in having our machines listen to us. It’s probably time for an in-depth comparison of the various options. If you know of a voice recognition system that runs on something embeddable — a single-board computer or even a microcontroller — and you’d like to see us look into it, post up in the comments. We’ll see what we can do.

Thanks to [vvenesect] for the tip!

Let Alexa Control Your Life; Guide To Voice-Enable Everything

Let’s face it, automation doesn’t feel quite as futuristic unless you can just say what you want out loud and have the machines flawlessly obey. That is totally possible now — and on the cheap. Well, cheap as far as money goes. It can be an expensive learning curve to get it all working. This will help. [Lindo St. Angel] has put together a guide to navigate voice control of hardware using Amazon’s Alexa SDK.

We previously reported that Amazon’s AI had escaped its hardware prison in the form of the Alexa Skills Kit. Yes, calling it the Alexa SDK above is wrong it’s actually the ASK but nobody knows what that acronym is while most recognize the gist of an SDK. It gives you the hooks and the documentation necessary to leverage the functionality in your own applications. The core functionality of Alexa is voice recognition. Even so, it’s still a tall hill to climb.

[Lindo] has broken down the problem into a very manageable example. The Amazon Voice Service (part of ASK) is used for voice recognition and control. Amazon’s Lambda service connects the ASK to your piece of hardware; in this case he’s using a Raspberry Pi as the server. The final step is to connect your hardware to the Pi. [Lindo] is interfacing a keypad-based home automation system with the Pi but the sky’s the limit at this point.

With all the authentication and connectivity laid bare, this is a lot more approachable. The question is no longer can you connect everything to voice control. The question becomes should you give control of everything over to one single online service?