Seeed Studio’s ReSpeaker Speaks All the Voice Recognition Languages

Seeed Studio recently launched its third Kickstarter campaign: ReSpeaker, an open hardware voice interface. After their previous Kickstarted IoT hardware, such as the RePhone, mostly focused on connectivity, the electronics manufacturer from Shenzhen now tackles another highly contested area of IoT: Voice recognition.

The ReSpeaker Core is a capable development board based on Mediatek’s MT7688 WiFi module and runs OpenWrt. Onboard is a WM8960 stereo audio codec with integrated 1W speaker/headphone driver, a microphone, an ATMega32U4 coprocessor, 12 addressable RGB LEDs and 8 touch sensors. There are also two expansion headers with GPIOs, I2S, I2C, analog audio and USB 2.0 and an onboard microSD card slot.

The latter is especially useful to feed the ReSpeaker’s integrated speech recognition engine PocketSphinx with a vocabulary and audio file library, enabling it to respond to keywords and commands even when it’s not hooked up to the internet. Once it’s online, ReSpeaker also supports most of the available cloud based cognitive speech recognition services, such as Microsoft Cognitive Service, Amazon Alexa Voice Service, Google Speech API, and Houndify. It also comes with an SDK and Python API, supports JavaScript, Lua and C/C++, and it looks like the coprocessor features an Arduino-compatible bootloader.

The expansion header accepts shield-like hardware add-ons. Some of them are also available through the campaign. The most important one is the circular, far-field microphone array. Based on 7 XVSM-2000 respeaker_meow2digital microphones, the extension board enhances the device’s hearing with sound localization, beam forming, reverb and noise suppression. A Grove extension board connects the ReSpeaker to the Seeed’s current lineup on ready-to-use sensors, actuators and other peripherals.

Seeed also cooperates with the Meow King Audio Electronic Company to develop a nice tower-shaped enclosure with built-in speaker, 5W amplifier and battery. As a portable speaker, the Meow King Drive Unit (shown on the right) certainly doesn’t knock your socks off, but it practically turns the ReSpeaker into an open source version of the Amazon Echo — including the ability to run offline instead of piping everything you say to Big Brother.

According to Seeed, the freshly baked hardware will ship to backers in November 2016, and they do have a track-record of on-schedule shipped Kickstarter rewards. At the time of writing, some of the Crazy Early Birds are still available for $39. Enjoy the campaign video below and let us know what you think of think hardware in the comments!

Talking Star Trek

Speech generation and recognition have come a long way. It wasn’t that long ago that we were in a breakfast place and endured 30 minutes of a teenaged girl screaming “CALL JUSTIN TAYLOR!” into her phone repeatedly, with no results. Now speech on phones is good enough you might never use the keyboard unless you want privacy. Every time we ask Google or Siri a question and get an answer it makes us feel like we are living in Star Trek.

[Smcameron] probably feels the same way. He’s been working on a Star Trek-inspired bridge simulator called “Space Nerds in Space” for some time. He decided to test out the current state of Linux speech support by adding speech commands and response to it. You can see the results in the video below.

Continue reading “Talking Star Trek”

You Speak, Your Scope Obeys

We’ve been scratching our heads about the various voice-recognition solutions out there. What would you really want to use one for? Turning off the lights in your bedroom without getting up? Sure, it has some 2001: A Space Odyssey flare flair, but frankly we’ve already got a remote control for that. The best justification for voice control, in our mind, is controlling something while your hands or eyes are already busy.

[Patrick Sébastien Coulombe] clearly has both of his hands on his oscilloscope probes. That’s why he developed Speech2SCPI, a quick mash-up of voice recognition and an oscilloscope control protocol. It combines the Julius open-source speech recognizer project with the Standard Commands for Programmable Instruments (SCPI) syntax to make his scope obey his every command. You’ve got to watch the video below the break to believe how well it works. It even handles his French accent.

Continue reading “You Speak, Your Scope Obeys”

The Voice Recognition Typewriter

Typewriters with voice recognition have existed for over one hundred years; they were called secretaries. Robots are taking all the jobs now, and finally dictation and typing is a job that can be handled by a computer. [Zip Zaps] used an old Smith Corona typewriter to automate the process of turning dictation into print. Like a secretary hunched over an anachronistic IBM Selectric in the first season of Mad Men, this robot will take dictation and accept the overt sexism of a 1960s Manhattan ad agency.

Instead of the machinations of a few biological actuators, this typewriter is controlled with an array of servos driven by Pololu Maestro servo controller. There are twelve servos that move a small actuator down onto the keys, and another twelve servos that move the others above the correct row of the keyboard. The carriage return lever is actuated by a stepper motor, linear rail, and giant plastic lever.

While a robot that can use a typewriter is impressive, the real trick is getting it to take dictation. [Zip Zaps] used the built-in voice recognition found in Windows for this, streaming characters over a serial port to the Arduino-based electronics.

Does it work? Yes, surprisingly it does. Is it useful? Well, typewriters naturally have a cleaner, more analog tone about them, and you can’t replicate the typing experience of an old Smith Corona typewriter with a digital format. This build is just the natural extension of what digital electronics are capable of these days, and we look forward to seeing someone with this amazing device in our local Starbucks.

Continue reading “The Voice Recognition Typewriter”

Turning A Page With Your Voice

[Justin]’s friend [Steve] injured his spine a while ago, and after asking what would make [Steve]’s life simpler, the answer was easy. [Steve] missed reading books. Sure, e-readers exist, but you still need to turn the page. Now [Steve] can do that with his voice thanks to some microcontrollers, Bluetooth modules, and a voice recognition module.

A voice-activated page turner wasn’t the first attempt at giving [Steve] the ability to turn a page on a Kindle. The first prototype was a big blue button that sent a keyboard code for ‘right arrow’ over Bluetooth, turning a book one page at a time. This worked well until multiple pages turned, and with no back button it was a major nuisance.

After playing with the voice recognition in an Amazon Echo, [Steve] and [Justin] wondered if the same voice recognition technology could be applied to page turns on a Kindle. With a voice recognition Arduino shield from SparkFun it was easy to detect a ‘page down’ command. A Bluetooth module sends HID commands to a Kindle, allowing [Steve] to read a book with only his voice.

[Justin] put all the design files for this build up on Github.

Upgraded GPS Now Accepts Voice Commands

[FreddySam] had an old Omnitech GPS which he decided was worthy of being taken apart to see what made it tick. While he was poking around the circuit board he found a couple solder pads labeled as ‘MIC1’. This GPS didn’t have a microphone. So, why would this unit have a mic input unless there is a possibility for accepting voice commands? [FreddySam] was about to find out.

The first step to get the system working was to add a physical microphone. For this project one was scavenged from an old headset. The mini microphone was removed from its housing and soldered to the GPS circuit board via a pair of wires. Just having the mic hanging out of the case would have been unsightly so it was tucked away in an otherwise unfilled portion of the case. A hole drilled in the case lets external sounds be easily picked up by the internalized microphone.

The hardware modification was the easy part. Getting the GPS software to recognize the newly added mic was a bit of a challenge. It turns out that there is only one map version that supports voice recognition, an old version; Navigon 2008 Q3. We suppose the next hack is making this work with new map packs. This project shows how a little motivation and time can quickly and significantly upgrade an otherwise normal piece of hardware. Kudos to [FreddySam] for a job well done.

You are Fined 1 Credit for a Violation of the Verbal Morality Statute


Some citizens can control their language and others cannot. What is a civilized society to do? In a dystopian future you can count on electronic monitoring. But wait, the future is now… or it will be in a few weeks. [Tdicola] is building the verbal morality monitor from Demolition Man as his entry in Hackaday’s ongoing Sci-Fi Contest.

Currently the project is in the early planning phase, but holy cow this is a fantastic idea! For those that didn’t see the glorious 1993 feature film, the young [Stallone] pictured above is accepting a ticket (as in: he must pay for his violation) from the tattle-tale wall-mounted computer. Everything about this device is completely feasible using today’s tech. It needs voice recognition and a list of naughty words, a way to play a pre-recorded message, and a printer to spit out the tickets. The build log for the project outlines all of this, as well as possible cost and sources for each.

We’ve been wondering who it was that injected an Artificial Intelligence into our project hosting system. We see both [tdicola] and [colabot] are on the team for this build. The names are too conveniently similar to be a coincidence, don’t you think?