Voice technology carries enormous promise, as many people know from their interactions with Alexa, the voice service that powers devices like Amazon Echo. Our teams here at Amazon are working hard to unlock that potential, but innovation requires a collective effort, from large companies like ours to two-person startups, and from casual hobbyists to major academic institutions.
Today, we’re excited to announce the Alexa Fund Fellowship, a new program to support universities and researchers focused on transformative voice technologies such as text-to-speech (TTS), natural language understanding (NLU), automatic speech recognition (ASR) and conversational artificial intelligence (AI).
Alexa Fund Fellows will receive funding, access to Alexa devices, and mentoring from an Alexa Science team member to develop an undergraduate or graduate curriculum around one or more of these disciplines. The year-long program culminates in a demo day where students can showcase their work for peers, university faculty and members of the Alexa team.
We’re also pleased to announce our first group of university participants: Carnegie Mellon University (CMU), Johns Hopkins University, University of Southern California (USC), and University of Waterloo. Both Carnegie Mellon and Waterloo have already chosen fellows and begun offering classes for engineering students, while courses from Johns Hopkins and USC will begin in fall 2017.[Read More]
A few months ago we introduced Flask-Ask, a new Python framework for rapid Alexa skill development created by Alexa Champion John Wheeler. Today, due to popular demand, John shares how you can deploy your Alexa skills built with Flask-Ask to AWS Lambda, a service that lets you run code without provisioning or managing servers, which you can use to build serverless applications. Check out John’s technical tutorial below, connect with him on Twitter, and hear more about Flask-Ask in the Alexa Dev Chat podcast episode 10.
In our first post, Flask-Ask and ngrok were used to rapidly create a memory game skill and test it locally. This post shows how to use Flask-Ask with the Zappa framework to quickly deploy skills to AWS Lambda. As of this writing, AWS Lambda supports Python 2.7. This tutorial assumes Python 2.7 is installed on your Windows, Mac, or Linux system.
Zappa, a serverless Python framework, uses a combination of AWS components to emulate the WSGI environment on Lambda that Python web frameworks require. Since Flask-Ask is a Flask extension and Flask requires a WSGI environment, Zappa is the perfect fit for deploying Flask-Ask skills to AWS Lambda. To demonstrate, we'll create an Alexa skill that uses the GitHub API to return how many stars, watchers, and forks a repository has.
Let's get started![Read More]
Today we’re happy to share that developers have published over 10,000 skills, making Alexa even better for customers. We’ve been blown away by the innovation and activity in the Alexa developer community. To put it in perspective, we’ve seen a 3x increase in the number of skills available since September 2016 alone. We’ve come a long way in the short time that the Alexa Skills Kit has been available for developers, and we’ve seen a wide range of unique skills that allow customers to do everything from reorder their favorite morning coffee, stay mindful through meditation, control smart home lighting or check their bank account balance.
In November we unveiled a new way for customers to discover Alexa skills and explore the breadth of the Alexa skills catalog. With Alexa skills on Amazon.com, customers can enable skills directly through the website and leave reviews, just like other items on Amazon. Many skills have hundreds of reviews and are rated 4-star or higher by customers. We’ve also added ways for customers to enable and find popular skills, just using their voice.
To celebrate this 10k milestone of skill selection, here are a few Alexa skill highlights:
Andy Huntwork has worked at Amazon for over 10 years, the last three as a principal engineer. He’s developed front-end and backend services for technologies ranging from websites to payment systems and everything in between. But when the Amazon Echo came out in 2015, he saw a new doorway open. Alexa was an exciting way to bring voice-based experiences to the world, and Andy wanted to part of it.
“So I joined the Alexa team,” Andy says, “and immediately started playing around with the Alexa Skills Kit (ASK).” Only a few months after Amazon released ASK, Andy and his wife, Laura, created their first skill. The skill recited public domain works, like Abraham Lincoln’s speeches and The Jungle Book, but the Huntworks wanted to build something more interactive and engaging.
Laura recalls wondering, “What would you ask Alexa to open that’s exciting, even magical? Wouldn’t it be fun to open a magic door?”
From that simple idea grew The Magic Door, an adventure with Alexa guiding you through a growing number of original, interactive stories. Today, The Magic Door skill is a sophisticated adventure framework, hosting 10 adventure storylines, 30,000 spoken words, numerous character voices and hundreds of sounds effects.
To enter a faraway land of magical creatures, perplexing riddles and hidden prizes, just say Alexa, open The Magic Door. Suddenly, you’re off on an adventure with Alexa as your personal guide.[Read More]
Guest post by Tom Hudson; Tech Director @thirteen23. Tom writes about new and emerging platforms and other tech-related stuff.
When I started my job as Technical Director at thirteen23, the owner Doug Cook and I were sitting in a room chatting about projects. At some point during the meeting he said “Alexa, is it still raining outside?” Uh what!? Previous to this I had never seen or heard of an Amazon Echo. Somehow I completely missed it. Needless to say, after the meeting I went back to my computer and immediately bought one. Since then I’ve been hooked on it, writing custom skills and taking advantage of all the integrations. I wrote a 3-part series on my experience building Alexa skills, and thirteen23 has played around with custom integrations such as controls for connected speaker systems.
In a couple of months my coworker Nikki Clark and I will be teaching a workshop at SXSW 2017 on how to design for and build an Alexa skill. If you’re in Austin this March for the SXSW Interactive Festival, you should sign up![Read More]
Today we are happy to announce support for thermostat query, a new feature for Alexa skills developed using the Smart Home Skill API. The feature is now available in the US, with support for the UK and Germany coming soon. With thermostat query, customers can issue a voice command to an Alexa-enabled device, such as the Amazon Echo or Echo Dot, and hear Alexa say the response. For example, a customer with a single thermostat could say, “Alexa, what is the temperature in the house?” and Alexa would respond with the current inside temperature. This complements thermostat commands that already allow customers to set the temperature value.
This new feature simplifies development efforts by enabling specific voice interactive experiences straight from the Smart Home Skill API. In the past, smart home skill developers had to create two skills (one for smart home, the other for custom voice interactions to allow querying data) to provide this overall experience.
When Amazon first introduced the Echo, Nick Schwab was intrigued. He’d always loved voice commands in his car, but he wasn’t sure he wanted to buy another cool device just yet. Then the Echo Dot came out, and once again, Nick couldn’t resist a good deal. He ordered his own Dot, dug into the Alexa Skills Kit (ASK). Right away, he started working on Bargain Buddy, an Alexa skill to relieve him of a daily surf to find daily deals.
Two days after the Bargain Buddy was certified, Nick received his Echo Dot in the mail—his first Alexa device. That’s right, he developed, tested and released his first Alexa skill, before he even had his first Echo Dot.
That was early in 2016. These days, Nick has become a force to be reckoned in the Alexa developer community.[Read More]
A few months ago we shared a free video course on Alexa development by A Cloud Guru, a pioneering serverless education company in the cloud space. Today, we’re excited to announce a new advanced course on Alexa skill building instructed by Alexa Champion Oscar Merry for A Cloud Guru. As the co-founder and head of technology at Opearlo, a voice design agency, Oscar has extensive experience with the Alexa Skills Kit (ASK). He has worked with the technology since November 2015, designing and building skills for clients across a number of industries and use cases. He’s also been giving back to the community and sharing his ASK knowledge by running the London Alexa Devs meetup since July 2016.
In this Advanced Alexa Skills Kit course, Oscar gets you started with the ASK SDK for Node.js and shares a practical project that any meetup organizer can implement to use Alexa as their event assistant.
We are happy to announce a new Amazon Alexa Skills contest with DevPost, the developer-focused job search and hackathon company. We are challenging developers and designers to create unique new skills that make Alexa smarter. To compete for over $40,000 in prizes, you will need to create an original Alexa skill. This is our most open-ended challenge yet. Will you turn Alexa into a concierge, sous chef, fitness coach, personal shopper, or DJ? You decide. The challenge starts now – sign up![Read More]
Speech Synthesis Markup Language, or SSML, is a standardized markup language that provides a way to mark up text for changing how speech is synthesized. Numerous SSML tags are already supported by the Alexa Skills Kit, including: audio, break, p, phoneme, s, say-as, speak, and w.
Alexa now understands SSML Speechcons, which are special words and phrases that are pronounced more expressively by Alexa. Speechcons can be used in English (US) skills by adding a <say-as interpret-as="interjection"> tag around the speechcon you would like to use.[Read More]
Today we’re excited to announce that the Alexa Voice Service (AVS) is now available for developers building voice-enabled products for the UK and Germany. AVS localization provides you with language and region-specific services to expand your audience and delight new customers. With a few lines of code, you can upgrade any product with Alexa to access localized languages and skills in the UK, Germany, and US. Now your end customers can speak with Alexa and receive responses and content in their preferred language and region.[Read More]
Today we are announcing the expansion of the Alexa Voice Service (AVS) to the UK and Germany. This update enables device manufacturers to reach and delight even more customers with localized language models for the cloud-based ASR, NLU and TTS engines, and region-specific skills and content. Your AVS device can now converse in German, get a Flash Briefing from Sky Sports, or call for an Uber in London.
Follow the steps in this blog to prepare your product for use in the UK and Germany.[Read More]
In September 2016, we announced that Amazon Echo, Echo Dot and Alexa were coming to the UK and Germany. Since then, developers have created hundreds of great new skills for customers in these countries. Today we’re excited to announce that the community website Echosim.io has made it even easier for you to build and test your skills by adding new language models for English (UK) and German.[Read More]
The Amazon Alexa team is excited to support betaworks, a startup studio and seed stage VC company based in New York, on its new initiative, voicecamp, an accelerator program focused on voice-based computing.
Accelerate your voice-powered startup with voicecamp
Betaworks’ first accelerator program, botcamp, brought together eight founding teams working on conversational interfaces and chatbots. Now with voicecamp, betaworks wants to support early-stage companies at the forefront of conversational software. Voicecamp’s announcement on January 11, 2017 was covered by TechCrunch, and VentureBeat, as well as other media outlets.[Read More]
Today a speaker is not just a speaker—it’s a connected device we use to play music when we want, where we want, and from whatever service we prefer. New cloud-based, streaming media providers have given us greater control over our music libraries, creating magical and memorable experiences every time we hit “play”.
More than ever, convenience matters, and that’s where Linkplay excels.
Linkplay is a turnkey Wi-Fi audio solution provider that works with device manufacturers to build connected speaker products at various price points and for a growing number of use cases. Whether you want to build a high-end product for the home or a durable portable speaker for camping trips, Linkplay offers customizable product solutions, complete with the latest technologies, to meet your needs.[Read More]