31 New Features to Unlock More Natural and Immersive Alexa Experiences

Nedim Fresko Jul 22, 2020
Alexa Live Mobile Accessories Make Money Dialog Management Multimodal Reach Customers

Customers now have hundreds of millions of Alexa devices, including smart speakers, smart TVs, headphones, and PCs, and interact with Alexa billions of times each week. Engagement with Alexa skills nearly doubled over the last year. You’ve told us how we can improve the Alexa Skills Kit (ASK) to help you do even more, and we’re excited to announce 31 new Alexa Skills Kit (ASK) features today in response.

With these new features, you can create natural and conversational experiences that allow customers to interact with your skill in an unconstrained way, while freeing you to focus on the highest value parts of your experience. You can deliver immersive multimedia experiences that combine voice with rich sound, visuals, and touch, mixing audio tracks at runtime and leveraging web technologies such as HTML5 for games. You can invent new experiences that customers can use on-the-go and seamlessly resume after doing something else. You can enable customers to use their voices and your mobile apps together, doing some tasks with voice alone and easily switching to your full app experience when needed. Finally, you can simplify discovery and use of your skills and premium experiences, increasing both customer engagement and delight.

Deliver More Natural Experiences with Less Work

The ability to provide a natural experience requires not only understanding individual words and sentences, but also the ability to respond to a wide range of conversational phrases and unexpected turns.

We are adopting deep neural networks (DNNs) to improve Alexa’s natural language understanding (NLU) of individual words and sentences. We’ve begun applying the technology to custom skills and are excited by the early results: although it will vary by use case, we expect skills that use our DNN-based NLU to realize an average of 15% improvement in accuracy. Even better, you don’t have to make any changes to your skill to benefit; your skill’s accuracy will improve automatically once included in the rollout.

Alexa Conversations (beta) is a new AI-driven approach to dialog management that enables you to create skills that customers can interact with in a natural, unconstrained way - using the phrases they prefer, in the order they prefer – while freeing you to focus on the highest value parts of your experience. Unlike traditional dialog managers, with Alexa Conversations (beta) you do not have to code or even identify all of the different ways customers might interact with your skill. Instead, you provide a set of example dialogs and how they map to specific services in your skill. Alexa Conversations (beta) applies deep learning to extrapolate the many possible dialog paths that customers might use, and uses this learning in real-time to automatically manage customer interactions. This includes keeping track of state, maintaining context, accepting customer-driven corrections, and then calling your services at the right time. iRobot and Philosophical Creations are already using Alexa Conversations (beta).

“Alexa Conversations promises to be a breakthrough for developers, and will create great new experiences for customers,” says Steven Arkonovich, founder of Philosophical Creations. “We updated the Big Sky skill with Alexa Conversations, and now users can speak more naturally, and change their minds mid-conversation. Alexa’s AI keeps track of it, all with very little input from my skill code.”

These features are available for US English (en_US) skills. You can learn more about DNNs in our Alexa Science article and about Alexa Conversations in our developer blog.

Create Immersive Audio and Visual Experiences

Customers want immersive experiences that use rich sounds and visuals to convey information, and accept both voice and touch for input. The Alexa Presentation Language (APL) is the technology that enables you to orchestrate these experiences.

APL for audio (beta) lets you use Alexa to mix speech, sounds effects, music, and other audio at runtime. With APL for audio (beta), you can deliver exciting and immersive audio experiences, without the time, effort, and cost required for pre-mixing. Audible, Creativity Inc, Doppio Games, Krogoor Entertainment Studio, Stoked Skills, and Volley, are already using APL for audio (beta).

“APL for audio is a powerful tool that has allowed me to build a rich audio landscape, with less reliance on manual audio editing. Mixing background audio with TTS enabled me to build much more dynamic responses,” says Gal Shenar, founder of Stoked Skills.

The Alexa Web API for Games enables you to take advantage of your knowledge of web technologies to create visually impressive, animated, multimodal Alexa games on screen devices. The Web API for Games supports HTML5, Web Audio, CSS, Javascript, and WebGL. Doppio Games, LC Publishing, Vocala.co, Voice App Labs, and Zynga have already published game skills using the new API.

“Being able to add a rich user interface to enhance the voice-first design is a tremendous tool in drawing players into the Dark Citadel and giving them new ways to play,” says Ryan Jordan, skill creator at LC Publishing. “The Web API opened an entirely new avenue of design for us.”

APL 1.4 is our latest update to APL, and adds editable text boxes, drag and drop UI controls, and back navigation so customers can return to previous screens. You can also take advantage of new live previews in the updated APL authoring tool, and use new APL authoring and preview support in the ASK toolkit for VS Code. APL 1.4 builds on earlier improvements, including animation and vector graphics.

“I use APL to excite my users. A rich display mixed with fun animations, like fireworks when a user reaches the top of Math Mountain, creates a more engaging, multi-dimensional experience that brings people back for more. With APL, skills are simply more fun,” says Brandon Nourse, founder of Seaside Voice Apps.

These features are available for all Alexa locales. You can learn more in our APL for audio blog, Alexa Web API for Games blog, and APL 1.4 blog.

Enable Seamless On-the-Go Experiences

Last year, we released devices that let customers take Alexa on-the-go, like Echo Auto and Echo Buds, as did Fitbit, with the Versa 2, and Bose with their Alexa built-in headphones. Customers tell us how much they like taking Alexa with them, and using their voices for things like getting information and playing music. They also tell us they want Alexa to do more, including help them do more things on-the-go.

Skill resumption (preview) allows customers to easily return to your skill after using Alexa to do something else, or after another activity. Customers can enable your skill to resume automatically, when it has new information to provide, or can simply ask. Alexa remembers that the customer was using your skill, eliminating the need to use your skill name. For example, after customers book a ride, Uber uses skill resumption to proactively report, “Your Uber has arrived.” Customers can also ask “Alexa, how far away is my Uber?”

Skill resumption (preview) is available for US English (en_US) skills. You can learn more in our skill resumption blog and apply for the preview here.

Combine Alexa Skills and Mobile Apps

While voice is helpful for many on-the-go experiences, at times customers want more information.

Alexa for Apps (preview) lets you combine your Alexa skill with your iOS and Android mobile apps to give customers the best of both worlds: natural and hands-free interaction via voice for many tasks, and the option to use voice, touch and visuals to go deeper when needed. With Alexa for Apps (preview), you can enable mobile customers to use their voices to open search results, view more information, and access other app functionality. For example, customers could previously ask the Twitter skill for trends or mentions, and listen to the results. Now, when customers ask, “Alexa, ask Twitter to search for #Alexa Live,” the skill can also open the Twitter app on their phones and display the results. Similarly, TikTok customers will soon be able to say, “Alexa, ask TikTok to start my recording” hands-free. Sonic, Volley, and Yellow Pages are also building with Alexa for Apps (preview).

“Alexa for Apps enables our users to seamlessly play the Volley FM episode they want, without opening our mobile app, finding the episode, and hitting play,” says Jess Thornhill, head of user experiences at Volley. “It’s also extremely helpful for tasks that cannot be completed with voice alone.”

Alexa for Apps (preview) is available for all Alexa locales. You can learn more in our Alexa for Apps blog and apply for the preview here.

Increase Engagement with Skills and Premium Experiences

Whatever type of experience you build with Alexa, customers only benefit when they can easily find and use it. It is not always easy to discover new experiences with voice alone, and to remember invocation names.

Quick Links for Alexa (beta) lets you add a link from your mobile app, website, or online ads that customers can click to launch your skill. This makes it easy for customers to access your skill, and easy for you to track conversion from online ads. CNBC, Domino's, Matchbox, and ViacomCBS are already using QuickLinks for Alexa (beta).

“Being able to open a skill straight from a link is a huge leap forward in our ability to market skills such as Comedy Central Standup,” says Mark Mezrich, VP of voice assistant products at ViacomCBS. “Instead of relying on our audience to remember what they see from us, we can help them directly open the skills.”

The name-free interactions (NFI) toolkit (preview) lets you provide additional signals that Alexa can consider when launching your skill. Using the toolkit, you can configure up to five suggested launch phrases. For instance, for a trip planning skill, one of these phrases can be, “Alexa, help me plan my trip.” You can also indicate specific intents in your skill that Alexa can consider. For example, in the trip planning skill, you can enable a “get train schedule” intent for name free-interaction. Then, if a customer asks, “When is the next train to Union Station?” your skill can be considered to answer. The NFI toolkit (preview) also provides an invocation dashboard that shows you the paths customers use to invoke your skill. While results will be different for every skill, some early adopters of the NFI toolkit (preview) saw up to a 15% increase in dialogs.

Customers now can make in-skill purchases via Amazon.com and on Echo screen devices in addition to via voice. This provides a traditional purchasing experience that some customers may prefer, and allows you to market your premium content with a direct link that customers can use to buy. Most developers with in-skill purchasing don’t have to do anything to enable the capability.

Quick Links for Alexa (beta) and In-skill purchases via Amazon.com and on Echo screen devices are available for US English (en_US) and US Spanish (es_US). The NFI toolkit (preview) is available in English in the US, the UK, and India. You can learn more in our Quick Links for Alexa and in-skill purchasing blog and in our NFI toolkit blog. You can apply for the NFI toolkit (preview) here.

Start Building Now

To learn about all 31 features announced during our Alexa Live keynote today, including updates to ASK SDKs and tools, please visit our Alexa Live release roundup. You can also watch recordings of the Alexa Live technical sessions (link to be posted after Alexa Live) to get started quickly, and attend office hours hosted by Alexa evangelists and the product experts to ask any follow-up questions.

Finally, we invite you to join the Alexa Skills Challenge: Alexa Conversations. In the challenge, you’ll compete with other developers to build the most natural and compelling experience with Alexa Conversations and to win a share of up to $100,000 in cash prizes. The challenge includes bonus prizes for the biggest improvement to an existing published Alexa skill, the best new game, and more.

We can’t wait to see what you build!

Related Articles

Introducing Alexa Conversations (beta), a New AI-Driven Approach to Providing Conversational Experiences That Feel More Natural
Enter the Alexa Skills Challenge: Alexa Conversations to Compete for Over $100,000 in Prizes
Reach More Customers with Quick Links for Alexa (Beta) and New In-Skill Purchasing Options