Alexa Skill

Notes from Voice Summit 2019

I spent some of this past week at the massive Voice Summit 2019.  Thousands attended to learn and share their experience in the Voice space.  Attendees and speakers were all from a broad set of backgrounds. A lot of the Summit’s speakers and workshops were given by the companies that provide smart speakers and digital Assistants, like Amazon with Alexa and Google.  In addition to helping to market the event, Amazon Alexa staffed a lot of Workshops and Breakout sessions, most of which were aimed at helping developers hone their skills in the voice space. Never used AWS services to boost your skills feature set? They held sessions to walk attendees through exactly what to do.  Samsung's Bixby and Microsoft’s Cortana also made appearances at the summit, by also hosting workshops and announcing new feature releases on the big stage.

It appears that the major Voice Platforms are going about their devices differently. However, one big takeaway from the event is the area that all the platforms seem to agree on. These devices require serious computing services.  Between storage, compute power, scalability, etc. the main platforms agree, you need a strong back-end to make a powerful voice application. Amazon, through their AWS services, Google through its “Cloud Computing” and Microsoft through Azure, all offer options to support an amazing voice experience.  It became a major theme of the Summit. Voice is able to work because of a culmination of technology. Great 4G or WiFi allows the voice devices to communicate with servers in the cloud to quickly give the user helpful information. It is the expertise of all these things that make the most compelling voice applications. This was one side of the conference, the other was all about making great dialog.

The consensus seemed to be, in order to make a compelling voice application, you need great computing, and you need great dialog. Voice applications are easy enough to make and implement; they are hard to make helpful and sticky.  On Alexa alone, a massive amount (over 90%) of skills are used once by a user, and they never return. The emphasis was put on the computing, you need useful information and tasks for a compelling skill, but more than that, you need to get the user in a compelling way.  The voice interaction needs to be quick and to the point.

Alexa and other devices allow for you to change the native assistant’s voice and replace it with actual human voice overs. The number of voice actors at the Summit was quite astonishing.  I counted at least 5 sessions that were focused on voice acting for the voice assistant age. Speakers talked about how the use of human voice differentiated their voice application and made it feel more natural.  

Many other speakers talked about how they use context to help speed up their voice experiences.  By remembering users, skills can quickly repeat actions without re-entering data. Every time I check the weather, I shouldn’t need to tell Alexa where I am.  Voice applications, that take advantage of this have succeeded. Voice applications even allow for third party integration. Want to know the balance of your bank account? Use your username and password once, then get the answer quickly every time you ask.  Similar to other Applications driven by User Experience, voice applications that are able to reduce customer friction have found the most success to date. Just because its called Conversational UI doesn’t mean you have to architect a half hour gab session just to get some basic information from your device.  Interactions designed for efficiency are getting the most utilization.

Find out more about how Voice could help you by reaching out to our team Alexa Subject Matter Experts, VUI designers and Developers:

https://www.bluefintechnologypartners.com/voice-interface-development

5 Tips for Giving Alexa a New Voice

BlogPic.png

                       Do you know someone that would make for a great Alexa Voice? As much as we enjoy a good Joke from Alexa or a quick update on the weather, her voice playback doesn’t always align in providing the unique brand experience you might want to create. Fortunately, the platform with the right voice talent capabilities allows you to substitute Alexa’s voice for something a bit more...

Customizing Alexa’s Voice

Recently, we’ve worked with our great partner at Cecilia.fm to build out a new skill for a client that is uniquely voice-branded. As part of the project, we thought we share a couple of tips for changing Alexa’s voice.

  1. Write out your complete script and build it with Alexa’s voice first

While writing out your script first seems obvious, building it using Alexa’s native voice first is a must. It will save you time in the long run and help you to plan out each transition in the conversation, so you can build out a very complete Voice asset list.

  1. Don’t forget the unexpected while you have your Voice Talent

Outside of your expected dialogues in your conversation map, don’t forget that errors can occur during a conversation if you don’t have the correct Audio files. Consequently, this will make for an awkward experience transitioning from your voice actor to Alexa voice and back. While cutting audio in the studio, make sure you account for the “Oops”, “That wasn’t supposed to happen”, and all those unexpected awkward moments.

  1. Keep your response pieces under 90 seconds

The only way you will be able to change out of Alexa’s voice is to use the SSML <audio> tag. The amount of SSML Audio playback for a given response is a hard limitation of 90 seconds. Likewise, even though you can use multiple <Audio> tags in a single response (up to 5), the sum of all that audio cannot be greater than 90 seconds.

  1. Using Audio over 90 seconds

If your skill requires Audio that is longer than 90 seconds, you need to use the Audio Player inside your code and your user will be exited out of the skill once the audio finishes. Unfortunately, this is a limitation to the Audio Player for now. If you need to use the Audio Player, it may be helpful to let the user know that they are leaving the skill at the end of the Audio file that plays. Also it is a good practice to kindly remind them on how to get back into the skill to encourage repeat visits.

  1. Using SSML in Slot Filling

If your skill needs to use Slots to capture key data from your users, you can use SSML <Audio> in Alexa Speech Prompts for Slot Filling and Slot Confirmation. However, there can be issues with the SSML formatting if you are entering it using the Alexa Skill Kit interface. We recommend you use the JSON Editor to make the changes in the JSON code directly to ensure the SSML tag is formatted properly. This approach also allows you to make sure you are escaping characters properly to prevent any extra spaces in between you Slot variables and the SSML tag.

BlogPic2.png

Snippet of Code

For example, here’s a snippet of a JSON file where we used SSML to playback a custom Audio file based on a prior input from the user. In the skill, we ask the user for the length of time they would like and store it in the variable {time}. We then use that {time} variable as part of an URL construct to call a custom audio file.  

Creating a Unique Voice Experience

Leveraging a custom voice can create a very unique and engaging experience for your end-users.  The effort to do so requires a bit more planning and some massaging of the code, but it is worth it at the end. The developer forum at Amazon is a great resource to leverage and we’d be happy to help you if needed. Feel free to drop us a line.

Cheers -

Jay

Photo Source: https://www.pexels.com/photo/black-amazon-echo-on-table-977296/

Owner: Fabian Hurnaus

Site: Pexels.com

Edited with Adobe XD

Alexa Skill Arbitration Draws Potential for Business Entry

Gone are the days where users have to dig through the deep depths of the skills marketplace to find the skill that they desire. Amazon recently rolled out a new feature called Skill Arbitration that is going to change the way that skills will be found.

Skills Arbitration:

In the fancy words of Amazon themselves:

"In the coming weeks, we’re rolling out this new capability that allows customers in the U.S. to automatically discover, enable and launch skills using natural phrases and requests."

In layman’s terms, when Alexa doesn’t have the information you ask for, it looks for the right skill to get you the answer. Now it will be possible for smaller niche skills to gain some penetration into the skill market.

Let's say you have a stain on that nice shirt that you were gonna wear to that business meeting, but you don’t know how to get the stain off. Being the tech enthusiast that you are, you decide to ask Alexa. Alexa will gracefully handle your request by suggesting you a skill that can handle the situation of getting a stain off by possibly suggesting the Tide skill as described in the announcement article here.

Why is this important?

With this new functionality, this gives any third-party skill opportunity for exposure all for free! This helps to encourage meaningful interactions between your ideal customer demographic and your third-party skill. No need for paid advertising, your own skills can now market themselves based on your own target demographic. I now envision a frenzy of enterprising scrambling to get their hands on their own skills so that they can get their share in the Skill Arbitration process. Getting a skill in the store today will give any type of business an edge over their competitors. Businesses that leverage voice interfacing will enjoy the fastest growing technology platform to date.

Numbers Don’t Lie:

Graph showing massive growth of smart speaker technology within the past year

 

Analysis of current sales trends hints at forecasted growths that appear to be absolutely astronomical. Due to the extremely high penetration rates of the smart speaker markets, smart speakers are set to become an integral component of the reality we will live in tomorrow. In translation, any type of corporation will hopefully seek Alexa based opportunities to get their share of the emerging technology. Rollouts of the arbitration mixed with a massive consumer demand for smart speakers such as Alexa is a mixture for success when it comes to business.

Forward Thinking:

As of last week, Amazon has also released a new feature for Alexa that allows you to sell products and services as well as subscription services all through Alexa. Monetization is a key component that will enable enterprises to add revenue streams all through voice commands. Have an idea of how you can apply a skill to your own business? Don’t know where to start? Check us out here and feel free to connect with us, we would love to help.

Google Assistant makes a splash at CES 2018

CES just wrapped up in Las Vegas.  The event, which takes place yearly, is where the cutting edge of consumer products are shown off.  This year had a clear theme -  getting everyday consumer products connected and equipped with voice interfaces.  Refrigerators, mirrors, toilets, televisions, cars, you name it, people are putting voice into it.  We aren’t here to tell you that all of those gadgets are necessary, but we can say that the age of voice interface is ramping up.  It is no longer in the early adopter stage as Amazon has now sold more than 10 million Alexa powered Echo products.  The market for voice products is no longer a 1 horse race, as Google has put a dent in what was once an Alexa only market.  In Q4 of 2017 it was reported that 7.6 million Google Home products sold, that is more than the total smart speakers sold in all of 2016.  That is a massive amount of hardware.  Reports indicate that 2018 will be even bigger for the purchase of smart speakers, with an estimated 56 million speakers to ship.  These voice assistants aren’t exclusive to their companies hardware though.  Google, for example, has their voice assistant on phones and a lot of the new connected products that were shown off at CES.  Reports say that Google’s voice assistant is now available on over 400 million devices!   This is an exciting time to be involved in Voice.  It can be a seamless and satisfying way to interact with a computer.  Over the holidays, the team at Bluefin did a fun in-house project, developing a Google Action for our kegerator.  We had previously built a connected keg, powered by the open-source Kegbot Arduino, and Raspberry Pi software.  A flow meter collects data on the kegs use and a web interface lets the user give input details about the keg, such as beer type and size of the keg.   Since Google Assistant isn’t restricted to one device, the information is available on any device with Google Assistant.  In the office, we use our Google Home to ask the kegbot questions, like “When was the last beer poured,” but we can also access it on a phone with Google Assistant enabled. Imagine you are at a liquor store, and can’t remember if the keg is low, you simply ask the voice assistant, “How much beer is left in the keg?” With what we were able to do in a week with our in house project, the possibilities seem endless for how helpful voice integration will be.

Below is a quick demonstration of some of what the voice assisted kegbot can do:

https://www.youtube.com/watch?v=_7fsNlsVhOM&t=18s

 

Voice Apps are the New Mobile Apps of the Day

2008-2018-300x146.png

The Voice Assistant and Voice Interface market for the past few years has experienced an increase in demand for high quality voice apps. Although the market as a whole is in the growth stage, the need for well designed voice apps has arrived.

Voice Assisted Devices

us-household-speaker-ownership-2020-01-1-300x176.png

Smart speakers, and devices with voice assistants such as Amazon’s Alexa or Google Assistant has boomed in the past year. If you look farther down the line, analysts predict that by 2020, up to 75% of all US households will have some sort of smart speaker in the home. There is no doubt that this market, just like the mobile phone market of the late 2000s, will see a massive influx of voice apps to support that consumer demand.

Voice Assisted Applications

The Alexa App Store is glutted with daily briefings and trivia apps. But analyzing the usage of most apps you see that many people will use a skill once and never “touch” it again. The market is longing for valuable voice interactions that give users cause to interact with them on a regular basis.

Benefits of Adding Voice to Your App

Companies have seen three main benefits from implementing voice interactions into their apps. 1) By receiving exactly what consumers are asking, businesses are able to tailor content on other platforms to best fit the information customers are looking for.  2) Some companies have found that voice interfaces can fill needs otherwise unreached by standard interface structures and 3) they have also seen that consumers feel that voice can be much more convenient and immediate than their traditional content acquisition solutions.

For more information on getting a voice app developed and launched along with a full report on the voice assisted market, get in contact with us here.

Is Voice The New Touch?

Gone are the days when your home’s IoT devices are controlled through your smartphone or web browser. With smart speakers entering more and more consumer residences, smart home  product interactions have shifted to include non-tactile interfaces which foster unique experiences. Consumers have shown that they are behind the shift, as the number one selling product during Amazon’s Prime Day on July 12 was their Echo Dot. The ability to execute commands and receive information passively without directly changing your task at hand seems to be highly valued by users. Another important feature about these products is that they can be easily integrated to work with other devices as control hubs. With the release of Google Home last November, and the arrival of a second giant to the playing field, the smart speaker/virtual assistant market entered the growth stage of its product life cycle. Prior to this, Amazon’s Echo series had controlled the market with other products launching, but either not creating traction, or having a large enough ecosystem to give them a retainable foothold. While both the Echo and the Google Home have similar functionality, the way in which they interact with other products along with the ecosystem architecture lends for different experiences depending on what product you use. Both products allow users to integrate other devices and services into their voice controlled environments, but use different methods to achieve the same purpose.

Being the first major smart speaker in the market, the Amazon Echo has had a massive lead over Google Home. This is represented in the number of Echo Skills, what amazon calls its voice apps, that have been developed since they released their device. A staggering 15,000  skills have been developed as of June 2017, but it is important to note that a large number of these have only been installed under 100 times. Skills are either integrations or dedicated apps for the device. Skills have been available for the Echo since launch with developer support from the beginning. Skills are handled through an app store experience where you to install individual skills onto the Echo based on users interests. Google takes a different approach with their Google Actions, their version of the same kind of app. Actions are not separate apps that need to be installed on the Google Home, rather Actions get directly integrated into the Google Assistant and can be used immediately by users. Users can still browse available Actions through a directory. This has the benefit of not requiring users to choose apps they need ahead of time. Conversely with Actions, users may find that there are more features than they actually use build into the system.

Neither Amazon or Google’s ecosystem is very challenging to integrate into current systems with straightforward processes for implementation. Both platforms have similar introductory courses on building a simple fact based app for either Alexa or Google Home. Both programs have incentives for developers to build on their platform. Google is currently trying to increase their total number of Actions through cash prizes, while Amazon has a longstanding rewards programs including Echo dot and other perks.

We suggest that the first voice based platform you introduce your product on be Amazon’s Echo through their Skills. There are currently many more users, the build time for the integration is similar to Google’s and if you are in individual developer you are more likely to get some Echo merchandise by releasing a Skill. The caveat that is the Amazon will require you to produce documentation to inform users to install your Skill. But in the short term, it is more likely that your user will actually own Amazon’s product over Google’s. Long term, Google will be a better system, because they have a much more established and wide reaching ecosystem, along with stronger computing potential. Currently their market share is much smaller than Amazon making them a less beneficial first development choice.'

Need assistance building your first Alexa skill? Click through to let Bluefin help you!

Do you have an IoT project you need help with? Bluefin Technology Partners helps companies build amazing connected solutions. We understand the complexity and collaboration required between organizational disciplines in order to deliver an IoT product to market on time and on budget.  We provide the services needed to assess your market, manage your partners, and shepherd your project through successful launch.