Build voice-first experiences that go beyond voice
Jeff Bezos has said that the original inspiration for Alexa and the Amazon Echo was the Star Trek computer: a cloud-based voice service that can converse with you in a natural way, as well as take advantage of displays when available. That last part is important to us. Since we've launched the first Echo Show, we've learned a lot about how combining voice and visual experiences can make skills even more delightful, engaging, and simple for customers. And with the recent launch of the Alexa Presentation Language (APL), which helps developers build interactive voice-first experiences for tens of millions of devices, we're excited to see what developers do next.
The Alexa Skills Challenge: Multimodal is a way for you to create an Alexa skill using APL and build a voice-first visual experience for devices like the all new Echo Show, Echo Spot, and Fire TV. In addition to helping push the boundaries of what's possible with voice and visuals, you can compete for up to $150,000 in prizes. Additionally, you can earn a new Amazon device just by publishing an APL skil.
What makes a great multimodal skill?
People embrace voice because it’s simple, natural, and conversational. Multimodal skills add additional input and output options when a screen is present in order to:
- Adapt skills to work on different devices. You can optimize your designs and experience based on the type of device to deliver the right experience, from focused personal information delivery on Echo Spot to communal, 7’ experiences on Fire TV.
- Add easily glance-able, complementary information. You can display images, text, and overlays to communicate requested information at a glance, and provide more detail than is possible with voice alone.
- Simplify navigation of large data sets. You can display large amounts of information and help people quickly review options and choose -- using scrolling and selection by voice or touch.
- Create immersive and delightful experiences. You can build engaging experiences that your customers can sit back and watch, or lean into to get things done.
What are the benefits of using Alexa Presentation Language (APL)?
APL is a new design language that enables you to create voice-first, visual Alexa skills that adapt to different device types. With APL, you can:
- Rich: build interactive voice-first experiences that include text, graphics, slideshows, and, soon, video content.
- Flexible: control your user experience by defining where visual elements are placed on-screen, and match the visual expression to your brand guidelines.
- Adaptable: optimize experiences for different Alexa devices for their unique characteristics
- Easy: take advantage of Amazon-supplied sample APL documents that are designed to work well across a broad range of different device types.
Looking for inspiration? See the multimodal experiences other developers have already built with the Alexa Presentation Language.
NEW SAMPLE SKILL - SPACE EXPLORER
- Alexa Skill Teardown: Building the Interaction Model for the Space Explorer Skill
- New Alexa Skill Sample: Learn Multimodal Skill Design with Space Explorer
Main Requirement: Build (or update) and publish a skill that uses the new Alexa Presentation Language (APL) to add multimodal elements to voice-first experiences.
- Skills using display interface or display templates are NOT eligible. Your skill must use APL and include at least one APL document to qualify.
- In some instances, using touch events requires that the Display interface be turned on for a skill. If you are using touch events and run into this problem, we will NOT disqualify the submission as long as you follow all other challenge requirements. You still should not use display interface templates, instead use the equivalent samples in the skill Display authoring tool.
Your skill must be usable on voice-only devices such as the Amazon Echo, and must use APL to add visual content when used on compatible devices with displays such as Echo Show, Echo Spot, and Fire TV.
Submission Package: A skill description, video demo, and other information must be submitted on the Devpost website by January 22, 2019 at 5:00pm EST to be considered. For a complete list of requirements, see the Official Rules.
Certification: All skills must be submitted to the Alexa Skill Store by January 22, 2019 at 5:00pm EST and PASS certification by February 22, 2019 at 5:00pm EST.
- Submissions applying for Category Prizes, Finalist Prizes, and the Grand Prize must use the U.S. Alexa Skills Store.
Submissions applying for International Skill Store Bonus Prizes must apply to the relevant Skill Store and support their primary language. See more info here.
How to enter
- Register for the Alexa Skills Challenge.
- Check out the portal, Getting, and the Resources page for tutorials and Alexa Skills Certification Checklist.
- Learn more about the new Alexa Presentation Language and plan how to best leverage the technology for a great user experience. Check out our blog post.
- Host your skill on AWS Lambda (recommended), or another hosting service of your choice.
- Shoot your demo video and take screenshots of your functioning skill.
- Submit your skill on alexamultimodal.devpost.com AND submit your skill for Alexa skill store certification before January 22, 2019 at 5:00pm EST.
A qualified panel of expert judges
Quality of the Idea Using Alexa Presentation Language
Including creativity and originality, and the ways in which the skill takes advantage of displays and touch when available with Alexa Presentation Language.
Quality of the User Experience
Including the visual design, whether it performs as expected, works well across device types, and more.
Potential Impact of the Idea
Including the extent to which the skill is widely useful, highly entertaining, and more.
Quality of the Submission Package
Including quality of the description, video demo, and any other materials submitted to Devpost.
Customer Engagement (round 2 only)
A variety of factors are considered such as new customers, recurring customers, customer ratings, and more.