We recently announced a new program that makes it free to build and host most Alexa skills using Amazon Web Services (AWS). The program aims to help you build engaging skills by giving you access to more AWS infrastructure beyond the AWS Free Tier. Here are five ideas for using AWS services to unlock your skills’ potential.
1. Memory and Context
Excite people to come back day after day by remembering what they were doing last. “Alexa, tell me a joke” is an example of a simple skill that has no memory; you use it and move on. More engaging skills have context and memory. In a game with memory (like the Wayne Investigation or Sub War), you could pause for a few hours then keep going. A skill with context, like Jeopardy! J6, ties its daily clues to the television show.
Storing data in Amazon DynamoDB allows you to add this memory and context to your skill. Persistence allows you to pause games or guide users through a step-by-step process like creating a recipe, tackling a DIY project, or a playing a game.
2. Sounds and Images
To give your customers a more immersive experience, consider incorporating audio files via Amazon S3 to stream short audio bursts, games, podcasts, or news stories in your skill. Many of our most engaging skills, like Ambient Noise and RuneScape Quests – One Piercing Note, include audio sounds, voiceovers, and sound effects that make the in-game experience more immersive. S3 also enables you to store images for Alexa Home Cards that help you provide context and visual feedback to your users.
3. Websites, Apps, VR, and Devices
Using Alexa, you can use your voice to teleport your avatar in VR, drill into a dashboard on a website, control a game, control a boat via raspberry Pi, run a magic mirror, and more. Several AWS services enable you to connect voice commands to Alexa to other devices. You can incorporate AWS IoT and SQS to send messages to websites or a user’s device like a phone, VR, mobile app, or appliance and integrate that device into your skill. As you connect devices and profiles in your skill, you can use Amazon Cognito to easily handle user management, authentication, and device syncing without requiring your own back-end.
4. Machine Learning and Vision
As Alexa continues to become a bigger part of everyday life for consumers and skills stretch into more categories and unexpected applications, developers like you are helping to improve voice user experiences with each innovative skill you create. More advanced AWS integration can help your skills stand out from the crowd.
Try using Amazon Machine Learning tools to create models (without learning complex algorithms) that will help you provide content personalization, surface recommendations, or perform trained behaviors in your skill. Some developers have even used vision-recognition APIs like Amazon Rekognition, a deep-learning image analysis service, to let you know who’s at the door, tell you when a package has been delivered, or further enhance home automation.
5. Continuous Improvement
AWS offers several solutions that will help you improve the user experience and dependability of your skill as it gains users and handles more intricate content. Try integrating Cloudfront to cache dynamic content and files that require heavy lifting so you can improve your response time and provide better deliverability.
Once your skill is live, you can use Amazon Quicksight to visualize analytics you track in Redshift. You can see how your skill is performing, fix user experiences that don’t resonate, and double down on what works to make your skill even more impactful.
For more information on getting started with developing for Alexa, check out the following resources:
- Voice Design Best Practices
- Alexa Skills Kit (ASK)
- Alexa Voice Service (AVS)
- The Alexa Fund
- ASK Developer Forums