Two Voice Devs

Allen has been trying to get into building apps that include LLMs, and has been hearing a lot about the LangChain library. But trying to understand it can be... dizzying. Guest host Noble Ackerson joins to help answer some of the questions about LangChain and how it can bring #ConversationalAI to the #VoiceFirst world and how to use it with your existing APIs.

With Daylight Saving Time ending in the US last weekend, Mark and Allen figured it would be a good... time... to take a look at what date and time features are available to voice developers on Alexa, Alexa APL, Google Dialogflow, Google App Actions, and Jovo. Not to mention discussing the role of ISO-8601 date/time formats, JavaScript libraries such as Luxon, and why UTC isn't always the right time zone.

Resources:

With Google's Universal Analytics sunsetting, everyone is looking at what other tools are available to record user activity in our skills and chatbots. At Allen's suggestion, Mark had checked out the BigQuery service offered by Google Cloud Platform, and created a Jovo plugin to make it available for everyone. We discuss BigQuery and how to use it and this new plugin.

Resources:

We've been exploring some new tools, concepts, and libraries - Mark has been looking at tools to do Named Entity Recognition, while Allen has been exploring the LangChain AI library. But this leads to the question - as you're just starting to learn something new, how do you do so? Do you start with example code? Or YouTube videos? Or what? We share what has worked well for us, along with some early discoveries about what we've been looking at.

If you're working on a #VoiceFirst application that requires Speech to Text in a controlled environment (for example, on an embedded device or in a medical environment), you don't want to have to rely on cloud processing such as those available from Google or AWS. Even if you are willing to use the cloud, it may be cheaper to run your own STT service. Mark and Allen discuss one such way to do so - using the Leopard STT product from Picovoice.

Additional info:

One of our favorite #VoiceFirst features (and not just because of the name) has come to Alexa! Allen and Mark (the real Mark) discuss the new onSpeechMark event that is now available in APL, how it compares to the feature in the Google Assistant Interactive Canvas, and some ways that you can use it to make more powerful and dynamic APL displays.

In our previous episode, Allen and Mark talked about the differences between Dialogflow ES and CX and how both had a notion of front-end integrations. This week, they go in a little deeper, discussing the various ways you can write your own integration if you need to - either by sending text or audio to the Dialogflow API.

Many #VoiceFirst developers know of Dialogflow as a Natural Language Understanding (NLU) system. But is there more to it? Mark and Allen discuss what's different between Dialogflow ES and CX, what's the same, and how both of them provide added value to voice developers (as well as designers).

Did you know Google Chat has an API? That you can build bots for? And that it can even integrate directly with Dialogflow, PubSub, or Google's App Script? Allen introduces Mark to some of the unique and powerful features that the Google Chat API has, explores the various ways you can use it, and ponders some things we can learn when developing for #VoiceFirst.

How is a chatbot different from what we usually think about in the #VoiceFirst world? There are parallels, so Mark discusses some of his recent explorations in what is going on with Microsoft and support for chatbots and Allen compares to some other technology available to developers. There are some interesting updates and changes in progress!