Shows
Two Voice DevsEpisode 266 - Supercharging Your AI Agent with SkillsMark and Allen dive into the emerging world of Agent Skills, an open standard for extending the capabilities of AI coding assistants like GitHub Copilot, Claude Code, and Gemini CLI. They explore how these skills work, how they compare to the Model Context Protocol (MCP), and walk through creating and installing a custom skill using the `skills` CLI. They also discuss the skills.sh website by Vercel, which acts as a registry and leaderboard for the ecosystem. The conversation touches on the potential for standardization, the current fragmentation in the ecosystem, and critical security considerations for these powerful new...
2026-01-2943 min
Two Voice DevsEpisode 263 - Exploring the Parlant Agent FrameworkIn this episode, Mark introduces Allen to Parlant, an open-source framework for building agentic AI. They explore how Parlant differs from other frameworks like LangChain and LangGraph by using concepts like "journeys" for flexible conversation flows and "guidelines" for conditional rule application. Mark walks through the key features, including the ability to define glossaries, tools, and the engine's matching process. They also discuss the recent version 3.1 updates, such as linked journeys and behavior criticality levels. Finally, they dive into "Emcie," Parlant's managed NLP service that utilizes a teacher-student model architecture to optimize performance and cost using Small Language Models...
2026-01-1637 min
Two Voice DevsEpisode 253 - The Future of Voice? Exploring Gemini 2.5's TTS ModelIn this episode of Two Voice Devs, Mark and Allen dive into the new experimental Text-to-Speech (TTS) model in Google's Gemini 2.5. They explore its capabilities, from single-speaker to multi-speaker audio generation, and discuss how it's a significant leap from the old days of SSML. They also touch on how this new technology can be integrated with LangChainJS to create more dynamic and natural-sounding voice applications. Is this the return of voice as the primary interface for AI?[00:00:00] Introduction[00:00:45] Google's new experimental TTS model for Gemini[00:01:55] Demo of single-speaker TTS in...
2025-08-2925 min
Two Voice DevsEpisode 251 - AI Agents: Frameworks and ConceptsJoin Mark and Allen in this episode of Two Voice Devs as they explore the fascinating world of AI agents. They break down what agents are, how they work, and what sets them apart from earlier AI technologies. The discussion covers key concepts like "context engineering," and the essential components of an agentic system, including prompts, RAG, memory, tools, and structured outputs.Using a practical example of a prescription management chatbot for veterans, they demonstrate how agents can handle complex tasks. They compare various frameworks for building agents, specifically focusing on OpenAI's Agent SDK...
2025-08-1239 min
Two Voice DevsEpisode 250 - Five Years Up, Up, and Away in Voice & AIJoin Mark and Allen for a very special 250th episode as they celebrate five years of Two Voice Devs! You won't want to miss the unique, AI-animated opening that takes them to new heights, or the special closing that brings it all home, both created with the help of Veo 3. In between, they take a look back at the evolution of voice and AI technology. From the early days of Alexa and Google Assistant to the rise of LLMs and generative AI, they discuss the shifts in the industry, the enduring importance of context, and what the future might...
2025-07-3136 min
Two Voice DevsEpisode 235 - A Developer's Dive into MCPFollowing up on our recent conversation about the Model Context Protocol (MCP), Mark and Allen take a step deeper from a developer's perspective. While still in the shallow end, they explore the TypeScript SDK, the MCP Inspector tool, and the Smithery.ai registry to understand how developers define and host MCP servers and tools.They look at code examples for both local (Standard IO) and potentially remote (Streamable HTTP) server implementations, discussing how tools, resources, and prompts are registered and interact. They also touch on the challenges of configuration, authentication, and the practical messy...
2025-04-2949 minTwo Voice DevsEpisode 230 - Is AI Making Alexa Development Fun Again?Amazon has announced Alexa Plus, powered by large language models (LLMs), and developers are buzzing with anticipation (and a healthy dose of skepticism!). Join Mark Tucker and Allen Firstenberg, your Two Voice Devs, as they dissect the news, explore the potential of the AI-native SDKs, and debate whether this overhaul will reignite the spark for Alexa development.In this deep dive, we cover:* The basics of Alexa Plus: What it is, who gets it for free, and how it differs from classic Alexa skills.* The fate of classic Alexa skills...
2025-03-1246 minTwo Voice DevsEpisode 223 - Grounding Gemini with Google Search and LangChainJSJoin Mark and Allen, your favorite Two Voice Devs, as they explore the exciting (and sometimes frustrating!) world of Gemini 2.0's search grounding capabilities and how to use it with LangChainJS! Allen shares his recent holiday project: a deep dive into Google's latest AI tools, including the revamped search grounding feature, and how he made it work seamlessly across Gemini 1.5 and 2.0. We'll show you the code and demonstrate the differences between using search grounding and not, using real-world examples. Learn how to build your own powerful, grounded AI applications and stay ahead of the curve in the rapidly changing...
2025-01-1022 minTwo Voice DevsEpisode 221 - AI Holiday Gift Guide: Amazon, Meta, Google, OpenAI, and MORE!It's the holiday season, and the AI world has been showering us with gifts! Join Mark and Allen on Two Voice Devs as they unwrap a mountain of new announcements and releases from Amazon, Meta, Google, and OpenAI. From groundbreaking new models to developer-friendly tools, this episode is packed with insights on the latest advancements in AI. We'll explore the features and potential of each new "present" and discuss what it means for you, the developer.
[00:00:00] Intro and Holiday Greetings: Mark and Allen kick off the show, reflecting on the recent flurry of AI...
2024-12-2323 minTwo Voice DevsEpisode 219 - The Ethics of Data Scraping and LLMsJoin Mark and Allen on Two Voice Devs this week as they delve into a critical discussion about data scraping, large language models (LLMs), and the ethical responsibilities of developers. From the recent controversy surrounding BlueSky data scraping and Hugging Face datasets to the complexities of copyright law and personal privacy in the age of AI, this episode explores the gray areas and tough questions facing developers today. Hear their perspectives on the potential misuse of publicly available data, the challenges of anonymization, and the importance of upholding ethical standards in a rapidly evolving technological landscape. They also share...
2024-12-1223 minTwo Voice DevsEpisode 218 - Jovo's Sunset: A Celebration and Look AheadThe Jovo open-source framework, a beloved tool for building cross-platform voice applications, is being archived. Join Mark and Allen as they discuss Jovo's history, its impact on the voice development landscape, and what its sunset means for developers. While the news might be bittersweet, we take this opportunity to celebrate Jovo's contributions and explore the valuable lessons learned from its innovative approach to voice app development. We delve into the framework's key features, including its plugin and pipeline architecture, and discuss how these concepts can still inspire future voice projects. Plus, Mark shares his personal experiences using Jovo and...
2024-12-0928 minTwo Voice DevsEpisode 213 - Scary Developer Stories: A Halloween SpecialBoo! Join Two Voice Devs for a special Halloween episode filled with chilling tales from the software development crypt. Mark and Allen recount true stories of coding nightmares, from dropped databases to runaway pings, and offer words of wisdom for surviving your own development horrors. Listen with the lights on (if you dare) as they explore the spooky side of coding, complete with a chilling Halloween soundtrack. Don't forget to share your own scary developer stories in the comments!
Timestamps:
[0:00:00]: Intro and Halloween greetings
[0:00:14]: Drop Dead Data...
2024-10-3122 minTwo Voice DevsEpisode 212 - Data Labeling for DevelopersJoin Mark and Allen, your Two Voice Devs, as they delve into the crucial world of data labeling for machine learning model training. Whether you're a seasoned data scientist or a developer just starting to explore AI, understanding data labeling is essential for building effective models. In this episode, they explore various data labeling techniques, from manual labeling for simple voice apps to automated approaches using open-source libraries like Snorkel. Discover how labeled data powers everything from chatbots and voice assistants to spam filters and advanced language models like BERT. They discuss practical examples and highlight the role developers...
2024-10-2536 minTwo Voice DevsEpisode 209 - AI-Powered Pronunciation: Conquering Tricky TTSThis episode of Two Voice Devs, recorded before the exciting announcement of OpenAI's GPT-4o Realtime and Audio previews, tackles a classic developer challenge: taming unruly text-to-speech (TTS) engines. Triggered by a listener question, Allen and Mark dive into the frustrating inconsistencies of TTS pronunciation, particularly when dealing with dynamically generated text from LLMs. They explore the limitations of SSML, experiment with phoneme alphabets like X-SAMPA, and even ponder the possibility of multimodal LLMs generating perfect audio natively – a concept now realized with models like GPT-4o Realtime and Audio! While Mark and Allen don't discuss these new models di...
2024-10-0418 minTwo Voice DevsEpisode 207 - Mentorship in Software DevelopmentJoin Mark and Allen on this episode of Two Voice Devs as they dive into the often overlooked but crucial topic of mentorship in software development. They explore what mentorship is (and isn't), the benefits for both mentor and mentee, and share personal anecdotes and practical advice. Whether you're a seasoned developer or just starting out, this episode offers valuable insights into fostering a culture of learning and growth within development teams.
Timestamps:
0:00:00 - Introduction
0:00:45 - Defining Mentorship: It's more than just giving advice
0:04:15 - Mentorship vs. Education...
2024-09-2034 minTwo Voice DevsEpisode 200 - Four Years and Looking ForwardMark Tucker and Allen Firstenberg celebrate 200 episodes and four years of Two Voice Devs! In this special episode, they reflect on the journey so far, the evolution of the AI landscape, and what excites them most about the future of development.
Join them as they discuss:
00:00 Four years ago...
00:10 The evolution of large language models (LLMs) and how the landscape has shifted over the past year.
03:10 The emergence of new players in the AI model space and how Google, Microsoft, and Amazon are vying for...
2024-07-2626 minTwo Voice DevsEpsidoe 196 - Is GPT 4o a Game Changer?OpenAI's ChatGPT 4o and GPT 4o announcements have sent shockwaves through the developer community! In this episode of Two Voice Devs, Mark and Allen dive into the implications of these new models, comparing them to Google's Gemini.
We discuss:
[00:00:10] Initial takeaways from the OpenAI presentations.
[00:02:29] The impressive voice capabilities of ChatGPT 4o.
[00:04:49] Concerns about OpenAI's ambitions for conversational AI.
[00:07:30] The difference between "doing" and "knowing" AI systems.
[00:14:15] A detailed breakdown of GPT 4o, including its strengths and weaknesses.
[00:17:43] Comparison...
2024-06-0622 minTwo Voice DevsEpisode 189 - Farewell, ADR: The Impact on Alexa DevelopersThe Alexa Developer Rewards Program (ADR) is shutting down, leaving many developers wondering about the future of Alexa skills. Mark and Allen discuss the implications of this change, explore alternative monetization options, and share their thoughts on the future of skill development.
Timestamps:
0:00 - Intro and announcement of the ADR program ending
1:45 - History of the ADR program and its impact on skill development
7:13 - Discussion of the Skill Developer Accelerator Program (SDAP) and Skill Coach
14:04 - Status of AWS credits for skill developers
15:10...
2024-04-0526 minTwo Voice DevsEpisode 187 - LLMs in Developer ToolsIn this episode of Two Voice Devs, Mark and Allen discuss how developers can leverage AI tools like ChatGPT to improve their workflow. Mark shares his experience using ChatGPT to generate an OpenAPI specification from TypeScript types, saving him significant time and effort. They discuss the benefits and limitations of using AI for code generation, emphasizing the importance of understanding the generated code and maintaining healthy skepticism.
Timestamps:
00:00:00 Introduction
00:00:49 Using AI as a developer tool
00:01:17 Generating OpenAPI specifications with ChatGPT
00:04:02 Mark's prompt and TypeScript types
2024-03-2126 minTwo Voice DevsEpisode 180 - Run Rabbit OneForget Apps! Talking to this Orange Cube Could Change Everything
Is the app model broken? The creators of Rabbit R1, a new voice-first device, certainly think so. In this episode of Two Voice Devs, Mark and Allen break down this innovative device and its potential to change how we interact with technology. What do developers think about the technology underlying RabbitOS? You may be surprised!
Key topics:
00:02:00 - What is the Rabbit R1? Rabbit R1 is a new type of device that prioritizes voice input and output. It...
2024-01-2947 minTwo Voice DevsEpisode 178 - Looking Forward to 2024In their New Year's discussion, Mark and Allen explore their hopes and predictions for technological advancements in 2024. They discuss the future of Large Language Models (and if that's the right name for them now), expressing anticipation for improvements in latency issues and the potential for models to be hosted on devices rather than cloud-based platforms. The conversation also ventures into the world of AI agents, function calling, and the importance of developers in ensuring safety measures are integrated in AI systems. Finally, they exude excitement about the possibility of AI in multimedia formats, where tools can generate differing output...
2024-01-0530 minTwo Voice DevsEpisode 176 - The Night Before Tech-masMark and Allen get into the Tech-mas spirit, with a little help from Bard.
Hoping you all have the happiest of holiday seasons.
#GenerativeAI #VoiceFirst #ConversationalAI #HappyHolidays
2023-12-2103 minTwo Voice DevsEpisode 169 - First Thoughts on TypeChatMark and Allen explore TypeChat - a new library from Microsoft that makes prompt engineering for function-like operations in #ConversationalAI easier and more robust. Is this a replacement for Intents? Does it go beyond what we could do with Intent-based systems? Is it lacking something? Let's explore!
Learn more:
https://github.com/microsoft/TypeChat
2023-11-0227 minTwo Voice DevsEpisode 168 - Defining Retrieval Augmented GenerationWhat started as a casual conversation between Mark and Allen turned into a brief exploration of what Retrieval Augmented Generation (RAG) means in the #GenerativeAI and #ConversationalAI world. Toss in some discussion about VoiceFlow and Google's Vertex AI Search and Conversation and we have another dive into the current hot method to bridge the Fuzzy Human / Digital Computer divide.
2023-10-2013 minTwo Voice DevsEpisode 167 - What Does Bard Have to Say to Devs?Last week, before Google's annual hardware event, Allen teased part of his prediction about Google Assistant and Bard. This week, we'll show the full clip of Allen's prediction and see just how close he was. Then Mark and Allen discuss how recent announcements from OpenAI, Amazon Alexa, and Google compare to each other and, more important, what they each mean for developers in a #GenerativeAI, #ConversationalAI, and perhaps even a #VoiceFirst world, and perhaps make a few more predictions and what we'll hear next.
More info:
Blog post about Assistant With Bard: https://blog.google/products...
2023-10-1232 minTwo Voice DevsEpisode 166 - What's Next at Google Cloud Next 2023The Google Cloud Next conference is a massive display of the latest technologies and products available from Google Cloud - from AI to Zero-Trust solutions. Unsurprisingly, #MachineLearning was prominent in this years show, so Mark and Allen take a look at some of the biggest #GenerativeAI and #ConversationalAI announcements this year.
More info:
https://cloud.google.com/blog/topics/google-cloud-next/next-2023-wrap-up
2023-10-0635 minTwo Voice DevsEpisode 157 - Three Years... and Still Going!Three years of Two Voice Devs! There's no doubt that the #VoiceFirst industry has changed over that time, with the rise of #GenerativeAI and #ConversationalAI taking the world by storm. Mark and Allen look back at how the show has evolved over this time, and why we hope you'll be joining us as we continue forward on our journey!
2023-07-2717 minTwo Voice DevsEpisode 151 - Requiem for Conversational ActionsThis week, Google completed the "sunset" of Conversational Actions for the Google Assistant. Mark and Allen discuss the ups and downs of Actions on Google, how it fit into the #VoiceFirst landscape, and what may come next.
2023-06-1537 minTwo Voice DevsEpisode 150 - Another Look Backwards and ForwardsAnother milestone episode! Mark and Allen take advantage of the event to look back at our predictions from episode 100, look back at how #VoiceFirst development has changed over the past 50 episodes (and several years), and look forward to what we'll be talking about in the next 50 episodes.
2023-06-0825 minTwo Voice DevsEpisode 146 - Visions of Vector DatabasesWe've touched on the use of vector databases as we've started to explore how LLMs and conversational AIs can be useful, but what are they and how do they work? How are they used for more than just LLMs? Mark and Allen explore some of the classic vector DBs, such as HNSW, and some of the newer fully managed ones, including Metal and Pinecone. We even start to ponder what a fully managed embedding and vector db system might look like from the likes of Google, Azure, or AWS, and are surprised that we're closer than we thought!
2023-05-1143 minTwo Voice DevsEpisode 143 - Experiments With LangChain (Part 1)Over the past few weeks, Mark and Allen have been playing with LangChain and OpenAI, exploring where #ConversationalAI and #VoiceFirst design intersects, and we recorded some of our experiments. In this early one, we take a look at how LangChain with a memory chain can work and keep track of what's going on in the conversation. All in just a few lines of code. More significantly, we discuss the role that LangChain can play in putting together AI and other API components to create voice, web, and app-based agents that include AI as part of the NLU or response...
2023-04-2015 minTwo Voice DevsEpisode 142 - More From APL 2023.1The latest update for the Alexa Presentation Language, APL 2023.1, has been out for a little bit, and Mark and Allen already discussed one of the biggest features - speech marks. But there was more to this release! Allen is, perhaps, even more excited about how selectors can enable some very dynamic APL interactions, and video subtitles and new graphic masks round out what's new.
More info:
* https://developer.amazon.com/en-US/docs/alexa/alexa-presentation-language/apl-latest-version.html - What's New With APL
2023-04-1313 minTwo Voice DevsEpisode 140 - ChatGPT Plugins (and Voice Agents?)With the announcement last week that ChatGPT will soon be supporting plugins, Mark and Allen explore what this means for developers, particularly developers who are used to #VoiceFirst development with Amazon Alexa, Google Assistant, and Samsung Bixby. OpenAI is launching it with some interesting features, including hints at how to monetize plugins, but there are still many questions that developers will need answers to. We explore what will be coming, how to prepare for it, what OpenAI still needs to address, and how all of this may play into the future of voice assistants.
...
2023-03-3051 minTwo Voice DevsEpisode 138 - Time After TimeWith 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:
Luxon: https://moment.github.io/luxon/
Alexa Date/Time slots: https://developer.amazon.com/en-US/docs/alexa/custom-skills/slot-type-reference.html#numbers-dates-times
APL localtime: https...
2023-03-1626 minTwo Voice DevsEpisode 135 - Simple STT with Picovoice and LeopardIf 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:
Serverless Speech to Text article: https://medium.com/picovoice/serverless-speech-to-text-5258e05f7031
...
2023-02-2315 minTwo Voice DevsEpisode 134 - All About (Speech) MarkOne 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.
2023-02-1635 minTwo Voice DevsEpisode 132 - Discussing DialogflowMany #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).
2023-02-0225 minTwo Voice DevsEpisode 127 - Looking Back at 2022As the end of 2022 looms, Mark and Allen look back at some of the highlights of the show, of #VoiceFirst development, of working with Amazon Alexa and the Google Assistant, and of talking to all of you.
2022-12-2916 minTwo Voice DevsEpisode 125 - Chatting About (and With) ChatGPTThe biggest buzz the past few weeks have been about ChatGPT from OpenAI, with some folks in the #VoiceFirst community pondering how this is going to change the nature of conversation design and voice development. Mark and Allen talk about what works with ChatGPT, what doesn't, and how voice developers might be thinking about it's role with building conversational apps and platforms in the future.
Learn more:
* ChatGPT: https://chat.openai.com/chat
2022-12-1526 minTwo Voice DevsEpisode 123 - About App ActionsAs Google has been sunsetting conversational actions, they've been ramping up with support for the new App Actions for Google Assistant. Mark and Allen discuss what App Actions offer for both users and developers and how this compares and contrasts to skills for Amazon's Alexa and apps for Apple's Siri
2022-12-0139 minTwo Voice DevsEpisode 120 - Live and In Person at VOICE22When you're seeing each other for the first time in 3 years, you make it an event! That's what Mark and Allen recently did when they met up at the 2022 Voice Summit in Alexandria, VA. And what better way to commemorate the event than to record a session of Two Voice Devs live in front of an audience? Why, to welcome questions from that audience! Hear our thoughts on #VoiceFirst topics from what developers need to real estate and urban planning in the DC metro region.
Our thanks to the VOICE2022 organizers for helping us with the production...
2022-11-1028 minTwo Voice DevsEpisode 118 - Voicing Thoughts on Glass' FutureAllen may be well known for coordinating his wardrobe with his Google Glass, but he's also as passionate about Glass as he is about Voice. With recent announcements coming from Google about Enterprise Glass v2, Mark asks Allen about what developers should be expecting for Glass' future. And where, exactly, does voice fit into that anyway?
More about Glass:
Glass Info: https://www.google.com/glass/start/
Developer Info: https://developers.google.com/glass-enterprise/
New updates: https://blog.google/products/google-ar-vr/bringing-more-of-googles-productivity-apps-to-glass-enterprise/
[Between] Advanced Wearables for the Enterprise: https://youtu.be/8g-GXFpYFgQ
2022-10-2732 minTwo Voice DevsEpisode 117 - VOICE22 Perspectives and PresentationsNow that Mark and Allen have returned from #VOICE22, they take a look at what the summit was like a share a bit about their presentations. Allen talks about outents and how tools like Dialogflow and Multivocal assist with this concept, while Mark talked about developing a #VoiceFirst prescription system for Alexa.
2022-10-2014 minTwo Voice DevsEpisode 115 - Author! Author!How do you learn new skills in the #VoiceFirst arena? How do you share what you've learned with others? A week before the Voice Summit, Mark and Allen share their experiences as authors, documenters, podcasters, and public speakers.
2022-10-0741 minTwo Voice DevsEpisode 114 - Rules And Regulations (Part 2)No matter if you're building an app for the iPhone or Android, a Google Action, or an Amazon Alexa Skill, there are guidelines that you need to follow to make sure your app is approved by the review team. Mark and Allen go over morerules that you should read before you start to develop your #VoiceFirst skill.
Check out the guidelines for Alexa: https://developer.amazon.com/en-US/docs/alexa/custom-skills/policy-testing-for-an-alexa-skill.html
2022-09-2927 minTwo Voice DevsEpisode 113 - Rules And Regulations (Part 1)No matter if you're building an app for the iPhone or Android, a Google Action, or an Amazon Alexa Skill, there are guidelines that you need to follow to make sure your app is approved by the review team. Mark and Allen go over some of the rules that you should read before you start to develop your #VoiceFirst skill.
Check out the guidelines for Alexa: https://developer.amazon.com/en-US/docs/alexa/custom-skills/policy-testing-for-an-alexa-skill.html
2022-09-2232 minTwo Voice DevsEpisode 112 - Beyond the Assistants: Getting InputIf you're building your own #VoiceFirst app outside the assistants, you'll also need to think about how you get input from people. Fortunately, there are a number of tools available from AWS and Google Cloud (and others) that will help you do this. Mark and Allen go over the raw technologies involved in Automatic Speech Recognition (ASR) and Natural Language Understanding / Processing (NLU / NLP), how they work (broadly speaking), and some thoughts on what needs to be done for the future.
Resources mentioned:
Google Cloud Speech-to-Text - https://cloud.google.com/speech-to-text
Google Dialogflow - https...
2022-09-1553 minTwo Voice DevsEpisode 110 - Building a Jovo PluginMark's been on a roll recently, converting many of the utilities he's built as part of writing Amazon Alexa Skills and Google Assistant Actions into open source plugins for Jovo. This week, Mark and Allen discuss why these kinds of libraries are important, review Mark's latest plugin to generate random player names, and uses this as an example for how to build a plugin for Jovo.
2022-09-0132 minTwo Voice DevsEpisode 109 - Verify and Verify AgainMaking sure our #VoiceFirst applications are written securely and use secure components is important. And when one of those components has a security bug, it is important that we update it as soon as we can. Mark highlights a recent security vulnerability in the node-forge module, which is used by the alexa-verifier-middleware module. Mark and Allen then discuss what the verifier does and how we can be careful when it comes to using libraries.
Some references:
alexa-verifier-middleware: https://www.npmjs.com/package/alexa-verifier-middleware
Alexa verification: https://developer.amazon.com/en-US/docs/alexa/custom-skills/host-a-custom-skill-as-a-web-service.html#manually-verify-request-sent-by-alexa
...
2022-08-2516 minTwo Voice DevsEpisode 105 - What's New From Alexa Live 2022Last week, Amazon Alexa ran their annual developer event, Alexa Live, where they showcased a number of new #VoiceFirst features for Alexa. Mark and Allen take a look at the list of announcements for Skill developers and give some first thoughts on what they mean.
Links:
Feature Roundup: https://developer.amazon.com/en-US/blogs/alexa/alexa-skills-kit/2022/07/Alexa-live-feature-roundup-july-2022
Skill Developer Announcements: https://developer.amazon.com/en-US/blogs/alexa/alexa-skills-kit/2022/07/Alexa-live-announcement-roundup-skill-developers-july-2022
2022-07-2847 minTwo Voice DevsEpisode 104 - Two Years, Two Voice DevsIt's our Second Anniversary show! In addition to a few kind words from our friends, Mark and Allen celebrate by sharing what goes on behind the scenes when creating an episode. How do we come up with #VoiceFirst topics? What is our recording setup like? How do we make transcriptions? Why does Allen always wear a blue shirt? How do you get an episode out every week?
Thank you, everyone, for your questions and your support as we enter our third year!
Mentioned:
Descript - descript.com
gimp - gimp.org
2022-07-2139 min
Two Voice DevsEpisode 101 - What Have You Learned This Week?With Mark and Allen's plans to explore some new tools and features for #VoiceFirst developers, we discuss what we've been playing with for the past week. Mark talks about the Dialog Management API in VoiceFlow and how it can be used by Amazon Alexa developers as a way to easily design and deploy skills, while Allen takes his first steps into re-learning Android development for App Actions.
More information:
https://developer.voiceflow.com/reference
https://developer.android.com/guide/app-actions/overview
2022-06-3021 min
Two Voice DevsEpisode 100 - Looking Back, Looking ForwardOn the occasion of our 100th episode, and with big changes in the #VoiceFirst industry from Google and beyond, Mark and Allen take a moment to look back on where voice has been, and what new developer tools and platforms we'll be looking at for the next 100 episodes.
2022-06-2350 minTwo Voice DevsEpisode 99 - APL: What's New in 2022?Amazon has introduced an update to the Alexa Presentation Language, which allows #VoiceFirst developers to create more dynamic visuals. Mark and Allen discuss what these changes are and why they matter.
2022-06-1625 minTwo Voice DevsEpisode 98 - Gaming and GatesBased on a question from Will Rongholt, Mark and Allen discuss different approaches to implementing a #VoiceFirst game for Alexa skills or Actions on Google that provides a limited number of levels, after which players will need to make a purchase of some sort.
2022-06-0938 minTwo Voice DevsEpisode 92 - AWS Lambda and Google Cloud FunctionsRecently, AWS announced that their Lambda functions could now be invoked directly via HTTP, rather than having to go through another AWS service to access it. Mark and Allen compare this (and Lambda in general) to Google Cloud Functions, which offer similar features, and why these are both important tools in the #VoiceFirst toolbelt.
2022-04-2825 minTwo Voice DevsEpisode 89 - Dealing With DatabasesBased on a question from Dana Gibson, Mark and Allen discuss some of the complexities when it comes to building Actions on Google for Assistant or Alexa Skills that access a database. From dealing with the asynchronous operations to making sure we complete the queries as quickly as possible, from SQL to tools like Firebase, Dynamo DB, and Air Table, we explore some tips and traps about databases in a #VoiceFirst world.
2022-04-0742 minTwo Voice DevsEpisode 88 - OAuth Weirdness, Wisdom, and WoesAn important feature in Account Linking with both Amazon Alexa and the Google Assistant is how they both integrate with existing authorization systems using the OAuth2 protocol. But OAuth2 can be tricky sometimes, as Mark and Allen relate with some tales of woe as they've tried to integrate OAuth into their #VoiceFirst skills and actions. Definitely some weird stuff happening!
2022-03-3137 minTwo Voice DevsEpisode 87 - Voice Content Management Systems (Part 3)With another week to ponder the implications (and implementation), Mark and Allen are both pretty excited to discuss some thoughts around what a #VoiceFirst CMS might look like and how it would work with the Actions for Google Assistant and Amazon Alexa. Specifically, we dig a little bit into what Multivocal and Jovo are currently doing to make things easier on developers and content creators and what more needs to be done.
2022-03-2422 minTwo Voice DevsEpisode 85 - Voice Content Management Systems (Part 1)When it comes to #VoiceFirst applications, we often say that "content is king". But creating great conversations are also part of the content, and require close collaboration between the content author, the conversation designer, and the developer. Frequently updating the content can make for a better Alexa skill or Google Assistant action, but could be complicated. Mark and Allen discuss how (and why) to make this easier using a voice-oriented Content Management System (CMS).
Some products discussed:
sanity.io
Graph CMS
Leximic
multivocal
Jovo
2022-03-1729 minTwo Voice DevsEpisode 83 - Invocations Start It UpLet's get this #VoiceFirst app going! Mark and Allen chat about some of the complexities when it comes to starting your Google Assistant Action or Alexa Skill - either as the start of a conversation, through a "deep link" invocation, or as a "one shot" question or command. While it seems like it should be straightforward, things aren't as easy as they seem! What tricks and tools do we have at our command?
2022-02-2426 minTwo Voice DevsEpisode 81 - HTTP For You And MeMark and Allen take a look at one of the foundational technologies for Alexa Skills and Google App Actions (and all of the modern web) - HTTP. Although originally standing for the HyperText Transfer Protocol, these days it has grown to support a wide range of uses, including the REST protocol, which many #VoiceFirst apps use to make information available for users.
2022-02-1032 minTwo Voice DevsEpisode 77 - A Day In The Life Of A DeveloperMark and Allen discuss what being a senior Software Developer looks like, for them, on a day-to-day basis, and compares how it may differ for #VoiceFirst and more conventional software projects.
2022-01-1844 minTwo Voice DevsEpisode 75 - LIVE!Mark and Allen are joined by friends from around the world via Twitter Space in a live episode to discuss what 2021 looked like for Amazon Alexa and Actions on Google Assistant development, and what 2022 looked like in the #VoiceFirst arena.
2022-01-0938 minTwo Voice DevsEpisode 74 - And a Partridge In a Pear TreeHappy Holidays, everyone! Mark and Allen take a quick look back to see what gifts the #VoiceFirst developer community has gotten for Amazon Alexa and the Google Assistant.
2021-12-2307 minTwo Voice DevsEpisode 72 - Terminology (Part 2)Mark and Allen continue their dive into some of the words we use as we develop #VoiceFirst.
In this episode:
Jovo
Multivocal
ASR
NLP
NLU
Intent
Slot
Slot type / Entity / Entity Type / Custom Entity
Alexa Conversations
Action Builder scenes
Context
Fallback
No match
In Skill Purchases
Account Linking
APL
Display Templates
Cards
Web API for Games
Interactive Canvas
2021-12-0931 minTwo Voice DevsEpisode 71 - Terminology (Part 1)We use a lot of strange terms in the #VoiceFirst world, so Mark and Allen start diving into some of what them mean and what they mean to us as developers.
In this episode:
Smart Speakers
Smart Displays
VoiceFirst
Ambient
Ubiquitous
Amazon Echo
Google Home
Amazon Alexa
Google Assistant
FarField microphone
Wake word
Persona
first party (1P)
third party (3P)
Skills
Actions
Capsules
Voice apps
App Actions
Conversational actions
Dialogflow v1, v2, ES, CX, API.AI
Action Builder
gactions
Console
Webhook
2021-12-0237 minTwo Voice DevsEpisode 66 - Cheering Up Designing Speech MarkdownSometimes you get into a funk, and you need a little bit of self-care to just deal with a week. Maybe you like talking to a friend when you're in that kind of mood. For Mark and Allen, a chat is just the sort of thing to lift their spirits. Even more so when they're talking about coding and how to tackle a design problem for one of the #VoiceFirst open source projects they work on - Speech Markdown. Let's peek in on their conversation to see how they explore and resolve the issues about adding a new feature.
2021-10-2824 minTwo Voice DevsEpisode 65 - Widgets and Other WondersMark and Allen continue talking about the most recent hardware announced from Amazon and how this may mark a change, for both Alexa and the Google Assistant, towards a more widget-focused environment. What do you think this means in a #VoiceFirst world?
2021-10-2145 minTwo Voice DevsEpisode 60 - Put More Pep In Your PromptDo your messages and prompts to your users just drone on and on? Are people begging your voice agent to stop talking and get back to work? Do you fall asleep testing your skill or action? Mark and Allen discuss how to make messages and prompts more exciting!
2021-09-1622 minTwo Voice DevsEpisode 59 - Count to FiveInspired by a design presented at VoiceLunch US/Canada, Mark and Allen discuss how we would implement the design - consisting of keeping a "score" about user's to our skill or action, adjusting the score sometimes, and presenting different prompts based on this score. While the design seems straightforward, there are a number of interesting approaches to the implementation.
How would you implement this design?
What libraries do you want to see to help make your implementations easier?
2021-09-0926 minTwo Voice DevsEpisode 58 - Everything's Pretty RoutineBoth the Google Assistant and Alexa have routines - ways you can create your own phrases to do things. But what do developers need to do to make routines better for their users? Mark and Allen explore the differences between the two platforms and what developers need to know.
Pages mentioned:
https://amzn.to/38zzFT9
2021-09-0325 minTwo Voice DevsEpisode 57 - Who Ya Gonna Call?Most voice skills and actions will need to work with a database or contact another service, and the most common way to do that is with an API. Web API calls are pretty common, but there are some tricks and issues when it comes to voice. Mark and Allen discuss their approaches to using APIs in their apps.
2021-08-2627 minTwo Voice DevsEpisode 53 - What's coming soon? Alexa Live ReviewAt "Alexa Live" last week, Amazon bombarded us with a pile of new features that developers will soon be able to take advantage of. Mark and Allen talk about which features jumped out at them, and what they're looking forward to learning more about.
Which features are you most interested in?
https://developer.amazon.com/en-US/alexa/alexa-live/release-roundup
2021-07-2942 minTwo Voice DevsEpisode 52 - The Anniversary Show!Mark and Allen, with a little help from our friends, celebrate one year of Two Voice Devs by looking back at some of the things that have stood out for us in the past year.
Most of all, however, we want to thank all of you for watching, listening, and sending us feedback. Here's to the next year!
2021-07-2219 min
Two Voice DevsEpisode 50 - "Hey Google, Talk to Two Voice Devs"Our 50th episode! Amazing! Thank you everyone who has been part of this along the way.
We figured this would be a golden opportunity to launch an Action, which we've now done. Mark and Allen chat about what inspired "Talk to Two Voice Devs", how it is more interactive than a typical podcast, how some of it works, and how this is just the first step.
What would you like to talk with a podcast about? We'd love to hear your thoughts and comments.
2021-07-0829 minTwo Voice DevsEpisode 49 - Ready for ReleaseYou've designed the conversations, you've written the code, everything is tested. You can release your skill or action now publicly, right? Well, not quite yet. First you have to get past the review and certification teams at Amazon and Google. Mark and Allen discuss this final step in the development process and what it means for you. Do you have any good tales about the process? Any nightmare stories?
2021-07-0223 minTwo Voice DevsEpisode 47 - Lessons Learned the Hard WayExperience helps you to not make mistakes. But how do you get experience? By making mistakes. And between Mark and Allen, they've made plenty of mistakes in years of programming. They'll talk about some of the lessons they've learned along the way, particularly for voice. What lessons have you learned that you want to share?
2021-06-1723 minTwo Voice DevsEpisode 46 - Hey Google, Show Me The MoneyEventually you're going to want to monetize your Google action and one way to do that is through in-Action transactions. Mark and Allen go over the different kinds of Digital Goods Transactions available and how to use them. (If you're looking for how to do this on Alexa - check out the previous episode.) For more about digital goods transactions, see https://developers.google.com/assistant/transactions
2021-06-1037 minTwo Voice DevsEpisode 45 - Alexa, Show Me the MoneyEventually you're going to want to monetize your Alexa skill, and one way to do that is through In Skill Purchases (ISP). Mark and Allen go over the different kinds of ISPs available and how to use them. (If you're looking for how to do this on the Google Assistant - tune in next week.)
For more about In Skill Purchases, see https://developer.amazon.com/en-US/docs/alexa/in-skill-purchase/isp-overview.html
2021-06-0328 minTwo Voice DevsEpisode 43 - "Live" From Mountain View, CaliforniaThis week is Google I/O, where Google regularly takes the opportunity to release what's new and coming "soon" in the Google ecosystem. Mark and Allen take the opportunity to review what new features have recently come out for developers of Alexa skills and actions for the Google Assistant. What new features of these platforms have you been building for?
2021-05-2036 minTwo Voice DevsEpisode 41 - Bug HuntingDo your skills or actions work on the first try? Of course they don't! That's why we have to find good methods of tracking down and squishing those bugs. Mark and Allen discuss some of their tips for figuring out what is wrong when, on those rare occasions, things don't quite work as expected.
2021-05-0624 minTwo Voice DevsEpisode 40 - Be... Your... Best!In a lot of ways, #VoiceFirst development is like any other programming. But not quite. There are always some good things we need to remember as we build and test our skills, actions, and capsules. Mark and Allen talk about the best practices they follow when starting a project. Do you have any tips and tricks you make sure you follow to make your development life easier?
2021-04-2923 minTwo Voice DevsEpisode 38 - Hello, Greetings, and/or SalutationsMake sure you get your conversation off to a good start with a good welcome message. While you'll rely on your conversation designer to make it sound right, Mark and Allen discuss how to implement all different sorts of welcome messages, and why you may need different approaches at different times.
2021-04-1526 minTwo Voice DevsEpisode 36 - Pete and RepeatImplementing "repeat" is one of the Intents that the review teams from both Amazon Alexa and the Google Assistant require. But they don't really give guidance about how to design or implement that Intent. Mark and Allen discuss the various approaches that they take with the Alexa Skills Kit, Assistant Library, Jovo, and multivocal.
2021-04-0224 minTwo Voice DevsEpisode 31 - Speedy Service with a SmileFive to seven seconds. That's how long you have for your Alexa Skill or Google Assistant Action to reply to a request from the user. And while that doesn't seem very long, if you're waiting for a reply, it can seem like forever. Mark and Allen discuss how important it is to shave milliseconds off your processing, and various techniques to do so.
2021-02-2645 minTwo Voice DevsEpisode 30 - What CAN you do?We received a question from Rebecca Evanhoe asking if there was a way to determine the features of our assistant device for a conversation. Mark and Allen dive into the various ways we can figure that out, and some of the "gotchas" that can come with it.
2021-02-1842 minTwo Voice DevsEpisode 28 - Bug Busters!Debugging is the bane of most developers, but it can be particularly tricky when it comes to voice - between the remote nature of it and the rapid response time required, it can be difficult to capture what is going wrong. Mark and Allen discuss the various tools and tips we have at our disposal to track down those pesky bugs.
Some tools mentioned:
Bespoken - bespoken.io
Sentry - sentry.io
Mocha - mochajs.org
Chai - chaijs.com
Assistant Conversation Test Tool - https://github.com/actions-on-google/assistant-conversation-testing-nodejs
2021-02-0431 minTwo Voice DevsEpisode 24 - Looking Forward: 2021Happy New Year! At least we hope it is. Mark and Allen take a glimpse at the year ahead and discuss what we hope the new year will look like for voice first developers. (Without getting TOO absurd!)
2021-01-0723 minTwo Voice DevsEpisode 21 - Getting the Game OnHave you played Snatch Word or Cross Talk yet? Mark and Allen chat about what it's taken to get their recent games developed and a bit about the underlying technology and code.
2020-12-1736 minTwo Voice DevsEpisode 19 - Oh Say Can You CMSWe often talk about skills and actions being "all about the content", but how do we manage that content if its so important? In a content management system, of course! Mark and Allen discuss their experiences using CMS tools and the crucial role they play in building practical skills and actions.
2020-12-0320 minTwo Voice DevsEpisode 17 - Byte by Byte Putting it TogetherBuilding for voice is more than writing a simple program and you're done. A good voice skill or action has many components that work together. Mark and Allen discuss what some of those components are, how they integrate, and what you should think about as you write them.
Number Spies System Components: https://markvoicedev.medium.com/creating-an-alexa-game-number-spies-system-components-overview-41bf142d0b3c
2020-11-1932 minTwo Voice DevsEpisode 15 - The Times They Are A-Changin'With all the confusion about Daylight Saving Time transitions finally behind us, Mark and Allen discuss all sorts of ways to handle time on Alexa, the Google Assistant, and Bixby. (And some tools and tips that make it easier!)
2020-11-0537 minTwo Voice DevsEpisode 13 - The Right Tool For the JobMark and Allen discuss the tools they use to build Skills and Actions, and some of the tricks to make a developer's life a little easier and more productive.
2020-10-2244 minTwo Voice DevsEpisode 12 - One new feature list just going up, and one even longer going downWhat happens when new features are released? Why, Mark and Allen break into song! And discuss the latest new features developers for Alexa and Google Assistant can work with .
2020-10-151h 00Two Voice DevsEpisode 9 - The Missing Account LinkingAuthentication and Authorization are some of the more difficult concepts that most developers end up having to deal with at some stage. Mark and Allen discuss the high level concept of Account Linking - connecting your auth system to the voice agents auth system. Alexa and Google Assistant offer some tools to help with this, and explore how some of the tools are similar, but others offer significantly different experiences for both users and developers.
2020-09-2433 minTwo Voice DevsEpisode 7 - A different Type of showWe never know where our conversations go, sometimes. This time, Mark and Allen chat about Intents, Slots, Types, Entities, Parameters, and the whole conversational model built around them, especially the slight differences between how Actions and Skills have to treat them.
2020-09-1049 minTwo Voice DevsEpisode 6 - Do you see what I hear?Just because our skills and actions are Voice First doesn't mean they are voice Only. Alexa and the Google Assistant have a long history of supporting displays in addition to the audio interactions. Mark and Allen dive into all the visual options available for Alexa, Assistant, and Bixby and the interesting differences between the three platforms.
2020-09-0341 minTwo Voice DevsEpisode 4 - Tracking the Wily AudioIn an audio-first environment, you want to sound like a movie or TV soundtrack... but with interaction and dynamic responses. With Google's flavor of SSML and Alexa's APLA, you can create these responses. Mark and Allen explore how these two methods are similar, and where they differ.
For more info:
Google's SSML "par" and "media" tags: https://developers.google.com/assistant/conversational/ssml#par
Nightingale SSML editor: https://actions-on-google-labs.github.io/nightingale-ssml-editor/
Alexa's APLA: https://developer.amazon.com/en-US/docs/alexa/alexa-presentation-language/apla-interface.html
2020-08-2025 minTwo Voice DevsEpisode 2 - ConversationsMark and Allen chat about tools we use to build conversations for Alexa and the Google Assistant. Ranging from new tools, such as Alexa Conversations and Google's Actions Builder, to more mature tools, such as Jovo and Dialogflow. We got so excited about the topic, we just couldn't stop!
References:
Alexa Conversations: https://developer.amazon.com/en-US/blogs/alexa/alexa-skills-kit/2020/07/introducing-alexa-conversations-beta-a-new-ai-driven-approach-to-providing-conversational-experiences-that-feel-more-natural
Actions Builder: https://developers.google.com/assistant/console/builder
Jovo: https://www.jovo.tech/
Narratory: https://narratory.io/
2020-08-0648 min