The seamless browser to browser real-time audio and video communication that WebRTC enables is supported by a complex infrastructure. Things like signaling, NAT traversal and codec optimization can be difficult to maintain by the average development team unfamiliar with the intricacies of the WebRTC stack. CPaaS providers such as the Amazon Chime SDK, Daily and Vonage encapsulate such complexity and offer easy to use Application Programming Interfaces (APIs) that you can integrate into your application

On the April 10, 2024 episode of WebRTC Live, Arin welcomed industry guest, Dan Jenkins for a discussion on a wide range of real-time and broadcast technologies and where WebRTC stands amidst these advancements. Dan shared the latest updates on the WHIP/WHEP protocols, discussed unbundling with WebTransport and WebCodecs, and delved into other cutting-edge technologies including Media over QUIC and SRT. Dan Jenkins is the founder and CEO of Nimble Ape and Everycast Labs and the organizer of CommCon, the only

In a previous post, Evaluating and Improving Voicebot Flows with Call Stats, we introduced this vital health check for the continuous improvement of voicebot performance. Call statistics gauge bot effectiveness and identify bottlenecks and potential flow disruptions in AI agent workflows. Adding call stats to voicebot flows involves identifying where the business logic is defined and adding the corresponding logic there. For simple scenarios, recording the data can be done taking advantage of tools that

Each month, we ask our dynamic team of WebRTC developers, mobile developers, designers, testers, DevOps experts, and project leads to share some of the impactful work they did in the past month. Here’s a short list of some that might interest you — at least the ones we can talk about! Building a WebRTC SDK for Windows applications using C#. Built a PoC using the Janus Gateway Server and the aiortc Python WebRTC library  Added

At Enterprise Connect 2024, I saw the latest updates around AI in enterprise communications. It was an interesting contrast to my 2023 visit to the same conference. While the hype was more or less the same, there has definitely been progress in turning that hype into reality. This was especially true around Deterministic AI and Generative AI in the contact center.  https://youtu.be/dDcQyRP5570 As you might guess from the name, the annual Enterprise Connect conference is

As the Program Manager of our dedicated Managed Services Provider (MSP) team at WebRTC.ventures, I cannot help but feel a profound sense of pride. Leading this talented and committed group has not only been a professional privilege, but a personal journey of growth and learning. Through the unwavering commitment and collaborative spirit of our team, we've navigated the complex landscape of providing superior managed services for real-time applications, uncovering valuable insights that are essential for

In A Serverless Approach to Post-Call Analysis Using AWS Lambda, Amazon Transcribe, and Amazon Bedrock, we saw the benefits of leveraging a serverless model for implementing AI-based post-call analysis in contact center solutions. We highlighted how building such a pipeline to evaluate service and sales calls avoids the compilations inherent in provisioning the underlying infrastructure of an AI model and avoids paying for unused resources. Instead, your technical team can focus on the application itself,

AI and LLMs are everywhere these days. In contact center applications, they are the key to implementing next generation post-call analysis, making manual work by supervisors and third party surveys a thing of the past. AI-based post-call analysis provides an automated approach to capture recordings of customer service or sales calls, transcribe them, and then leverage an LLM to analyze the activities to evaluate agent effectiveness, identify areas for improvement, and gain a range of

As I prepare to attend Enterprise Connect 2024 in Orlando next week, I’ve been thinking about what has changed around the state of large-scale business communications and enterprise-ready AI since last year’s event. I’m also very curious to hear what the speakers and vendors see on the horizon.  My only full day there will be Wednesday March 27, so there’s going to be a lot to pack in! If you’ll be at Enterprise Connect, too,

The Amazon Chime SDK emerges as a compelling alternative to Twilio Programmable Video, offering a comprehensive suite of features and a secure, scalable infrastructure that supports customized WebRTC video, audio, and chat solutions that cater to the dynamic demands of many industries. In telehealth and edtech where video communication is vital infrastructure, the Amazon Chime SDK provides a reliable and feature-rich alternative to the Twilio Video SDK.  While prompted by the discontinuation of support for the

The Janus WebRTC Media Server turns ten this year. Its author, Meetecho, is celebrating with JanusCon, a live event April 29 and 30 in Napoli, Italy on all things Janus and RTC! WebRTC.ventures is not just proud to be a sponsor; our Chief Technology Officer, Alberto González Trastoy, will also be speaking at the event. Unveiling the Tech Salsa of LAMs with Janus in Real-Time Applications In the realm of real-time applications, Large Language Models (LLMs)

The WebRTC industry continues to evolve at a rapid pace.  On the March 13, 2024 episode of WebRTC Live, Arin welcomed Tsahi Levent-Levi, leading authority in the WebRTC community, for a deep dive into the technologies, opportunities, challenges, and key players shaping the 2024 WebRTC landscape. Tsahi regularly talks about real-time communications, WebRTC, and CPaaS on bloggeek.me. His commitment to knowledge sharing extends to WebRTC Weekly, WebRTC Insights, and webrtccourse.com, where he simplifies and teaches WebRTC. This episode began

Large Language Models (LLMs) are a hot Generative AI topic and everyone wants them in their WebRTC application! Use cases range from real-time in-call assistance to contact center agents, passing through post-call analysis, and even powering voice bots that are capable of answering calls without any human intervention. The newest WebRTC Tips by WebRTC.ventures video walks us through the technical components of how to integrate an LLM into a WebRTC application integration using Nebula, a

In the previous posts of our Polybot.ai translator bot (“Polly”) series, we looked at AI + WebRTC product development, brand creation and UI, and also how to successfully build prompts for interacting with the Large Language Model (LLM).  In this final post, we will take a look at the technical steps for integrating all of Polly's pieces together using Web Speech API and one of OpenAI's ChatGPT underlying models: GPT-3, in order to add voicebot

Call for Speakers for the WebRTC & Real-Time Applications Track! The 2024 RTC Conference and Expo at the Illinois Institute of Technology (IIT) will be held October 8th - 10th, on the Illinois Institute of Technology's Mies Campus in Chicago. As the conference celebrates its 20th anniversary, they will bring together thought leaders from across industry and academia to shape the future of real-time communications. The conference is co-hosted by the IEEE Chicago Section & Real Time

Prompt engineering involves organizing text so that a Generative AI Large Language Model (LLM) can interpret input and generate an expected or desired output.  Imagine a friend is making you a sandwich and you want them to prepare it just the way you like it. You say, "Hey, could you throw in some extra cheese and skip the tomatoes?” That's a lot like how prompt engineering works. You are telling a LLM that feeds a

Here's February 2024’s Team Talk, where we ask our dynamic team of WebRTC developers, designers, testers, DevOps experts, and project leads to share some of the impactful work they did in the past month. Here’s a short list of some that might interest you — at least the ones we can talk about! Assessed the best CPaaS to use to replace Twilio Video SDK based on pricing, ease of use, and a use case which

Voicebots offer efficient resolution of common customer inquiries, making them an indispensable component of today's customer service flows. In previous posts, we have seen how you enhance the capabilities of voicebots using the power of LLMs and also integrate such capabilities in a web interface using WebRTC, allowing you to empower your customer service agents with AI-powered real-time in-call and post-call assistance.  In order to optimize the performance of bot flows, it’s important to have

Creating a brand that stands out is often as crucial as the innovation itself. At WebRTC.ventures, we recently embarked on an exciting journey to develop a unique brand identity for our latest creation, Polybot.AI. “Polly” seamlessly integrates WebRTC technologies with AI, offering real-time, on the go translation through audio and speech recognition. Simply open up your browser, speak to the screen and have a GenAI-powered real-time translator speak to the representative on your behalf.  We

I was working from the WebRTC.ventures Testing & QA headquarters in Panama City, Panama during the Super Bowl this year. I went to a sports bar filled with Panamanians watching the Chiefs win a close game over the 49ers. In the US, the Super Bowl has a media dynamic different from other sporting events because the commercials (and the halftime show!) get as much or even more hype than the game itself.  Watching from Panama,