Twilio has announced that ConversationRelay, its tool for integrating Voice AI into applications, is now generally available. Originally introduced in beta at SIGNAL London in late 2024, ConversationRelay is designed to make it dramatically easier for organizations to integrate natural, human-like voice capabilities into their GenAI stacks—without the headaches of fragmented infrastructure or multiple vendors. This general availability release brings enterprise-grade Voice AI and Conversational AI capabilities to production environments using Twilio. With HIPAA compliance,

WebRTC gave us real-time media for the Web — but it came with complexity, workarounds and tight coupling. In this episode, we explore Media over QUIC (MOQ), a protocol designed to deliver real-time media more simply, more flexibly and without the legacy overhead. We’ll dive into how MOQ works, how it compares to WebRTC under the hood and why it might be the future of streaming — especially for developers building collaborative, low-latency or async

While most people know Zoom as a video conferencing app, the Zoom Video SDK opens up the powerful infrastructure behind it to developers who want to embed custom video experiences directly into their own web applications. Behind the scenes, Video SDK v2 now leverages WebRTC, the industry-standard protocol for real-time communication in the browser, ensuring lower latency and broad cross-platform compatibility. If you're looking to create a live video experience—such as internal collaboration tools, telehealth

Zoom's WebRTC-powered Video SDK for web is a valuable tool for businesses and developers looking to deliver modern, browser-based real-time communication experiences. By combining the accessibility of WebRTC with Zoom's enterprise-grade infrastructure, the SDK enables rapid integration, robust performance, and a wide array of features for custom video solutions. For organizations already using Zoom, it offers the added advantage of leveraging existing adoption to seamlessly integrate familiar video capabilities into custom workflows. In this post,

Debugging video issues in WebRTC applications can be a challenging task. With numerous moving parts under the hood, pinpointing the exact cause of problems can feel like searching for a needle in a haystack. One of the most effective strategies is to reproduce the issue consistently in a controlled environment. In this post, we explore a powerful technique first featured on the WebrtcH4cKS blog: isolating and reproducing video issues using the video_replay tool. By capturing

In a previous post, Building an Interactive Emoji Expression Game with LiveKit Video Conferencing, we set the basis on how to create a fun and engaging web-based game using LiveKit that we call FaceOff. Today, we’re adding the game logic by integrating facial detection technology into it.  By leveraging FaceAPI, a lightweight AI-powered facial expression analysis library, we’ll detect emotions in real-time from video streams and match them to corresponding emojis—adding an exciting layer of

Traditional static web interfaces—while reliable for decades—are increasingly inadequate for the dynamic, adaptive nature of AI-powered applications. In a previous post, Rethinking UX: Emerging Interfaces for the AI Age, we explored key principles that define modern AI interface design, including: Visual Feedback Latency Management Adaptability Trust Through Transparency Voice and Multimodal Interfaces Keyboard Shortcuts Balancing Quality and Speed Human-in-the-Loop Design In this case study, we’ll show how these principles came to life in the redesign

Quality is always a priority in WebRTC communications, and becomes even more critical in media applications that demand high-fidelity audio and video recording. On April 23, 2025, we welcomed Michalis Daniilakis, Co-founder and CTO of Chord.fm, a browser-based podcasting platform that leverages WebRTC to deliver studio-quality production. Achieving that level of performance came with valuable technical lessons. Michalis walked us through the architectural decisions that shaped their application. We dove into key topics like local and

Our WebRTC.ventures Developer Advocate, Hector Zelaya, was recently accepted as an AWS Community Builder! This program offers technical resources, education, and networking opportunities to AWS enthusiasts and emerging thought leaders who are passionate about sharing knowledge and connecting with the technical community.  In this spirit of knowledge sharing, Hector has published his first post with the AWS Community Builders DEV organization, where community members share content with fellow AWS builders. In his post, Hector explores

As AI continues to evolve beyond backend algorithms into user-facing applications, we're witnessing a fundamental shift in how interfaces need to be designed. Traditional static web interfaces that have served us well for decades are increasingly insufficient for the dynamic, adaptive nature of AI-powered applications. Recently, I was tasked with redesigning a demo application that integrates WebRTC technology with AI Voice/Video Bots for live commerce called LiveCart. After nearly a decade of designing WebRTC interfaces,

During a recent onsite gathering of our team at the WebRTC.ventures Panama QA office, we did a deep dive into Prompt Engineering with John Berryman, an early engineer at GitHub Copilot and author of Prompt Engineering for LLMs: The Art and Science of Building Large Language Model-Based Applications.  While we mainly focused on text-based scenarios (in LLMs, text has been king so far), we also explored specific considerations for voice and audio/video-driven applications leveraging WebRTC.

Video conferencing can be more than just communication—it can be an interactive gaming experience! We built a web application that connects players via LiveKit open source video conferencing and challenges them to an emoji-matching game using the FaceAPI for real-time facial expression analysis. We call it “FaceOff”. In this first post of the series, we’ll cover the basics of using LiveKit and how we leveraged it to build this web-based video conference game. Our focus

Voice-to-text technology has advanced significantly, enabling real-time transcription for various applications. From enhancing workplace productivity to supporting individuals with disabilities, speech-to-text solutions have become integral across numerous sectors. Professionals in fields like journalism, legal services, education, and healthcare, to name a few, are leveraging real-time transcription to capture critical information accurately and efficiently.  In this post, we'll explore how to build a simple Android app that transcribes conversations locally using SpeechRecognizer from android.speech. We'll also

Interactive, personalized video commerce is shaping the future of online retail. At WebRTC.ventures, we’ve harnessed the power of Agora’s real-time communication platform, OpenAI's Realtime API, and Simli's AI-driven avatars to create LiveCart—a next-generation live selling platform that turns watchers into buyers. Online retailers face several hurdles when trying to replicate the in-store shopping experience: Lack of personal interaction leads to lower engagement. Product questions often go unanswered, causing cart abandonment. Sellers struggle to scale personalized

On March 19, 2025, the milestone 100th episode of WebRTC Live, we showcased an ongoing WebRTC.ventures project that highlights the powerful potential of WebRTC and AI. AVA Intellect is at the forefront of developing AI-powered virtual teammates that seamlessly integrate into Microsoft Teams and other video conferencing platforms—collaborating like real colleagues. Is this the future of business? And how is it being accomplished? Learn more about this project in our WebRTC.ventures Story of Success: AI Voice Agents

The integration of conversational AI and agentic systems into WebRTC applications has evolved from a novel concept to an essential component in creating truly intelligent communication systems. The convergence of real-time communication, large language models (LLMs), and agentic AI systems has unlocked new opportunities for voice-based interfaces that don't just facilitate communication but can take meaningful action. We're no longer simply navigating a set of fixed workflows; we're building systems that can understand speech, reason

Imagine having a conversation with a sophisticated AI assistant or agent without your words ever leaving your machine. No data being shipped to third-party servers. No LLM API costs. No added latency waiting for distant data centers to process your requests.  If you're concerned about confidential business data, work in a regulated industry, or simply want more control over your AI tools, on-premise, local processing of Large Language Models (LLMs) ensures that data remains on

As the CTO of WebRTC.ventures, I recently attended ITEXPO 2025 in South Florida, an annual gathering of communications and technology professionals. The event brings together telecom and IT executives from enterprise and SMBs, small business owners, MSP and channel C-levels and business owners, service provider/carrier engineers, network executives, and industry suppliers and solutions providers. The conference typically covers a broad range of topics, including scaling infrastructure, network security, communication protocols, customer experience strategies, and emerging

The webrtc-internals tab is a powerful debugging tool built into Chrome and other Chromium-based browsers. It provides real-time insights into active WebRTC sessions, offering developers a detailed view of connection behavior and media transport. In this post, we’ll take a quick tour of how webrtc-internals enables real-time insights into active WebRTC sessions, helping developers analyze and debug connection behavior, media transport, and performance metrics. We’ll also explain why a different approach may be required for

Real-time video calls have become the backbone of how we work, learn, and connect. And when users connect, they expect seamless, high-quality communication. Yet many factors can affect call quality - from internet connectivity to device settings to network configurations. While these issues often originate outside the application itself, they significantly impact the user experience. Pre-call testing helps identify potential problems before a call begins, enabling proactive solutions and clearer expectations.  In this post, we'll