Stream Blog

Everyone talks about models. New architectures, larger parameter counts, faster inference—those tend to dominate the conversation. But if you’re actually building AI systems (or evaluating vendors), you quickly realize something else matters more: The data. Not just how much of it you have, but where it comes from, how it’s processed, and how it evolves

When building voice AI applications, you have industry-leading cloud options for text-to-speech, such as Cartesia Sonic 3 and Grok TTS. For privacy and to avoid sharing your business’s data with these commercial text-to-speech (TTS) providers, your team may want to use free, open-source solutions that run locally on mobile and desktop devices. Continue reading to

It’s been a busy period since our last release, and now it’s time to share Vision Agents v0.5.0 — a step toward making production-grade multimodal AI agents easy to build and deploy. While previous versions laid the groundwork for real-time voice, video, and Vision Agents, v0.5.0 focuses on stability at scale and even more expressive

Moderation has quietly become one of the hardest problems in modern apps. As chat, feeds, and real-time video interactions expand globally, the challenge isn’t just catching bad content; it’s doing it in real time, across languages, with context, and at scale. At Stream, we’ve been investing deeply in solving that problem. This roadmap is a

Event-driven architecture is nothing new. IBM MQ shipped in 1993. JMS has been around since 1998. Kafka launched in 2011. But for most of that history, event-driven patterns were for specialized domains. Most developers never touched them. That’s changed. Real-time mobile features, such as chat, activity feeds, live collaboration, or presence indicators, have pushed event-driven

TL;DR The Problem For hourly workers, communication is rarely simple. Messages are often scattered across third-party applications like WhatsApp groups, Facebook Messenger threads, texts, or generic workplace tools that were never designed for shift-based teams. The Solution Deputy set out to solve that problem by bringing real-time messaging directly into its workforce management platform. The

Let’s build a restaurant reservation system to speak with a voice agent via a real-time phone call. The service will have three main features: Agent Outbound Call: The agent can act as both a customer helper and a restaurant assistant. For example, it can be configured as an AI restaurant employee that calls customers back

Stream and CometChat are two of the most-evaluated platforms for teams building real-time communication into their products. Both offer APIs, SDKs, and UI components for messaging, audio, and video. But they are built around different philosophies:  Stream is engineered for deep customization and extreme scale, CometChat is designed to get you to production fast with