Stream Blog

Not long ago, text-to-speech (TTS) was a laughing stock. Robotic, obviously synthetic output that made customer service jokes write themselves and relegated TTS to accessibility contexts where users had no alternative. Now, you may have listened to text-to-speech today without even realizing. AI-generated podcasts, automated customer service calls, voice assistants that actually sound like assistants.

Marketplaces only work when people trust each other. Buyers trust that listings accurately represent what they’re purchasing. Sellers trust they won’t be scammed, harassed, or pushed off the platform by bad actors. And both trust that the marketplace itself is actively protecting them, not reacting after damage is already done. As marketplaces scale, maintaining that

AI won’t stay online. It won’t stay on your laptop. It won’t stay centralized. It will move to every device and to the edge of every network, into your earbuds, your car, your factory floor, and your doorbell. This opens up a remarkable number of use cases. A fitness coach who listens continuously, counts your

A2UI (Agent-to-UI) is a protocol designed by Google to standardize how AI agents communicate with user interfaces. Instead of tightly coupling agents to specific frontends, A2UI defines a clear contract for intent, state, and actions – making it easier to build interactive, agent-driven experiences that are portable, composable, and UI-agnostic. As AI systems move from

Stream has reached a major milestone in activity feed infrastructure, successfully benchmarking over 37 million operations with a 10% write and 90% read workload distribution across a dataset of 100M users, 500M activities, and 200M follow relationships. Each scenario was tested at 500, 1,000, and 1,500 requests per second to measure performance under increasing load.

Stream has reached a major milestone in real-time video infrastructure: Successfully scaling a single WebRTC-based livestream to 100,000 concurrent participants while maintaining ultra-low latency, stable frame rates, and zero packet loss. Today, Stream powers real-time chat, activity feeds, moderation, audio, and video for applications serving over one billion end users worldwide, backed by a 99.999%

Claude isn’t the model most users turn to when needing visual capabilities. Rather than optimizing primarily for object detection or scene description, Claude processes visual content through the same reasoning architecture it uses for text. This design choice has significant implications for developers: Claude excels at tasks requiring interpretation and explanation rather than pure perception.

Voice agents are getting better, but most text-to-speech pipelines still assume you’re okay with cloud APIs, large models, and unpredictable latency. If you want fast, natural-sounding speech that runs entirely on your own hardware (no GPU, no network calls), you need a different approach. In this tutorial, you’ll build a real-time AI voice agent that