Cartesia, an AWS Partner specializing in real-time voice AI, uses purpose-built State Space Models (SSMs) and AWS infrastructure to deliver sub-100ms text-to-speech and speech-to-text at global scale, according to an AWS blog post. The post states that conversational AI is transforming how humans interact with technology, with voice-first interfaces becoming the default mode of interaction for millions of users worldwide, and that delivering a natural voice experience remains one of the hardest challenges in AI infrastructure because excess latency can break conversational flow and erode trust. It notes demand for real-time voice AI is growing across contact centers, telehealth, gaming and virtual worlds, accessibility, and inbound and outbound sales. Traditional transformer-based text-to-speech models struggle with streaming latency because they process entire sequences before producing output, creating a tension in which higher quality often means higher latency, while SSMs treat a sequence as a system that evolves continuously over time, processing it step by step and carrying a compact internal state forward, an efficiency the post says makes SSMs well suited to real-time, streaming data like live speech.