Cartesia is an AI company focused on real-time multimodal intelligence and voice AI. Its work centres on State Space Models (SSMs) and foundation models, applying these to products that process and generate human speech. The company combines deep expertise in model innovation and systems engineering with a design-minded approach to building developer tools.
The company's two main products are Sonic and Ink. Sonic is a text-to-speech model designed to produce human-like vocal output, including emotive qualities such as laughter. Ink is a speech-to-text model engineered specifically for real-time voice AI applications.
The founding team met as PhDs at Stanford's AI Lab. Cartesia operates in the voice AI vertical and is focused on building tools that help developers create voice applications that connect with people in real time.
