Estuary: A Framework For Building Multimodal Low-Latency Real-Time Socially Interactive Agents

TL;DR

Estuary is a versatile, multimodal framework designed to facilitate the development of low-latency, real-time socially interactive agents, addressing the lack of standardized tools in this emerging AI field.

Contribution

It introduces a modular, cloud-compatible framework that unifies multimodal components for real-time social agents, enhancing reproducibility and configurability.

Findings

Supports multimodal inputs: text, audio, video (future)

Enables low-latency, real-time interactions

Facilitates reproducible social agent research

Abstract

The rise in capability and ubiquity of generative artificial intelligence (AI) technologies has enabled its application to the field of Socially Interactive Agents (SIAs). Despite rising interest in modern AI-powered components used for real-time SIA research, substantial friction remains due to the absence of a standardized and universal SIA framework. To target this absence, we developed Estuary: a multimodal (text, audio, and soon video) framework which facilitates the development of low-latency, real-time SIAs. Estuary seeks to reduce repeat work between studies and to provide a flexible platform that can be run entirely off-cloud to maximize configurability, controllability, reproducibility of studies, and speed of agent response times. We are able to do this by constructing a robust multimodal framework which incorporates current and future components seamlessly into a modular and interoperable architecture.