TL;DR: Vogent is an all-in-one platform for building voice agents by using intelligent building blocks, including drag-and-drop conversational flow builders, IVR detection models, spelling-optimized voices, custom phone-ready LLMs, and more. Vogent is made for developers and no-code users alike.
We’ve spent the past year building high-volume voice AI agents for a number of big-ticket customers, including the second largest prescription network in the US, the biggest flight and hotel booking sites in Europe, top-10 health insurance companies, car dealership chains, and more.
While the core voice agent cycle (STT-LLM-TTS-VAD) is a mostly solved problem at this point, the last-mile problem for making these agents performant was frustrating. We ended up building a lot of band-aids, and we decided to consolidate all of the tools that we used to build these agents into a self-serve platform for developers and non-developers alike.
Voice AI isn’t new, and neither are platforms to build agents. Our approach is to also offer higher-level building blocks that make it easier to build performant agents that can handle complex tasks. These include:
As well as other powerful abstractions.
Our other focus is providing as much to developers as possible. We expose most of our platform through GraphQL and REST APIs, and we have a JS SDK that makes voice as easy to add to your product as any other AI modality. (Mobile SDKs in beta – email j@vogent.ai for access!)