Introduction & Concepts

Welcome to the VoiceBooker section! Here, you can explore your voicebots capabilities as well as various use-cases. This documentation is tutorial driven showcasing the different features and functionality of the VoiceBooker platform.

LLMs

VoiceBooker voice bots use LLMs as underlying technology.

What is a LLM? A large language model (LLM) is a type of artificial intelligence (AI) program that can recognize and generate text, among other tasks. LLMs are trained on huge sets of data — hence the name "large." LLMs are built on machine learning: specifically, a type of neural network called a transformer model.

Since LLMs can understand natural language, they are perfect fit for voice bots. First, they understand what the client/caller said, and second, voice bot developers/creators can program and instruct the LLM how to react and what to do using natural language. Hence, voice bots can be created with very little code usage.

Basic Execution Model

The voice bot works similar as when using ChatGPT:

Using prompts, the voicebot can be instructed what to do, such as querying the caller/client for some information, and the voicebot can also answer questions based on some predefined information and knowledge base.

Let's get started: VoiceBooker Voice bots are generally composed of a set of stages.