Introduction

AmiVoice API is a speech recognition API. It takes audio as input, identifies any human speech within that audio, and converts that speech into text. When you send audio to AmiVoice API, it returns the spoken content as text. This allows you to create speech-enabled applications such as transcribing meetings or voice dialogue systems.

This document explains how to create client programs for AmiVoice API and provides the necessary information for developing various speech recognition applications.