Text To Speech (TTS) generates synthesized speech from textual representations of language. The technology allows dialogue systems to “talk back” in audible speech, which can make the user experience feel more realistic, especially when used alongside Automatic Speech Recognition.

[table sort=”asc”]
Name[attr style=”width: 150px;”], Location, Cost, License, Overview

Festival Speech Synthesis System, Local, Free, X11, Written in C++ and uses the Edinburgh Speech Tools Library for low level architecture

Merlin Toolkit, Local, Free, Apache Version 2.0, Written in Python based on the Theano numerical computation library; used for building deep neural network models for statistical parametric speech synthesis

Chrome TTS, Cloud, Free, Proprietary, Chrome provides native support for speech on Windows (using SAPI 5) Mac OS X and Chrome OS

IBM TTS, Cloud, Paid, Proprietary, Understands text and natural language to generate synthesized audio output complete with appropriate cadence and intonation

Android TTS, Local, Free, Proprietary, A class that can be instantiated by an Android application

ResponsiveVoice.JS, Cloud, Paid, Proprietary, A HTML5-based Text-To-Speech Javascript library designed to add voice features to web sites and apps with an unending free trial

NeoSpeech, Cloud, Paid, Proprietary, A cloud software as a service TTS online tool

Voice RSS, Cloud, Paid, Proprietary, Voice RSS provides 350 free cloud based TTS requests per day

Amazon Polly, Cloud, Paid, Proprietary, Amazon Polly API allows 5 million free characters of TSS per month

iSpeech, Cloud, Paid, Proprietary, Easy integration with many languages

[/table]