VoiceTextTM Text-To-Speech (TTS) Engine

VT Engine/Embedded

Overview

VoiceText™ Text-To-Speech Engine is the core software component that generates synthesized speech from a given input text. Generally, VoiceText™ Text-To-Speech Engine is used for building custom stand-alone applications such as desktop applications, navigation systems, etc. However, it can also be used simply to output speech from an input text using the provided desktop TTS program.

Features

Natural Sound and Clear Pronunciation

VoiceText™ Text-To-Speech Engine provides very natural and highly intelligible output.

Variable Footprints

With variable footprints ranging from 16 to over 600 megabytes, VoiceText™ is configurable for use in a wide range of desktop applications.

Multiple Languages, Multiple Voices

VoiceText™ is available as US English TTS, Latin American Spanish TTS, Korean TTS, Japanese TTS and Mandarin Chinese TTS. A collection of eleven native voices is available across these languages.

Large Extensible Dictionary

Hundreds of thousands of pronunciations are included in the default dictionary of each of the supported languages. VoiceText™ also supports customization of the dictionary so that developers can adjust pronunciations of symbols, abbreviations, and new terms.

Expressive Control

Pitch, speed, volume, and pauses can be customized, both dynamically and by global setting. VoiceText Markup Language (VTML) is provided for inline customization.

Pre-Processing of Input Text

VoiceText™ automatically handles special input such as dates, times, abbreviations found in addresses, and sentences with mixed languages.

Flexible Data Output Formats

VoiceText™ Text-To-Speech Engine currently supports the following formats in 8KHz, 11KHz, and 16KHz sampling rates:

16bit linear PCM
8bit A-law PCM
8bit Mu-law PCM
4bit Dialogic ADPCM
16bit linear PCM Wave
8bit unsigned linear PCM Wave
8bit A-law PCM Wave
8bit Mu-law PCM Wave

Support of APIs

VoiceText™ supports SAPI 5.1 and C-based Application Programming Interfaces (APIs).

System Requirements

Standard Embedded
Operating System

Windows 98 or higher (works under Vista  with admin privilege).

Linux  RHEL 5 or higher (known to work under other RedHat-base distributions, such as  Fedora).

Windows CE 3.0 or higher.

PocketPC 2002 or higher.

iPhone

Linux  (custom)
CPU Pentium III 500 MHz

ARM 170 MHz

X-Scale, SH3, SH4, x86, MIPS (custom)

RAM 128 MB (256 MB Recommended) 6-16 MB
Database space 64-900 MB 16-128 MB

Experience NeoSpeech natural-sounding text-to-speech (TTS) software. NeoSpeech offers superior text-to-speech applications with natural-sounding voice synthesis software. Our TTS languages include: Japanese TTS, Mandarin Chinese TTS, Korean TTS, Latin American Spanish TTS, and of course English. Robotic voices are now history.