PRODUCTS
NeoSpeech natural-sounding text-to-speech (TTS) products
give you the control and confidence to deploy high quality solutions.

VoiceText™
TTS Engine SDK

Text-To-Speech Engine is provided with versatile SDK for developers. VoiceText™ Text-To-Speech Engine is used for building custom applications.

VoiceText™
TTS Server SDK

Text-To-Speech Engine is provided with Server API and SDK for multi-thread dynamic TTS conversions.

VoiceText™
Embedded SDK

SDK for iOS and Android platforms. Specific embedded operating systems i.e. embedded Linux SDKs are ported on customer requests.

VoiceText™
Editor and SAPI

Powerful PC software that generates audio files in WAV format.
Any software or application that is SAPI (Microsoft API) compliant can utilize NeoSpeech SAPI voices. NeoSpeech SAPI voices can also function as multi-thread server.

VoiceText™ Text-To-Speech Engine SDK

Vocalize Your Thoughts With NeoSpeech

Whether you’re developing a new e-learning software or putting the finishing touches on the perfect announcement system, NeoSpeech can help you let your ideas be heard—loud and clear. VoiceText Engine SDK allows you to build and integrate your applications with our synthesized voices in perfect harmony. E-learning software, announcement systems, audio books, and any other devices or applications—NeoSpeech’s voices are primed and ready to meet your professional needs.

FEATURES

  • Exceptional Performance From Life-like, Natural Sounding Voices

    “Do-mo A-ri-ga-to Mr. Ro-bo-to.”

    Thank you, Mr. Robot, but gone are the days where your voice was the standard. Speech Technology has since then evolved rapidly and synthesized voices are no exception. NeoSpeech’s voices are realistic, clear, and life-like, refined to express your content intelligently. Optimized for your specific platform, they’re designed to deliver the highest quality sound and exceptional performance every time. Communication has never been easier or more pleasant to the ears.

  • Multilingual Voice Family

    Make your application appeal to a global audience. NeoSpeech has you covered with 30+ voices in 8 languages: English (US and UK), Spanish, Canadian French, Korean, Japanese, Mandarin, Cantonese, and Taiwanese. And if you can’t find one that you like, don’t worry—we have more coming.

  • Elevate Speech Fluidity and Make Your Speech More Human

    Edit to your heart’s content. Our simple user interface makes it a cinch to produce and tweak your files. Adjust the flow and pace of the content to go hand-in-hand with your application. Speed up or slow down voices and incorporate pauses for effect in audio books or training courses. You have complete control over the speed, pitch, volume, and pause. Combined with our easy-to-use VoiceText Markup Language (VTML), you can quickly insert and switch between the various prosody controls to achieve your desired results.

  • Personalize Your Language With a Customizable Dictionary

    NeoSpeech’s voices come equipped with the CMU (Carnegie Mellon University) Pronouncing Dictionary filled with over a million pronunciations, but you don’t have to stop there. Capture regional dialects and enrich the lexicon with new words. Fine tune pronunciations and clarify abbreviations. Iron out the minute details in people’s names and street intersections. Expand the language to suit your industry. Whether you’re adding a whole list of medical terms or just one slang phrase—you can do it all using one or more of the phonetic alphabets available. Phonetic alphabets include:

    IPA

    X-Sampa

    TeleAtlas Sampa

    Navteq Sampa

    X-Sapi

    X-CMU

    X-PENTAX

    X-PINYIN

    X-WORLDBET

  • Text Normalization Accuracy for Special Characters Differentiation

    No need to painstakingly edit every date and time—convert your content to speech quicker, with less time needed for revision. We take all that stuff into consideration along with acronyms and abbreviations to make your life a little easier. Sentences are read off eloquently—no number sequences or unnatural pronunciations—just the way you like it.

  • Adaptable Footprint

    16 MBs, 400 MBs, up to 700 MBs—you decide what works best for your desktop application and we will provide it. Whether you need the highest quality voice for your IVR system or one just high enough for your website content—NeoSpeech has you covered.

  • Multiple Audio Formats and Sampling Rates

    Listen to your audio in 2 different sampling rates and determine which works best for your application. For IVR systems and emergency notifications, 8 kHz is the best bet. While 16 kHz works for all other applications, additional sampling rates are available for certain voices for customers using a Windows operating system. Afterwards, export your sound files in one of the 8 formats:

    16-bit linear PCM

    8-bit A-law PCM

    8-bit Mu-law PCM

    4-bit Dialogic ADPCM

    16-bit linear PCM Wave

    8-bit unsigned linear PCM Wave

    8-bit A-law PCM Wave

    8-bit Mu-law PCM Wave

  • Operating System and API Compatibility

    Have it your way—Windows or Linux. Pick your operating system of choice and create your application using C-based APIs.

SYSTEM REQUIREMENTS

Operating System

Windows 98 and highter.

Linux RHEL 5 or higher, Fedora and CentOS

CPU

Pentium III 500 MHz

RAM

128 MB (256 MB Recommended)

Database space

64 MB ~ 900 MB per voice.

APPLICATIONS

Ideal Solutions for Every Customer

  • Accessibility

    Make communication easier for people with speech disorders, vision impairments, and dyslexia. Build voice assistive applications and improve their way of life.

  • Announcement Systems

    Whether you’re trying to find an exhibit at a museum or looking to grab a bite at the mall, get easy access using an interactive audio kiosk.

  • Audio Publishing

    Make your content accessible to everybody. Let drivers listen to your audiobook on their way home. Have joggers catch up on the news while stretching and prep high school seniors on the beauty of your university while filling out their college applications.

  • Education

    Take complex ideas and simplify them—speech enable your content for e-learning, training simulations, company orientations, etc.

  • Electronic Gaming

    Immerse gamers in audio-driven storytelling. Assist players stuck in an area with voice prompts that activates over a hotspot. Generate narration for graphic-heavy scenes and more.

  • Transportation

    Equip bus and train stations with voice announcements to accurately inform passengers about estimated time of arrival, delayed departures, upcoming stops, and more.

VoiceText™ Text-To-Speech Server SDK

Optimize Your Server-based Application With NeoSpeech

Take your application to the next level—manage multi-threaded and multiple voices text-to-speech requests for IVR systems, emergency alert systems, mobile devices, and more with VoiceText Server SDK. Integrate NeoSpeech’s voices with your client-server architecture and run your application efficiently.

Application

 

Voice Text Engine

Kate, Paul, Hugh, and More!

SDK

VoiceText™ Access Protocol VTAP (API) using TCP/IP

FEATURES

  • Web Admin Control Panel

    Access the control panel wherever you are. Sign in to manage all the settings. Adjust the pitch, volume, speed, and pause. Enable and disable voice engines. Set maximum channels and more on the web interface.

  • Monitor Thread Usage in Real Time.

    No need to wait—track simultaneous text-to-speech synthesis occurring in real-time and over time on a live graph.

  • Incremental Reporting

    Break down your customers’ usage by their speech requests, text’s length, response time from the server and more—and see how it compares to the usage from the last hour, last day, last week, and three months ago. VoiceText Server SDK automatically generates a log file every 15 minutes, so you can figure out what caused a traffic spike and when it occurred.

  • Personalize Your Language With a Customizable Dictionary

    NeoSpeech’s voices come equipped with the CMU (Carnegie Mellon University) Pronouncing Dictionary filled with over a million pronunciations, but you don’t have to stop there. Capture regional dialects and enrich the lexicon with new words using the industry-standard SSML (Speech Synthesis Markup Language). Fine tune pronunciations and clarify abbreviations. Iron out the minute details in people’s names and street’s intersections. Expand the language to suit your industry. Whether you’re adding a whole list of medical terms or just one slang phrase—you can do it all using one or more of the phonetic alphabets available. Phonetic alphabets include:

    IPA

    X-Sampa

    TeleAtlas Sampa

    Navteq Sampa

    X-Sapi

    X-CMU

    X-PENTAX

    X-PINYIN

    X-WORLDBET

  • Multiple Audio Formats and Sampling Rates

    Listen to your audio in 2 different sampling rates and determine which works best for your application. For IVR systems and emergency notifications, 8 kHz is the best bet. While 16 kHz works for all other applications, additional sampling rates are available for certain voices for customers using a Windows operating system. Afterwards, export your sound files in one of the 10 formats:

    16-bit linear PCM

    8-bit A-law PCM

    8-bit Mu-law PCM

    4-bit Dialogic ADPCM

    16-bit linear PCM Wave

    8-bit unsigned linear PCM Wave

    8-bit A-law PCM Wave

    8-bit Mu-law PCM Wave

    ASF (Windows only)

    Ogg Vorbis

  • Operating System and API Compatibility

    Choose what works best for you—Windows or Linux. Integrating VoiceText Server SDK within your application is easy and straightforward thanks to the familiar API. Our server is designed to support all major APIs, including:

    C-based APIs

    Java

    .NET

    MRCP v1

    MRCP v2

    UniMRCP

SYSTEM REQUIREMENTS

Operating System

Windows Server 2000 and highter
Windows XP
Windows 7 and higher.
Linux RHEL 5 or higher, Fedora and CentOS

CPU

Pentium IV 1.7 MHz

RAM

1 GB (*depends on the number of channels)

Database space

64 MB ~ 900 MB per voice.

APPLICATIONS

Ideal Solutions for Every Customer

  • Announcement Systems

    Forget about background noise and lost messages—send public announcements and emergency alerts reliably.

  • Education

    Learn new languages—anytime, anywhere with an internet connection. Improve a student’s reading and vocabulary through audio-driven educational games. And prepare for the impossible—in specialized training simulations.

  • Health Care

    Add audio readback to increase accuracy and efficiency in electronic prescribing. Eliminate medication errors and streamline prescription processing at the pharmacy.

  • Mobile Devices

    Transcribe your received text messages into audio, allowing you to be hands-free to do other tasks like: driving, exercising, and cooking.

  • Telecommunications

    Manage your sophisticated IVR systems effectively. Enable multiple voices running on VoiceText Server SDK to handle call spikes and deliver the best quality to your customers.

  • Transportation

    Equip train stations and airports with real time voice announcements to accurately inform passengers of flight changes, departures, arrivals, and more.

VoiceText™ Text-To-Speech Embedded SDK

Embed Your Application With NeoSpeech

NeoSpeech is a one stop shop for your embedded application. Whether you’re creating an educational mobile app or adding voice feedback for blood glucose meters, NeoSpeech has a simple solution for your embedded needs.

FEATURES

  • Exceptional Performance From Life-like, Natural Sounding Voices

    Communication has never been easier or more pleasant to your ears. NeoSpeech’s voices are realistic, clear, and life-like, refined to express your content intelligently. Optimized for your specific embedded platform, they’re designed to deliver the highest quality sound and exceptional performance every time.

  • Multilingual Voice Family

    Make your application appeal to a global audience. NeoSpeech has you covered with 30+ voices in 8 languages: English (US and UK), Spanish, Canadian French, Korean, Japanese, Mandarin, Cantonese, and Taiwanese. And if you can’t find one that you like, don’t worry—we have more coming.

  • Elevate Speech Fluidity and Make Your Speech More Human

    Edit to your heart’s content. Our simple user interface makes it a cinch to produce and tweak your files. Adjust the flow and pace of the content to go hand-in-hand with your application. Speed up or slow down voices and incorporate pauses for effect in audio books or training courses. You have complete control over the speed, pitch, volume, and pause. Combined with our easy-to-use VoiceText Markup Language (VTML), you can quickly insert and switch between the various prosody controls to achieve your desired results.

  • Personalize Your Language With a Customizable Dictionary

    NeoSpeech’s voices come equipped with the CMU (Carnegie Mellon University) Pronouncing Dictionary filled with over a million pronunciations, but you don’t have to stop there. Capture regional dialects and enrich the lexicon with new words. Fine tune pronunciations and clarify abbreviations. Iron out the minute details in people’s names and street intersections. Expand the language to suit your industry. Whether you’re adding a whole list of medical terms or just one slang phrase—you can do it all using one or more of the phonetic alphabets available. Phonetic alphabets include:

    IPA

    X-Sampa

    TeleAtlas Sampa

    Navteq Sampa

    X-Sapi

    X-CMU

    X-PENTAX

    X-PINYIN

    X-WORLDBET

  • Multiple Audio Formats and Sampling Rates

    Listen to your audio in 2 different sampling rates and determine which works best for your application. For SCADA systems and emergency notifications, 8 kHz is the best bet. While 16 kHz works for all other applications. Afterwards, export your sound files in one of the supported formats based on your platform.

    16-bit linear PCM

    8-bit A-law PCM

    8-bit Mu-law PCM

    4-bit Dialogic ADPCM

    16-bit linear PCM Wave

    8-bit unsigned linear PCM Wave

    8-bit A-law PCM Wave

    8-bit Mu-law PCM Wave

    8-bit Mu-law PCM SUN AU
    (only support iOS and Android.)

  • Support for Your Preferred Platform

    VoiceText Embedded SDK supports a range of mobile operating systems that are designed specifically to help app developers quickly and seamlessly integrate NeoSpeech’s voices into their applications. They include:

    iOS

    Android

    Embedded Linux

    QNX

    Windows Mobile

    And upon request, other specifications such as database footprints and CPU type can be provided to ensure optimal compatibility by contacting NeoSpeech.

SYSTEM REQUIREMENTS

Operating System

iOS
Android
Embedded Linux
WinCE 3.0 or higher
Windows Mobile 5.0 or higher
*Other OS can be ported upon request.

CPU

ARM 170 MHz X-Scale, SH3, SH4, x86, MIPS (custom)

RAM

6-16 MB (smaller sizes may be available for certain voices)

Database space

16 ~ 900 MB

APPLICATIONS

Ideal Solutions for Every Customer

  • Accessibility

    Give users a way to communicate and take in information easily. Integrate NeoSpeech’s voices into AAC devices, mobile applications, DAISY digital talking books, and more.

  • Announcement Systems

    Prevent disasters—enhance human-machine interface functionality in SCADA systems. Always know what is happening when an alarm activates. Trigger voice messages to notify SCADA operators about the situation.

  • Education

    Put your mind to the test. Sharpen memory, increase focus, and keep your mind in tip-top shape with audio-accompanied brain training apps.

  • Health Care

    Take a step towards a healthier lifestyle with voice feedback from heart rate monitors, blood glucose meters, and blood pressure monitors.

  • Mobile Devices

    Give your eyes a break and listen instead. Keep updated with current events, learn new languages, and lose yourself in a good audiobook—all in the palm of your hand.

  • Transportation

    Never get lost again—drive like a local with clear, natural-sounding directions. Navigate confidently to reach your destination with time to spare.

VoiceText™ Editor and SAPI

Articulate Your Ideas With NeoSpeech

Designed to simplify cost and time—NeoSpeech’s voices are primed and ready to meet your professional needs. Whether you’re creating hundreds of voice prompts for your IVR system or just one for your audiobook, NeoSpeech gives you the flexibility to create content—anytime, any day.

VoiceText™ Editor

  • Exceptional Performance From Life-like, Natural Sounding Voices

    Make the voice a priority—why settle for dull and monotonous when NeoSpeech’s voices are realistic, clear and life-like, refined to express your content intelligently. Improve your business by giving your audience the best listening experience. They’re designed to deliver the highest quality sound and exceptional performance every time.

  • Multilingual Voice Family

    Make your application appeal to a global audience. NeoSpeech has you covered with 30+ voices in 8 languages: English (US and UK), Spanish, Canadian French, Korean, Japanese, Mandarin, Cantonese, and Taiwanese. And if you can’t find one that you like, don’t worry—we have more coming.

  • Elevate Speech Fluidity and Make Your Speech More Human

    Edit to your heart’s content. Our simple user interface makes it a cinch to produce and tweak your files. Adjust the flow and pace of the content to go hand-in-hand with your application. Speed up or slow down voices and incorporate pauses for effect in audio books or brain training apps. You have complete control over the speed, pitch, volume, and pause. Combined with our easy-to-use VoiceText Markup Language (VTML), you can quickly insert and switch between the various prosody controls to achieve your desired results.

  • Personalize Your Language With a Customizable Dictionary

    NeoSpeech’s voices come equipped with the CMU (Carnegie Mellon University) Pronouncing Dictionary filled with over a million pronunciations, but you don’t have to stop there. Capture regional dialects and enrich the lexicon with new words. Fine tune pronunciations and clarify abbreviations. Iron out the minute details in people’s names and street’s intersections. Expand the language to suit your industry—medical, education, transportation and more.

APPLICATIONS

Text Editor

  • Audio Publishing

    Remove barriers to content—let your content be accessible to the ears as much as it is to the eyes. Add audio to news articles, blogs, websites and audiobooks.

  • Education

    Put together dictation lessons for language classes and voice files for e-learning courses—quickly and efficiently.

  • Telecommunications

    Reduce costs by routing calls effectively. Utilize NeoSpeech’s voices to customize natural-sounding voice prompts suited for your business.

VoiceText™ SAPI

  • Add Variety to Your Voice Selection With NeoSpeech SAPI

    Have an application that uses SAPI? No problem—we have you covered. So whether you’re creating training modules with rich media content on Adobe Captivate or adding new voices to screen readers, NeoSpeech SAPI voices are designed in compliance with Microsoft SAPI specifications.

  • Multilingual Voice Family

    Make your application appeal to a global audience. NeoSpeech has you covered with 15+ voices in 6 languages: English (US and UK), Spanish, Canadian French, Korean, Japanese, and Mandarin. And if you can’t find one that you like, don’t worry—we have more coming.

  • Markup Language Compatible

    NeoSpeech SAPI is compatible with SAPI XML TTS as well as our easy-to-use VoiceText Markup Language (VTML) to adjust the volume, speed, pitch and pause of your content.

  • Versatile to Adapt to Your Business

    Use NeoSpeech SAPI voices in a variety of SAPI programs including, but not limited to:

    Screen readers

    E-learning

    Screen casting

    Desktop publishing

    IVR Server

APPLICATIONS

SAPI

  • Accessibility

    Make content accessible—provide AAC users with more options for their screen readers and other AAC-specific software.

  • Audio Publishing

    Author confidently for your learners. Create precise training modules with slides filled with rich media content. Enable hover activation on certain slides and allow users to access audio clips when the graphic is triggered.

  • Education

    Maximize focus and attention—add audio to example scenarios, media content, and quiz questions.

  • Telecommunications

    Manage sophisticated IVR systems effectively. Enable multiple voices running on VoiceText SAPI to handle call spikes and deliver the best quality to your customers.

GET A FREE TRIAL