An SDK Designed for Developers and Integrators
Wizzard Speech is pleased to offer the most current version of AT&T Natural Voices Text to Speech (TTS) SDKs for Windows or Linux. AT&T Natural Voices is an award winning text to speech technology developed by AT&T Laboratories, and believed by many to be the most natural sounding TTS available.
These SDKs are designed for dynamic text to voice conversion in single and multi-user environments, and are perfect for high volume desktop applications, ATMs, telephony, transportation and web based apps. They can quickly add tremendous interactive and humanistic value and automation to a wide variety of applications and projects.
This SDK is perfect for desktop and server applications since most implementations are made on the same computer. However, if your deployment requires client/server architecture on “separate” computers, please contact our Sales department for an “extendable” version of this SDK.
- Designed for developers and integrators to add voice to their projects
- Implemented with a software developer kit (SDK) and distributable runtime software available in (8) voices in US English and (2) voices in Spanish
- Dynamically converts text into voice for a wide variety of applications and environments
- features a flexible "engine + voice font" architecture
- Supports customization of pronunciations, acronyms, abbreviations, speaking rate
- highly scalable technology for large volume projects
- supports dynamic multiuser creation of wavefiles for an extensive range of projects (wavefile usage requires additional licensing)
- proven technology from years of research by voice pioneer AT&T
|
Supported Languages*
Voice Fonts available in
8 &16 KHZ
- US English (Mike, Crystal, Claire, Julia, Lauren, Mel, Ray, Rich)
- Spanish (Alberto, Rosa)
*SDK includes a trial version of the TTS runtime engine and up to 2 voices for 1 language |
|
Voice Samples
|
Typical Text-to-Speech Projects
Typical projects that you might voice enable using our technologies include websites, broadcasting sites, e-learning , transportation and informational, integrated Voice Response (IVR) Systems, simulators and online/offline games, ATMs, Kiosks, eBooks, games, alert systems, assistive applications for the impaired, server based iphone applications, and more... If you have a project that is not listed above and are wondering if our products are a good fit for you, contact us.
Procurement/Licensing
- Obtain a Software Developers Kit (SDK)
- May be purchased on the website with a 90 day evaluation engine* and downloaded (requires internet connection)
- Provides a software environment for internal development and testing
- Purchase Usage licenses (requires agreement)
- Any type of usage/deployment/distribution of audio files or TTS runtime software requires licensing
- A broad range of licensing models are available for internal use or external distribution
- Minimum order levels and Volume pricing apply
- A permanent* TTS engine is provided at time of purchase of Usage/Distribution licenses
To request information and prices click Inquire or call Sales at 954-678-4155
SDK: $250(package includes)
- Libraries and documentation in US English for building Windows or Linux applications
- SDK includes 90 day trial runtime engine (requires internet connection) for development and testing only, and your choice of one language (additional voice fonts are available for $50 each) A permanent runtime engine is provided when usage licensing is purchased
- Compatible with SAPI 5.0 and newer - Windows only
- Supports custom user dictionaries and SSML compatible control tags
- API documentation
- C++ Libraries
- Visual Basic 6, .NET, C #, ASP and Flash/PHP sample programs using SAPI 5.x - Windows only
- Binaries for Simple SAPI (TTS audio creation tool) and Dictionary Editor (create user dictionary) - Windows only
- SDK is licensed for internal development/testing only and Usage or Distribution licensing is required for runtime or wavefile usage or distribution
|
