Back to Speech technology

Voice licensing

Nuance Vocalizer Expressive offers a wide portfolio of more than 40 languages and 70 voices, allowing you to create global solutions using a single engine. A broad range of options are offered in order to fit a great variety of applications and platforms: from 4MB to over 900MB depending on the voice, language and model.

Supported platforms are Windows, .NET Framework, iOS, Android and Linux. If your platform is not listed please contact us for details.

Code Factory will advice you to make the optimal voice model choice for your platform and your application to assure a great end user experience.

voice-licensing

Listen to our voices

More about our Speech technology services

Features and benefits

Feature

Benefit

Amazing expressivity

Highly expressive speech gives the voice personality for the most natural and engaging user experience possible.

Advanced multi-lingual support

Accurate language identification and high-quality acoustic extensions provide unparalleled foreign language readout.

Naturalness

Natural sounding human-like speech output guarantees an exceptional end user listening experience.

Built-in domain intelligence

Optimization settings provide extra control options for special use cases such as SMS reading.

Flexible speech generation

Volume and speaking rate can be changed at run time for more dynamic and lively effects.

Direct phonetic input

Allows for optimal and seamless read out of off-line phonetic databases such as navigation map data.

User text rules

Customized read out of application specific abbreviations and text pattern is possible using a user text processing rule set.

User dictionaries

Application specific lexica can be phonetically optimized for accurate readout of exceptional pronunciations.

Prompt tuning

With offline tuning options any prompt set can be further optimized and customized for maximum flexibility.

Seamless prompt insertion

Recorded audio prompts or tuned prompts can be blended with dynamic text to speech seamlessly by active prompt matching.

Universality

A truly universal voice portfolio offers more than 40 languages and 70 voices to facilitate the creation of global solutions using a single engine.

Accuracy

High linguistic accuracy offers correct readout of all types of text input including a large dictionary of person names.

Scalability

A wide range of footprints from 2MB to 900MB ensures optimal performance on embedded platforms from very small mobile devices to powerful multi-media systems.

Voice data

Vocalizer Expressive offers a wide range of voice models suited for a great variety of applications.

Voice Model

Data size per voice

Total RAM usage

Compact

Fluent and versatile TTS suited for constrained platforms.

Average: 3 MB

Max: 8 MB

Average: 6700 kB

Max: 9800 kB

Plus

High quality, medium size TTS, with extra optimizations for reading names and addresses.

Average: 55 MB

Max: 97 MB

Average: 9500 kB

Max: 13500 kB

Premium

High quality natural TTS read-out for dialogs, announcement messages, SMS and e-mail, suitable for all types of applications.

Average: 95 MB

Max: 300 MB

Average: 23000 kB

Max: 75800 kB

Premium High

Highest quality TTS readout for all types of applications

Average: 306 MB

Max: 985 MB

Average: 23000 kB

Max: 75800 kB

We put our expertise, experience and knowledge at your disposal. Get in touch and hear more

Contact us