Creating audio output for any automated phone system can be a complex and challenging task when you consider the prospect of recording every prompt. And while the promise of text-to-speech engines is to eliminate the need for recordings, sometimes recorded prompts are better suited to the task. Until now, the ideal scenario - combining recordings and computer generated speech - has presented its own challenges. That changes with the introduction of Nuance Vocalizer 5, the complete spoken output engine.
Vocalizer 5 handles all application audio, including both static recordings and dynamically generated prompts. By incorporating static recordings into Vocalizer's speech database, it can seamlessly blend them with computer-generated speech where appropriate. Callers hear a seamless ﬂow of speech, free from undesirable artifacts such as clicks and gaps that surface when using separate systems for playback of recordings and for computer generated speech.
In addition to improving the user experience, Vocalizer 5 simplifies application development effort by eliminating the need to write custom code to mix and match recordings with computer generated speech. Now, an application can just send text to Vocalizer 5 and it will determine whether to use pre-recorded prompts, dynamically generated speech or a combination of the two.
Vocalizer 5 advances the state of the art in automated speech output. In addition to the ability to gracefully blend static and dynamic speech output, Vocalizer 5 features enhanced speech quality and accuracy through optimized text processing, more comprehensive pronunciation dictionaries and, in many languages, complete voice refreshes.
Name and address optimization
The interpretation of addresses and the pronunciation of names have been optimized in all Vocalizer 5 languages. In recognition that the world of proper names is ever-changing, proper name dictionary supplements are made available periodically to provide up-to-date pronunciations for new words or phrases and to account for shifting trends in the pronunciations of names over time.
Highly tunable and customizable
Vocalizer 5 offers unprecedented control over speech output with Vocalizer Studio, a suite of easy-to-use tools. With Vocalizer Studio, creating text processing rules and modifying pronunciations is straightforward and intuitive. Vocalizer Studio also includes PromptSculptor, a powerful interface for customizing the intonation and expressivity of speech output.
Vocalizer 5 includes support for emerging and accepted standards such as SSML, VXML, and MRCPv2.
Easy to useProduct Highlights
Vocalizer 5 has been re-architected to facilitate operations and maintenance. Up to twice as many voices can be run on the same server compared to previous Nuance TTS products. Documentation, error messaging, versioning and sizing information have been updated to provide the most useful information in the most useful manner. Tuning and customization, such as user dictionary or user rule set updates, can be affected without interrupting live traffic. And multiple speech based applications can share the same instance of Vocalizer 5 and still be tracked separately for logging and reporting tasks.
- One source for all output
- Name and address optimizations
- Lower costs of implementation
- Easy to customize