| Class | Description | 
|---|---|
| AudioFormat | 
 Audio format supported by the  
TextToSpeech service. | 
| CustomTranslation | 
 A customized word translation, assigning a specific pronunciation to a given word. 
 | 
| CustomVoiceModel | 
 A customized voice model, that allows users to specify custom pronunciations for Waton's Text to Speech API. 
 | 
| Pronunciation | 
 Phonetic pronunciation class. 
 | 
| Voice | 
TextToSpeech voice. | 
| Enum | Description | 
|---|---|
| Phoneme | 
 Phoneme enumeration. 
 | 
Copyright © 2015–2016 IBM Watson. All rights reserved.