The supported server interfaces are:
- SAPI 5 (Win32)
- C / C++
- Python client API
- Java (beta) client API
- W3C SSML 1.0
To get examples of our speech synthesis, please contact us here.
No, we don’t charge SSML tags. So, “Hi<break>” will be charged as 2 characters.
At the moment, we support:
- English (a variety of UK accents, Irish, US, South African, Australian, New Zealand)
- Spanish (Castilian, Catalonian and Latin American)
- German (High German and Austrian)
- Portuguese (European and Brazilian)
- Italian
- French
- Dutch
- Japanese
- Romanian
No, you don’t need any of these. If you want, you can synthesise plain text only. Should you decide that your text needs some optimization, our intuitive TTS-Designer GUI helps you to easily add SSML tags with the press of a button.
Currently, our TTS supports iOS and Android native.
SSML is a subset of VoiceXML (VXML) and thereby an XML based markup language specified by the World Wide Web Consortium (W3C).
With SSML, it is possible to augment text ranges with additional information, such as emphasis, volume, pitch or adjust the duration of the pronunciation.
A detailed set of all standard SSML tags can be found on the W3C website.
Our CereVoices do not support W3C standardized tags.
You can download our SSML guide here.