Speech Cloud offers a secure, scalable and worldwide responsive web-service with simple API that provides a broad range of polyglot, high-quality, natural-sounding voices.
Speech Cloud supports automatic language identification and sophisticated polyglot speech generation of mixed-lingual texts for a broad range of languages.
Speech Cloud based text-to-speech allows using large statistical voice models, regular lexicon updates and a semantic analysis on the server to improve overall pronunciation quality, speech melody and rhythm.
Easy to use API for C, C++, Java and HTTP
OGG, MP3 with 16, 22 and 44kHz sampling rate
Metadata allowing synchronization of text with audio, useful for text highlighting and lip synchronization