From marked text to mixed speech and sound
MetadataShow full item record
Loquendo TTS is a commercial Multilanguage/Multivoice Text-To-Speech synthesizer, attaining great acoustic naturalness and linguistic accuracy. Currently available languages are: Catalan, Chinese, Dutch, British English, American English, French, German, Greek, Italian, Portuguese, Brazilian, Castilian, Argentine, Chilean, Mexican and Swedish. Loquendo TTS is a flexible engine, based on multi-language external knowledge-bases, efficient and platform-independent. It performs text-to-speech conversion as a real-time ``software-only'' process. The Loquendo TTS integrated audio mixer allows mixing sound files and synthetic voice. It's possible to mix one or more sound files simultaneously, at the same time. Thanks to explicit tags embedded in the text, easy synchronization between audio files and speech is guaranteed even if the text is modified. Every sound effect is treated as an independent track, with independent timeline, volume and sample rate. Commands such Mix, Play, Stop, Pause, Resume, Loop and Fade allow users to have complete control on the audio sources. In order to make easy the use of the integrated audio mixer, a multi-platform application is shipped with Loquendo TTS SDK: TTSDirector. Loquendo TTS Director is a Java multiplatform development tool intended for helping the user in the design of the application prompts. The text of the application prompt can be written in the edit box and interactively refined by means of a ``listen & edit'' procedure, allowing to tune the TTS behavior by means of the Loquendo TTS User Control Tags. This paper gives details about the previous topics and can be used as basis for the workshop demonstration, concerning the use of the audio mixer, integrated into the Loquendo TTS, and other functionalities.