Flexible and Adaptive Text To Speech

Flexible and Adaptive Text To Speech

Text To Speech Synthesis server ready for your application on the web.



Contact person(s)

For licensing information:

What it does

The Flexible and Adaptive Text To Speech (FA-TTS) SE is a Text To Speech server that enables simple and fast creation of synthetic speech based on a text input. The technology used allows the manipulation of various acoustic and linguistic parameters in order to obtain the synthetic voice that is most suitable for a specific situation. Pitch/rhythm modifications and a vocal tract scaler can be used to generate more expressive speech.

How it works

The FA-TTS SE is designed as a Saas. It is developed using the open source software MARYTTS, with additional features and all the scripts necessary to make install the enabler. Various parameters such as language, style, gender, age and voice can be edited in order to achieve the most suitable synthetic voice.

What you get

The implementation is available both as source archive either as docker image ready for use. It includes scripts to launch the server and run a test client.

Delivery model

  • Source

Discover more FIWARE Media & Content Enablers