ALTextToSpeech

Overview | API | Tutorial

What it does

The ALTextToSpeech module allows the robot to speak. It sends commands to a text-to-speech engine, and authorizes also voice customization. The result of the synthesis is sent to NAO’s loudspeakers.

How it works

ALTextToSpeech is based on a speech synthetizer provided by:

  • ACAPELA for european languages, Chinese & Korean, and
  • HTS Engine for Japanese.

Depending on the engine, effects voice customization are possible.

For ACAPELA engine, voice can be customized through “tags” included within the string command sent to the engine. Further informations can be found here: Acapela Mobility Text TAGS Documentation

The output audio stream of both engine can also be modified by using one of these effects:

  • pitch shifting effect modifies the initial picth of the voice,
  • double voice effect produces a “delay/echo” effect on the main voice.

Further information can be found here : ALTextToSpeechProxy::setParameter

Note

ACAPELA and HTS engines are only available on the robot.

Getting Started

The easiest way to get started with ALTextToSpeech is to use the Say Choregraphe box.