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 the robot’s loudspeakers.
How it works ¶
Speech engines ¶
ALTextToSpeech is based on speech synthesizers - or speech engines.
According to the selected language, a specific engine is used:
|Japanese||microAITalk engine, provided by AI, Inc.|
|Other languages||According to the language package the engine is provided by ACAPELA or Nuance. The engine used is indicated in the description of the package.|
Using parameters ¶
The output audio stream can be modified.
For example, these effects are available:
- pitch shifting effect modifies the initial pitch of the voice,
- double voice effect produces a “delay/echo” effect on the main voice.
Additional parameters are available for microAITalk engine.
Further information can be found here : ALTextToSpeechProxy::setParameter()
Using tags ¶
To add some expressiveness when the robot speaks, it is highly recommended to use “tags” in your text. Tags, allows you to change, in the middle of a sentence, the pitch, the speed, the volume of a word, or add pauses between words, change the emphase of word.
For further details, see: Using tags for voice tuning.
Getting Started ¶
The easiest way to get started with ALTextToSpeech is to use the Say Choregraphe box.