1     Version

V2.1

2     Functions

Text-To-Speech:

  1. Receives
    1. Text
    2. Speech Descriptors
    3. Personal Status.
  2. Produces a speech utterance that conveys the Text with a type of speech specified by Speech Descriptors and with a Personal Status specified by the input Personal Status.

3      Reference Architecture

Figure 1 depicts the Reference Architecture of the Text-To-Speech AIM.

Figure 1 – The Text-To-Speech AIM

4      I/O Data

Table 1 specifies the Input and Output Data of the Personal Status Display AIM.

Table 1 – I/O Data of the Text-To-Speech AIM

Input data From Comment
Speech Descriptors E.g., a local storage of a Personal Status Display To personalise a Machine’s utterance.
Text Entity Dialogue Processing Text produced by Machine
PS-Speech Entity Dialogue Processing Personal Status of Speech
Output data To Description
Speech Downstream AIM e.g., for actual rendering via a Portable Avatar

5     SubAIMs

No SubAIMs.

6     JSON Metadata

https://schemas.mpai.community/MMC/V2.1/AIMs/TextToSpeech.json