1     Functions

Receives
  1. Text Object.
  2. Personal Status.
  3. Speech Model.
Feeds Text Object and Personal Status to Speech Model.
Produces Utterance.

2      Reference Architecture

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

Figure 1 – The Text-To-Speech AIM

3      I/O Data

Table 1 specifies the Input and Output Data of the Automatic Speech Recognition AIM.

Table 1 – I/O Data of the Automatic Speech Recognition AIM

Input
Text Object Input Text.
Personal Status Input Personal Status
NNFormat 0=NNEF
1=ONNX
Speech Model Neural Network Speech Model
Output Description
Speech Object Output of the Text-To-Speech AIM

4      SubAIMs

No SubAIMs.

5     JSON Metadata

https://schemas.mpai.community/MMC/V2.2/AIMs/TextToSpeech.json

6 Profiles

The Text-To-Speech Profiles are specified.