|
<< Click to Display Table of Contents >> Navigation: 3. Script Language > AI - Artificial Intelligence Commands > AIU. - OpenAI API > ! Speech and Voice Configuration > AIU. - Artificial Intelligence Utility |
MiniRobotLanguage (MRL)
AIU.SetTtsModel
Sets the model to be used for Text-to-Speech.
Intention
The AIU.SetTtsModel command (aliased as AIU.Stsm) selects the underlying AI model that will be used to generate audio with the AIU.TextToSpeech command. You can choose between a standard, fast model and a high-definition model for the highest quality audio.
It’s like choosing the engine for your robot’s voice—AIU.SetTtsModel lets you decide between speed and superior audio quality for the speech you generate.
Illustration
┌─ AI Voice Model Selection ─┐
│ │
│ ( ) tts-1 (Standard) │
│ (◉) tts-1-hd (HD Audio) │
│ │
└────────────────────────────┘
Selecting the desired audio quality for speech synthesis.
Syntax
AIU.SetTtsModel|$$MDL
Parameter Explanation
P1 - $$MDL - (Variable, String, Required)
The name of the Text-to-Speech model to use. The value is case-insensitive. Valid options are:
"tts-1" - (Default) Optimized for real-time use cases.
"tts-1-hd" - Optimized for quality.
Examples
'***********************************
' AIU.SetTtsModel - Sample 1: Select High Definition model
'***********************************
VAR.$$KEY=sk-YourSecretKeyHere
AIU.SetKey|$$KEY
' Set the model to high definition for the best quality
AIU.SetTtsModel|tts-1-hd
VAR.$$TXT=Hello from the high definition model.
VAR.$$PTH=?path\hd_audio.mp3
AIU.TextToSpeech|$$TXT|$$PTH
AIU.GetLastError|$$ERR
JNZ.$$ERR|Lab_failed
MBX.Success:|Audio file created at $$PTH
END.
Remarks
- The alias AIU.Stsm can be used for convenience.
- The default model is "tts-1" if this command is never called.
- If an invalid model name is provided, the setting will revert to the default ("tts-1").
- The chosen model setting persists for the duration of the script session or until it is changed again.
See also: