Docs
MAC Whisperer
Text

[Text] to speech

The Text-to-Speech operation converts a provided text into an audio file.

Embedding Generate from Text

Input Fields

Module Configuration

This refers to the MAC Whisperer Configuration set up in the Getting Started section.

General Operation Fields

  • Text to convert: The text to convert in to audio.
  • Path to the output file: The complete path to the output file (to be generated). If file exists, it will be overwritten.

Additional Properties

  • Model Name: Indicates the model to be used (default is tts-1).
  • Voice: Indicates the voice to be used (default is alloy).
  • Speed: Indicates the speed of the playback (default is 1.0).
  • Response format: Indicates the output file format (default is mp3).

XML Configuration

Below is the XML configuration for this operation:

<
  whisperer:text-to-speech 
  doc:name="Text to speech" 
  doc:id="a3fb05f7-d093-43c0-891e-c8095ff260b8" 
  config-ref="OpenAI" 
  textToConvert="#[payload.text]" 
  pathToOutputFile="/Users/amir.khan/Downloads/audio/speech.mp3"
/>

Output Field

This operation responds with a json payload.

Example Output

This output has been converted to JSON.

{
    "outputDirectory": "/Users/amir.khan/Downloads/audio/speech.mp3"
}
  • outputDirectory: The output directory path to the output file.