The Text to Speech block is powered by Eleven Lab’s speech model. This block is used to generated a speech output based on any text.

The Text to Speech block has 1 input and 1 output.

Inputs:

  • Text: The text to convert into speech (audio).

Output:

  • Speech: The audio output from the Text to Speech model based on the text input.

Upon clicking on the settings for the Text to Speech block, you can choose the type of voice the audio output will use with from the drop down menu:

You can preview each voice before using, and tinker additional settings for voice stability and “similarity” to the original voice.

Compliant Audio TranscriptionWhisper