What is the Text to Speech block?

The Text to Speech block is a block you can add to your automation workflow to convert text captured by the user into speech that can be played back and downloaded.

How to configure the Text to Speech block

Once the Text to Speech block has been added to your workflow, configure the block by using the panel on the right. Here is how you would configure the block for a simple poem generator that then converts the poem to speech:

1. Text: In the Text field of the Text to Speech block, add the variable containing the audio that you want to translate. In this example, the variable name is poem_text. Use double curly braces when typing the variable into this field.
2. Output: Assign an output variable name to the audio. For this example, we’ve named it poem_audio. You don’t have to add double curly braces when writing a variable name in this field.
3. Model Settings: Select the text to speech model you will use for this application. For this example, we chose ElevenLabs TTS.

Example automation workflow

Here’s what the automation workflow for this example includes:

1. User Input: First, the user is asked to provide text to be converted to speech.
2. Generate Text: The user’s input is passed to the Generate Text block.
3. Text to Speech: The Generate Text output is then passed to the Text to Speech block.
4. Display Text: Finally, the output of the Text to Speech block, the poem_audio variable, is displayed to the user as an audio player, allowing the user to either download or play back the audio at a different speed.

‍