The ElevenLabs block uses ElevenLabs API and enables you to convert text into speech using their voices and models. This integration is useful for enhancing user interactions with Audio Agent Dialogs by generating realistic audio responses dynamically.

​
Features

  • Text-to-Speech Conversion: Transforms a text input into speech using ElevenLabs’ models.
  • Temporary Audio Link: Generates a temporary URL to the audio file, which can be used directly in an Audio Agent Dialog or other functionalities.

​
How to Set Up the Integration

​
1. Obtain ElevenLabs API Key

  1. Visit ElevenLabs and log in.
  2. Navigate to your API Key section and copy the key for use in your configuration.

​
2. Configure your Agent flow

Add your ElevenLabs block to your agent flow. This block will allow you to convert text into speech. Then configure the block with the following parameters:

  • ElevenLabs API Key: Paste your ElevenLabs API key here.
  • Text: The text you want to convert into speech. This can be a static text or a variable that holds the text.
  • Voice: Select the voice model you want to use for the conversion. ElevenLabs provides various voice options.
  • Model: Choose the model you want to use for the text-to-speech conversion. Different models may have different characteristics and capabilities.
  • Save audio URL in variable Save the generated audio URL in a variable for later use. Call the variable using an Audio Agent Dialog block to play the audio.

​
Example: Text-to-Speech API Request

  • Create a short greeting message using the Text dialog block.
  • Prompt the user to enter their name using the Text Input block.
  • Use the ElevenLabs block to convert the greeting message into speech. For example, if the greeting message is “Hello, [User’s Name]!”, you can set the Text parameter to Hello, {{user_name}}.
  • Select the desired voice and model from the ElevenLabs options.
  • Save the generated audio URL in a variable, e.g., greetings.

You can enable auto-play on the Audio Agent Dialog block to play the audio automatically when the dialog is triggered. This feature enhances user experience by providing immediate feedback.

Oncew triggered, the ElevenLabs block will send a request to the ElevenLabs API with the specified parameters. The API will process the request and return a response containing the audio file URL.