Configuring a voice

Configure your agent to use voice when communicating with users. On IBM watsonx Orchestrate, you can configure more than one voice to be used in any agent.

Note: Voice is limited to the agent builder preview and cannot be deployed to the channels.

Before you begin

Before configuring a voice, you need:

  • Access to IBM Watson Speech to Text and Text to Speech service instances.
  • API details, including the API key, for both instances.

To get the API details or create new instances of these services, access the IBM Cloud page.

Creating a voice configuration

To create a voice configuration and enable it in an agent:

  1. Click the watsonx Orchestrate menu menu.

  2. Select Manage > Voice.

  3. Click Create voice configuration.

  4. In the Details tab, enter a name for the voice configuration and click Next.

  5. In the Speech to Text tab, you must configure the Watson Speech to Text service.

    1. Enter the API URL of the Watson Speech to Text instance.
    2. Enter the API key of this instance.
    3. Select the Speech to Text language model.

    For more information, see the Speech to Text documentation.

  6. Click Next.

  7. In the Text to Speech tab, you must configure the Watson Text to Speech service.

    1. Enter the API URL of the Watson Text to Speech instance.
    2. Enter the API key of this instance.
    3. Select the language of the voice.

    For more information, see the Text to Speech documentation.

  8. Select the type of voice.

  9. Define the speed and pitch of the voice.

  10. Click Save.

You have a voice configuration available to define voice interactions for your agents.

Editing voice configuration

To edit the voice configuration:

  1. On the Voice page, choose the voice configuration and click the three vertical ellipses.
  2. Select the Edit option.
  3. Apply the changes through the three tabs.
  4. Click Save.

Deleting voice configuration

To delete the voice configuration:

  1. On the Voice page, choose the voice configuration and click the three vertical ellipses.
  2. Select the Delete option.
  3. In the pop-up window that appears, click Delete.
Note: If the voice configuration is linked to one or more agents, you must remove all links before the deletion.

Selecting the voice in the agent

After you have created the voice configuration, you must select it in your agent. See the following steps:

  1. Open the agent in the agent builder.
  2. In the Profile tab, go to the Voice modality section.
  3. Select the voice configuration from the drop-down list.
Note: To enable the voice modality, you must create at least one voice configuration.

Testing the voice

You can test the voice in the chat preview in the following way:

  1. Click Being voice chat Voice chat icon.
  2. Give the required microphone permission in the browser.
  3. After interacting with the agent through the voice, click End voice chat to finish the conversation.