Set up a personal voice

Set up a personal voice before you add the voice talent's consent and audio prompt.

Prerequisites

  • Your use case must be approved for limited access to custom voice.
  • You must have explicit permission from the voice talent to create and use a synthetic version of their voice.

Prepare your Foundry project

Use a Foundry project associated with a resource in a region that supports personal voice. Check the Personal voice column in the Speech service regions table. To create a project, see Create a Foundry project.

Personal voice isn't available on the Free (F0) tier. For supported tiers and limits, see Personal voice quotas.

Start a personal voice customization

In Foundry (new), you create a personal voice as a customization. To start, follow these steps:

Tip

To start from Build, select Services > Customizations. Select Create, and then complete Basic details in this procedure.

  1. Sign in to Microsoft Foundry. Make sure the New Foundry toggle is on. These steps refer to Foundry (new).

  2. Open the Foundry project associated with the resource you want to use for personal voice.

  3. Select Discover.

  4. On Overview, under Experiment with prebuilt services, select Azure Speech.

  5. On the Services page, under Customize, select Personal voice to open the Customize a model page.

    Screenshot of Azure Speech services in Foundry with Personal voice outlined under Customize.

  6. On the Basic details step, fill in these settings:

    • Select model: Select Azure Speech - Text to Speech if it isn't already selected.
    • Type: Select Personal voice if it isn't already selected.
    • Voice name: Enter a name for your voice.
    • Description: Optionally enter a description.

    Screenshot of the Customize a model page with Personal voice selected and the Type and Voice name fields outlined.

  7. Select Next.

The wizard continues to the Register voice talent step, where you add user consent.

Next steps

Add user consent for personal voice.

The custom voice REST API organizes the user consent statement and personal voice ID in a Personal Voice project.

Create a project

To create a personal voice project, use the Projects_Create operation of the custom voice API. Construct the request body according to the following instructions:

  • Set the required kind property to PersonalVoice. The kind can't be changed later.
  • Optionally, set the description property for the project description. The project description can be changed later.

Make an HTTP PUT request using the URI as shown in the following Projects_Create example.

  • Replace YourResourceKey with your Speech resource key.
  • Replace YourResourceName with your Speech resource name.
  • Replace ProjectId with a project ID of your choice. The case sensitive ID must be unique within your Speech resource. The ID will be used in the project's URI and can't be changed later.
curl -v -X PUT -H "Ocp-Apim-Subscription-Key: YourResourceKey" -H "Content-Type: application/json" -d '{
  "description": "Project description",
  "kind": "PersonalVoice"
} '  "https://YourResourceName.cognitiveservices.azure.com/customvoice/projects/ProjectId?api-version=2026-01-01"

You should receive a response body in the following format:

{
  "id": "ProjectId",
  "description": "Project description",
  "kind": "PersonalVoice",
  "createdDateTime": "2024-09-01T05:30:00.000Z"
}

You use the project id in subsequent API requests to add user consent and get a speaker profile ID.

Next steps

Add user consent for personal voice.

  • Last updated on