Help Center/ MetaStudio/ User Guide/ Voice Modeling/ Creating a Voice Modeling Task
Updated on 2024-12-23 GMT+08:00
View PDF
Share

Creating a Voice Modeling Task

You can view the preset voices of MetaStudio on the Video Production or Livestreams page. If the preset voices cannot meet your requirements, you can use models to customize voices.

Constraints

Only enterprise users can customize voices on MetaStudio.

Preparations

Before creating a voice modeling task, you need to prepare the following items by referring to Procedure:

  • If you select Script Upload, record an audio in advance by referring to the recording guide on the voice modeling page.

Procedure

  1. Log in to the MetaStudio console.
  1. Click Create under Voice modeling.

    On the page displayed, the area on the left is for voice modeling, and the area on the right shows the voice modeling process.
    Figure 1 Customizing a voice

  2. Under the Huawei Models tab, configure voice modeling parameters.

    For details, see Table 1.

    Table 1 GUI operations

    Parameter

    Description

    Voice modeling (advanced edition)

    Only 100 pieces of script are required for voice modeling (advanced edition). You need to record a WAV audio of 10 to 30 minutes (recommended: 15 minutes).

    The remaining voice modeling quota will be displayed.

    Voice Settings

    Enter a voice name.

    Example: emotion_joyful_healing

    Voice Gender

    Gender of the voice. Options:

    • Male
    • Female

    Input Language

    Language of the voice. Options:

    • Chinese
    • English

    Voice Tag

    Tag of the voice. Options:

    • News
    • Marketing

    Script of each of the preceding tags is preset in MetaStudio, as shown in Script Examples (Advanced Edition). When using the preset script, you must select the corresponding tag.

    Produce Voice

    The method of voice modeling is Script Upload. You can follow the recording guide provided on the GUI to record 100 pieces of script in a WAV file, which can be directly uploaded without being compressed or containing TXT files.

    If the preset script is not used, the voice tag is only used to indicate the application scenario.

  3. Click Submit.

    The Information dialog box is displayed, notifying you of the remaining voice modeling quota and indicating that one resource will be consumed this time.

  4. After confirming the information, click Submit.

    After the voice modeling task is submitted, the message Production task submitted is displayed, as shown in Figure 2.

    After the voice modeling task is submitted, the task review will take about one day. After the task is approved, you can start voice modeling. The task takes about 1 to 3 working days.

    • Figure 2 Production task submitted

  5. You can click View Production Tasks to view the review progress of the voice modeling task.

    When the status changes to Reviewed, algorithm training is automatically started. If there are multiple algorithm training tasks, queuing and delay may occur.

Parent topic: Voice Modeling