tencent cloud

PrevNext

Feedback

search by keyword

Recent Pages

Documentation
Cloud Infinite
    Documentation

    Text to Speech

    Last updated: 2024-01-31 16:44:15

      Overview

      For files already in a bucket, you can create a job for smart audio operations. Currently, only text to speech jobs are supported, which can be created using a template. You can use CI's preset templates or customize templates. For more information, see Template.
      Note:
      Currently, the job feature can only manipulate existing files. To manipulate files during upload, use the workflow feature as described in Workflow.
      A created job will incur fees. For detailed pricing, see Smart Audio Fees.

      Viewing Jobs

      On the job page, you can view all jobs in different types for the specified time period, click Status to filter and view jobs in different statuses, search for jobs by job ID in the search box, and click View on the right of a job to view its following information:
      Job information: Job ID, job status, queue ID, template ID, job creation time, and job end time.
      Input information: Source video bucket, region, and storage path.
      Destination information: Destination audio address, bucket, region, and storage path.
      Note
      A job has six statuses: succeeded, failed, executing, pending, paused, and canceled.
      You can query the records of jobs for the past month only.

      Creating a Text-to-Speech Job

      The text to speech feature converts text into natural-sounding and smooth speeches for use in smart customer service and audiobook scenarios.

      Directions

      1. Log in to the CI console.
      2. Click Bucket Management on the left sidebar to enter the bucket list.
      3. Click the name of the target bucket.
      4. On the left sidebar, click Data Processing Workflow > Task Management and select the corresponding tab at the top.
      5. Select Artificial Audio Intelligence > Text to Speech as the job type, click Create Job, and configure as follows:
      Source File URL: Enter the path of the source file, which cannot begin or end with /.
      Template: Select a custom template. If there are none, create one first.
      Destination Bucket: Select a bucket for which the media processing feature has been enabled in the current region.
      Destination Path: Storage path of the output file.
      Voice Filename: Name of the output voice file.
      Queue: Currently, only the default queue queue-1 is supported.
      Contact Us

      Contact our sales team or business advisors to help your business.

      Contact Us
      Technical Support

      Open a ticket if you're looking for further assistance. Our Ticket is 7x24 avaliable.

      Submit a Ticket
      7x24 Phone Support
      Copyright © 2013-2024 Tencent Cloud. All Rights Reserved.
      Privacy PolicyLegalCookie Policy