CLOVA Speech scenarios

Available in Classic and VPC

With CLOVA Speech of the NAVER Cloud Platform, you can easily convert the voice of media files to texts. You can check how to use CLOVA Speech in detail in Getting started with CLOVA Speech and Use CLOVA Speech, but it is recommended to first look at the entire scenario of using CLOVA Speech. You can use CLOVA Speech more efficiently by learning how to use it after studying the usage scenario. The full sequence of using CLOVA Speech and a description of each sequence are as follows:

1. Set usage permissions
2. Create domain
3. Register recognition tasks
4. Edit and export recognition results

1. Set usage permissions

You can set use permissions for CLOVA Speech. CLOVA Speech use permissions are defined by mapping "roles" to "sub accounts" issued by Sub Account of the NAVER Cloud Platform. Thus, you need to first create sub accounts other than your main account through Sub Account.

You can use sub accounts provided by Sub Account to configure administrator permissions and user permissions of CLOVA Speech. You can refer to the following guide:

• Managing CLOVA Speech permissions
• Sub Account Guide

2. Create domain

Create a domain on the NAVER Cloud Platform console. For each domain, you can specify the speech recognition target file and the storage path of the result file. You can refer to the following guide:

• Domain

3. Register recognition tasks

Register recognition tasks. You can request recognition tasks through the builder, or you can batch process multiple media file recognition tasks by creating a batch. You can refer to the following guide:

• Request recognition task
• Batch

4. Edit and export recognition results

After viewing and editing the recognition results, you can export them in the format of your choice. You can refer to the following guide:

• Edit and export recognition results