Domain

Available in Classic and VPC

CLOVA Speech allows you to create domains and manage recognition tasks per domain. For each domain, you can set the storage paths for input files and result files, and use the Builder provided for each domain to request recognition tasks.
In the Domain menu, you can create and manage domains, and launch the Builder for each domain.

Domain interface

The basic overview of the Domain interface for using CLOVA Speech is as follows.

View domain list

To view information about your created domains:

1. From the NAVER Cloud Platform console, navigate to > Services > AI Services > CLOVA Speech.
2. Click Domain.
3. When the domain list appears, review the summary information for each domain.
   • Domain name: Name entered when the domain was created
   • Domain code: Code entered when the domain was created
   • Type: Service plan of the domain
   • Created (UTC+09:00): Domain creation date and time
   • Action: Click [Launch Builder] button to run the Builder for this domain (For details on the Builder, refer to Long-form recognition builder or Short-form recognition builder)

Create a domain

To create a domain:

1. From the NAVER Cloud Platform console, navigate to > Services > AI Services > CLOVA Speech.
2. Click Domain.
3. Click [Create domain] button.
4. Enter the domain information.
   • Domain name: Enter the name for the domain
   • Domain code: Enter the code for the domain
     • The domain code cannot be modified later, so enter carefully.
   • Service plan: Select a plan
     • Free: Applies the Free plan; provides a limited amount of free monthly recognition time Only one Free domain can be created per account, and Free domains cannot be deleted.
     • Basic: Applies the Basic plan
   • Additional features: Select additional features based on domain type
     • (Short-form recognition) Pronunciation evaluation: Checks word- and sentence-level pronunciation accuracy. Available when the recognition language is Korean or English.
     • (Long-form recognition) Speaker recognition: Detects and differentiates speakers.
     • (Long-form recognition) Event detection: Detects events such as music or applause in the audio.
     • (Streaming recognition) Papago translation: Translates speech recognition results into the desired language. To use this feature, you must first apply for Papago Translation and register an Application.
   • The domain type cannot be changed later, so choose carefully.
   • For detailed pricing, refer to the CLOVA Speech introduction page.
5. Enter the Object Storage paths where input and result files will be stored.
   • Result file storage path: Click the field and select the Object Storage path for recognition result files
   • Input file storage path: Click the field and select the Object Storage path for input files
   • [Go to Object Storage] button: Click to open the Object Storage console interface
6. Click [Save] button.

Edit a domain

To modify a domain:

1. From the NAVER Cloud Platform console, navigate to > Services > AI Services > CLOVA Speech.
2. Click Domain.
3. In the domain list, select the domain you want to edit and click [Edit] button.
4. Modify the domain information, then click [Edit] button again.
   • For detailed descriptions of each field, refer to Create a domain.

Delete a domain

Deleted domain information cannot be restored.

1. From the NAVER Cloud Platform console, navigate to > Services > AI Services > CLOVA Speech.
2. Click Domain.
3. In the domain list, select the domain you want to delete and click [Delete] button.
4. When the domain deletion popup appears, review the warnings, then click [Delete domain] button.