- Print
- PDF
Prerequisites for using CLOVA Speech
- Print
- PDF
Available in Classic and VPC
Check supported specifications and usage fees for efficient use of CLOVA Speech.
Cloud environment specifications
The cloud environment specifications supported by CLOVA Speech are as follows:
Item | Supported specifications |
---|---|
Region (zone) | Korea |
Platform | VPC, Classic |
Languages | Korean, English, Japanese, and Chinese |
If you are curious about the VPC environment, see NAVER Cloud Platform portal service introduction, and if you want to know whether the VPC and Classic environments are supported for each service, see the Ncloud use environment guide.
There may be differences in the languages provided by each domain.
Scope of support
The recognition targets and result files supported by CLOVA Speech are as follows:
Item | Scope of support |
---|---|
Recognizable languages | Long sentence recognition: Korean, English, simultaneous recognition of Korean and English, Japanese, and Chinese (traditional/simplified) Short sentence recognition: Korean, English, Japanese, and Chinese |
Recognizable time | Long sentence recognition: up to 2 hours Short sentence recognition: up to 60 seconds |
Size of the recognition file | Long sentence recognition: up to 2 GB Short sentence recognition: up to 3 MB |
Recognized file formats | Long sentence recognition:
|
Usage fee
CLOVA Speech charges according to the voice recognition usage time. For detailed information on CLOVA Speech usage fees, see the Service > AI Services > CLOVA Speech menu of the portal or the pricing information page for each region.
- Portal > Services > AI Services > CLOVA Speech
- Pricing information by Region page