- Print
- PDF
Prerequisites for using CLOVA Speech Recognition
- Print
- PDF
Available in Classic and VPC
You can view supported environments, pricing plans, and restrictions, etc., for smooth use of CLOVA Speech Recognition.
Cloud environment specifications
The following details are the cloud environment specifications supported by CLOVA Speech Recognition.
Item | Supported specifications |
---|---|
Region (Zone) | Korea, U.S., Singapore, Hong Kong, Japan, and Germany |
Platform | VPC, Classic |
Languages | Korean, English, and Japanese |
The languages in the cloud environment specifications refer to languages supported in the NAVER Cloud Platform console. For the types of languages recognized by CLOVA Speech Recognition, see Precautions when using the service.
Precautions when using service
The following are the precautions for using CLOVA Speech Recognition.
- Supported Languages: Korean, English, Japanese, Chinese (Simplified)
- Maximum speech length that can be recognized when calling the CLOVA Speech Recognition API once: 60 seconds
- Minimum sample rate of the original sound source file: 16 kHz or higher
- API service usage limits: Adjustable directly from 300,000 per application per month (30,000 seconds per day) to 30,000,000 per month (10,000,000 seconds per day). If you wish to raise the service usage limit beyond the range that you can adjust yourself, contact customer support on the NAVER Cloud Platform portal.
Supported specifications
Supported specifications of CLOVA Speech Recognition are as below.
Item | Supported specifications |
---|---|
Mobile SDK platform | |
REST API voice file format | mp3, aac, ac3, ogg, flac, wav |
Usage fee
CLOVA Speech Recognition is serviced on a pay-as-you-go pricing plan. For detailed criteria on the pricing for CLOVA Speech Recognition, see the Portal > Service >AI·NAVER API > CLOVA Speech Recognition menu or Portal > Pricing Plan menu.