CLOVA Speech Recognition(CSR) Overview
- Print
- PDF
CLOVA Speech Recognition(CSR) Overview
- Print
- PDF
Article Summary
Share feedback
Thanks for sharing your feedback!
We are preparing a localization service for the content. We will do our best to provide the localization service as soon as possible.
The CLOVA Speech Recognition (CSR) API helps you create services such as a secretary application, chatbot and voice memo, which need to recognize and interpret human speech. The API delivers the speech data to the CSR engine, which then recognizes and converts it into text.
Common information
You can get a Client ID by registering your application in NAVER Cloud Platform Console.
Go to AI·NAVER API > AI·NAVER API > Application in your web console and register an application. Learn how to register >
Check your Client ID and Client Secret by selecting the application registered in AI·NAVER API > AI·NAVER API > Application.
Click [Edit] of the application to make sure that CLOVA Speech Recognition is selected. If it is not selected, a 429 error (Quota Exceed) occurs.
How to make an API request
The CSR API is a REST API that transmits speech data to recognize to the speech recognition server over HTTP communications. The REST API’s URI provided by the speech recognition server is shown below. You should use the POST method to make an API request.
API URL
| Method | Request URI |
|---|---|
| POST | https://naveropenapi.apigw.ntruss.com/recog/v1/stt |
Request Header
| Header | Description |
|---|---|
| X-NCP-APIGW-API-KEY-ID | Client ID issued when registering an appX-NCP-APIGW-API-KEY-ID:{Client ID} |
| X-NCP-APIGW-API-KEY | Client Secret issued when registering an appX-NCP-APIGW-API-KEY:{Client Secret} |
| Content-Type | Set this to application/octet-stream.Content-Type: application/octet-stream |
Error Codes
{
"error": {
"errorCode": "300",
"message": "Not Found Exception"
}
}
Common errors
| HTTP status code | Error code | Error message | Description |
|---|---|---|---|
| 400 | 100 | Bad Request Exception | Request error in protocol (https) or encoding (UTF-8). |
| 401 | 200 | Authentication Failed | Authentication failed. |
| 401 | 210 | Permission Denied | Authentication failed. |
| 404 | 300 | Not Found Exception | Authentication failed. |
| 429 | 400 | Quota Exceeded | Quota exceeded. |
| 429 | 410 | Throttle Limited | Rate exceeded. |
| 429 | 420 | Rate Limited | Rate exceeded. |
| 413 | 430 | Request Entity Too Large | Content-length exceeded (10 MB). |
| 503 | 500 | Endpoint Error | End point connection error |
| 504 | 510 | Endpoint Timeout | End point connection timeout |
| 500 | 900 | Unexpected Error | Unexpected error |
API errors
| HTTP status code | Error code | Error message | Description |
|---|---|---|---|
| 413 | STT000 | Request Entity Too Large | Speech data volume exceeded (up to 3 MB). |
| 413 | STT001 | Exceed Sound Data length | Speech data length exceeded (60 sec.). |
| 400 | STT002 | Invalid Content Type | The content-type is not application/octet-stream. |
| 400 | STT003 | Empty Sound Data | No speech data entered. |
| 400 | STT004 | Empty Language | No language parameter entered. |
| 400 | STT005 | Invalid Language | Invalid language specified. |
| 500 | STT006 | Failed to pre-processing | Error occurred while pre-processing speech recognition. Check if speech data is a valid WAV, MP3, or FLAC file. |
| 500 | STT998 | Failed to STT | Error occurred during speech recognition. Contact us and we will take action as soon as possible. |
| 500 | STT999 | Internal Server Error | Unknown error occurred. Contact us and we will take action as soon as possible. |
Was this article helpful?