Clova Speech Synthesis(CSS)
입력한 텍스트를 자연스러운 목소리로 재생해주는 음성 합성 API입니다
Speech Synthesis APIthat Transforms Text to Professional Voice Narrations
A service that is useful when developing an application that narrates text in a voice actor's charming voice. Text is spoken naturally, so it can be utilized for services such as voice guidance systems and news/book reading services.
- Natural-sounding Synthesized Speech
- The most natural-sounding synthesized speech in Korea as a result of NAVER’s years of research and development experience. You can use an API that is as technologically advanced as the speech recognition technology used by Clova. The API is available in Korean, English, Japanese, and Chinese.
- Performance Improvement through Learning
- A service that learns continuously using the artificial intelligence technology of Machine Learning. Meet Clova Speech Synthesis (CSS), which is becoming smarter with abundant data obtained via NAVER services.
- Easy Use
- Web-based console allows easy use. The API supported in RESTful-type allows easy application of the speech synthesis features to your service. You can check the resulting materials as an mp3 format in streaming data or file.
Provides a range of artificial intelligence services that learns from NAVER's abundant data.
An API that sends the input text using the RESTful API method, recognizes text in the server, and returns streaming data or a file in the mp3 format.
|Return Format||Streaming data or files in the mp3 format|
|Available Languages||Korean, English, Japanese, and Chinese|
Using the API
As an open API that does not require a login, service usage is possible by sending the Client ID and the Client Secret value issued when you registered the application in the HHTP header at the time of calling POST.
You can develop book reading, voice guidance, news, and audio services using a natural-sounding human voice in a conversational
tone, instead of a rigid machine voice.
This is the same level of speech synthesis technology as the one currently used in Clova.
Service Usage Limit
You can adjust the usage limit of Clova Speech Synthesis API yourself using various options from 3 million characters a month (100,000 characters a day) to 3 billion characters a month (1 billion characters a day) per application.
Calling is allowed for the last call that exceeds the usage limit. (The usage fee is calculated based on the number of actual calls.)
E.g., you have set the monthly usage limit to 1,000 characters. Once you use 990 characters, you can call extra 20 characters. Then, you can use a total of 1010 characters and will be billed for 1010 characters.
If you need to increase the service limit, please contact Customer Support
CSS usage fee will be charged on the number of service usage per 1,000 characters.
|Billing Basis (Monthly)||Unit||Usage Fee (KRW)|
|Usage Fee Based on the Characters Used for Speech Synthesis||Characters used (per 1,000 characters)||4 KRW per 1,000 characters|
- Number of characters will be rounded up to the nearest 1,000.
- Characters used will be accumulated and calculated by on a monthly basis.
Case 1) Using 100 characters from API call 1: 4 KRW.
Case 2) Using 4,500 characters from API call 1: 20 KRW.
Case 3) Using 700 characters from API call 1 and using 200 characters from API call 2 within the same month: Since monthly usage of characters is added up to a total of 900 characters and 4 KRW will be charged.