tts (Premium)

Overview

CLOVA Voice - Premium API is an HTTP-based REST API that synthesizes speech from text using parameters, such as tone, speed, and emotion.

Requests

curl -i -X POST \
	-H "Content-Type:application/x-www-form-urlencoded" \
	-H "X-NCP-APIGW-API-KEY-ID:{Client ID value issued upon registering the application}" \
	-H "X-NCP-APIGW-API-KEY:{Client secret value issued upon registering the application}" \
	-d 'speaker={voice type}&text={text}&volume={volume}&speed={speech playback speed}&pitch={pitch}’ \
 'https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts'

Request parameters

Request headers

Request bodies

• This API does not require request bodies.

Responses

Response bodies

• Binary MP3 or WAV data

Examples

Request examples

curl -i -X POST \
	-H "Content-Type:application/x-www-form-urlencoded" \
	-H "X-NCP-APIGW-API-KEY-ID:{Client ID value issued upon registering the application}" \
	-H "X-NCP-APIGW-API-KEY:{Client secret value issued upon registering the application}" \
	-d 'speaker=nara&text=Nice to meet you&volume=0&speed=0&pitch=0&format=mp3' \
 'https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts'

Response examples

[HTTP Response Header]
HTTP/1.1 200 OK
Server: nginx
Date: Wed, 09 Sep 2020 02:35:50 GMT
Content-Type: audio/mpeg
Content-Length: 15216
Connection: keep-alive
Keep-Alive: timeout=5
Playtime: 1890
X-Chars-Count: 6
X-QUOTA: 1
X-Ssgw-Request-Id: f53c46c5-cce6-4943-b986-47ba752f8937
X-Text-Length: 26

[HTTP Response Body]
{Binary data in MP3 format}

API examples

// NAVER speech synthesis open API example
import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;
import java.net.URLEncoder;
import java.util.Date;

public class APIExamTTS {

    public static void main(String[] args) {
        String clientId = "YOUR_CLIENT_ID";//Application client ID value";
        String clientSecret = "YOUR_CLIENT_SECRET";//Application client secret value";
        try {
            String text = URLEncoder.encode("Nice to meet you.", "UTF-8"); // 13 characters
            String apiURL = "https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts";
            URL url = new URL(apiURL);
            HttpURLConnection con = (HttpURLConnection)url.openConnection();
            con.setRequestMethod("POST");
            con.setRequestProperty("X-NCP-APIGW-API-KEY-ID", clientId);
            con.setRequestProperty("X-NCP-APIGW-API-KEY", clientSecret);
            // post request
            String postParams = "speaker=nara&volume=0&speed=0&pitch=0&format=mp3&text=" + text;
            con.setDoOutput(true);
            DataOutputStream wr = new DataOutputStream(con.getOutputStream());
            wr.writeBytes(postParams);
            wr.flush();
            wr.close();
            int responseCode = con.getResponseCode();
            BufferedReader br;
            if(responseCode==200) { // Successful call
                InputStream is = con.getInputStream();
                int read = 0;
                byte[] bytes = new byte[1024];
                // Randomly generates the MP3 file name
                String tempname = Long.valueOf(new Date().getTime()).toString();
                File f = new File(tempname + ".mp3");
                f.createNewFile();
                OutputStream outputStream = new FileOutputStream(f);
                while ((read =is.read(bytes)) != -1) {
                    outputStream.write(bytes, 0, read);
                }
                is.close();
            } else {  // Error occurred
                br = new BufferedReader(new InputStreamReader(con.getErrorStream()));
                String inputLine;
                StringBuffer response = new StringBuffer();
                while ((inputLine = br.readLine()) != null) {
                    response.append(inputLine);
                }
                br.close();
                System.out.println(response.toString());
            }
        } catch (Exception e) {
            System.out.println(e);
        }
    }
}

// NAVER speech synthesis open API example
<?php
  $client_id = "YOUR_CLIENT_ID";
  $client_secret = "YOUR_CLIENT_SECRET";
  $encText = urlencode("Nice to meet you.");
  $postvars = "speaker=nara&volume=0&speed=0&pitch=0&format=mp3&text=".$encText;
  $url = "https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts";
  $is_post = true;
  $ch = curl_init();
  curl_setopt($ch, CURLOPT_URL, $url);
  curl_setopt($ch, CURLOPT_POST, $is_post);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
  curl_setopt($ch,CURLOPT_POSTFIELDS, $postvars);
  $headers = array();
  $headers[] = "X-NCP-APIGW-API-KEY-ID: ".$client_id;
  $headers[] = "X-NCP-APIGW-API-KEY: ".$client_secret;
  curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
  $response = curl_exec ($ch);
  $status_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
  echo "status_code:".$status_code."<br/>";
  curl_close ($ch);
  if($status_code == 200) {
    //echo $response;
    $fp = fopen("tts.mp3", "w+");
    fwrite($fp, $response);
    fclose($fp);
    echo "<a href='tts.mp3'>play TTS</a>";
  } else {
    echo "Error content:".$response;
  }
?>

// NAVER speech synthesis open API example
var express = require('express');
var app = express();
var client_id = 'YOUR_CLIENT_ID';
var client_secret = 'YOUR_CLIENT_SECRET';
var fs = require('fs');
app.get('/tts', function(req, res) {
  var api_url = 'https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts';
  var request = require('request');
  var options = {
    url: api_url,
    form: { speaker: 'nara', volume: '0', speed: '0', pitch: '0', text: 'Have a good day', format: 'mp3' },
    headers: { 'X-NCP-APIGW-API-KEY-ID': client_id, 'X-NCP-APIGW-API-KEY': client_secret },
  };
  var writeStream = fs.createWriteStream('./tts1.mp3');
  var _req = request.post(options).on('response', function(response) {
    console.log(response.statusCode); // 200
    console.log(response.headers['content-type']);
  });
  _req.pipe(writeStream); // Output to file
  _req.pipe(res); // Output to browser
});
app.listen(3000, function() {
  console.log('http://127.0.0.1:3000/tts app listening on port 3000!');
});

// NAVER speech synthesis open API example
import os
import sys
import urllib.request
client_id = "YOUR_CLIENT_ID"
client_secret = "YOUR_CLIENT_SECRET"
encText = urllib.parse.quote("Hello, NAVER")
data = "speaker=nara&volume=0&speed=0&pitch=0&format=mp3&text=" + encText;
url = "https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts"
request = urllib.request.Request(url)
request.add_header("X-NCP-APIGW-API-KEY-ID",client_id)
request.add_header("X-NCP-APIGW-API-KEY",client_secret)
response = urllib.request.urlopen(request, data=data.encode('utf-8'))
rescode = response.getcode()
if(rescode==200):
    print("save TTS mp3")
    response_body = response.read()
    with open('1111.mp3', 'wb') as f:
        f.write(response_body)
else:
    print("Error Code:" + rescode)

# -*- coding: utf-8 -*-
import os
import sys
import urllib
import urllib2
reload(sys)
sys.setdefaultencoding('utf-8')
client_id = "YOUR_CLIENT_ID" # application client ID value";
client_secret = "YOUR_CLIENT_SECRET" # application client secret value"
text = unicode("Hello, NAVER") # sentence for speech synthesis
speaker = "nara" # type of voice to use for speech synthesis
speed = "0" # speech playback speed
volume = "0" # speech volume
pitch = "0" # speech pitch
fmt = "mp3" # speech format
val = {
    "speaker": speaker,
    "volume": volume,
    "speed":speed,
    "pitch": pitch,
    "text":text,
    "format": fmt
}
data = urllib.urlencode(val)
url = "https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts"
headers = {
    "X-NCP-APIGW-API-KEY-ID" : client_id,
    "X-NCP-APIGW-API-KEY" : client_secret
}
request = urllib2.Request(url, data, headers)
response = urllib2.urlopen(request)
rescode = response.getcode()
if(rescode==200):
    print("TTS mp3 save")
    response_body = response.read()
    with open('1111.mp3', 'wb') as f:
        f.write(response_body)
else:
    print("Error Code:" + rescode)

// NAVER speech synthesis open API example
using System;
using System.Net;
using System.Text;
using System.IO;

namespace NaverAPI_Guide
{
    public class APIExamTTS
    {
        static void Main(string[] args)
        {
            string text = "Have a good day."; // Character value for speech synthesis
            string url = "https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts";
            HttpWebRequest request = (HttpWebRequest)WebRequest.Create(url);
            request.Headers.Add("X-NCP-APIGW-API-KEY-ID", "YOUR-CLIENT-ID");
            request.Headers.Add("X-NCP-APIGW-API-KEY", "YOUR-CLIENT-SECRET");
            request.Method = "POST";
            byte[] byteDataParams = Encoding.UTF8.GetBytes("speaker=nara&volume=0&speed=0&pitch=0&format=mp3&text=" + text);
            request.ContentType = "application/x-www-form-urlencoded";
            request.ContentLength = byteDataParams.Length;
            Stream st = request.GetRequestStream();
            st.Write(byteDataParams, 0, byteDataParams.Length);
            st.Close();
            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
            string status = response.StatusCode.ToString();
            Console.WriteLine("status="+ status);
            using (Stream output = File.OpenWrite("c:/tts.mp3"))
            using (Stream input = response.GetResponseStream())
            {
                input.CopyTo(output);
            }
            Console.WriteLine("c:/tts.mp3 was created");
        }
    }
}

curl "https://naveropenapi.apigw.ntruss.com/tts-premium/v1/tts" \
	-d "speaker=nara&volume=0&speed=0&pitch=0&format=mp3&text=Nice to meet you." \
	-H "Content-Type: application/x-www-form-urlencoded; charset=UTF-8" \
	-H "X-NCP-APIGW-API-KEY-ID: {Client ID value issued upon registering the application}" \
	-H "X-NCP-APIGW-API-KEY: {Client secret value issued upon registering the application}" -v \
		> out.mp3

Error codes