stt (Speech-To-Text)

개요

CLOVA Speech Recognition REST API (이하 CSR REST API)는 HTTP 기반의 REST API로 제공하는 음성인식 API입니다. 인식에 사용할 언어와 음성 데이터를 입력받고 그에 맞는 인식 결과를 텍스트로 반환합니다.
입력 음성 데이터 포맷은 mp3, aac, ac3, ogg, flac, wav을 지원합니다.

요청

요청 파라미터

요청 헤더

요청 바디

응답

응답 바디

예시

요청 예시

[HTTP Request URL]
https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang=Kor

[HTTP Request Body]
--- binary sound data ---

응답 예시

{
  "text": "안녕하세요"
}

API 예제

다음은 각 언어별 CSR API 구현 예제입니다.

import java.io.*;
import java.net.HttpURLConnection;
import java.net.URL;

public class Main {

    public static void main(String[] args) {
        String clientId = "YOUR_CLIENT_ID";             // Application Client ID";
        String clientSecret = "YOUR_CLIENT_SECRET";     // Application Client Secret";

        try {
            String imgFile = "음성 파일 경로";
            File voiceFile = new File(imgFile);

            String language = "Kor";        // 언어 코드 ( Kor, Jpn, Eng, Chn )
            String apiURL = "https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang=" + language;
            URL url = new URL(apiURL);

            HttpURLConnection conn = (HttpURLConnection)url.openConnection();
            conn.setUseCaches(false);
            conn.setDoOutput(true);
            conn.setDoInput(true);
            conn.setRequestProperty("Content-Type", "application/octet-stream");
            conn.setRequestProperty("X-NCP-APIGW-API-KEY-ID", clientId);
            conn.setRequestProperty("X-NCP-APIGW-API-KEY", clientSecret);

            OutputStream outputStream = conn.getOutputStream();
            FileInputStream inputStream = new FileInputStream(voiceFile);
            byte[] buffer = new byte[4096];
            int bytesRead = -1;
            while ((bytesRead = inputStream.read(buffer)) != -1) {
                outputStream.write(buffer, 0, bytesRead);
            }
            outputStream.flush();
            inputStream.close();
            BufferedReader br = null;
            int responseCode = conn.getResponseCode();
            if(responseCode == 200) { // 정상 호출
                br = new BufferedReader(new InputStreamReader(conn.getInputStream()));
            } else {  // 오류 발생
                System.out.println("error!!!!!!! responseCode= " + responseCode);
                br = new BufferedReader(new InputStreamReader(conn.getInputStream()));
            }
            String inputLine;

            if(br != null) {
                StringBuffer response = new StringBuffer();
                while ((inputLine = br.readLine()) != null) {
                    response.append(inputLine);
                }
                br.close();
                System.out.println(response.toString());
            } else {
                System.out.println("error !!!");
            }
        } catch (Exception e) {
            System.out.println(e);
        }
    }
}

<?php

$curl = curl_init();
$file_path = "음성 파일 경로";

$lang = "Kor";  // 언어 코드 ( Kor, Jpn, Eng, Chn )
$client_id = "YOUR_CLIENT_KEY";
$client_secret = "YOUR_CLIENT_SECRET";

curl_setopt_array($curl, array(
  CURLOPT_URL => "https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang=".$lang,
  CURLOPT_RETURNTRANSFER => 1,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_POST => 1,
  CURLOPT_POSTFIELDS => file_get_contents($file_path),
  CURLOPT_HTTPHEADER => array(
    "Content-Type: application/octet-stream",
    "X-NCP-APIGW-API-KEY-ID: ".$client_id,
    "X-NCP-APIGW-API-KEY: ".$client_secret
  ),
));

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

?>

const fs = require('fs');
const request = require('request');

const clientId = 'YOUR_CLIENT_ID';
const clientSecret = 'YOUR_CLIENT_SECRET';

// language => 언어 코드 ( Kor, Jpn, Eng, Chn )
function stt(language, filePath) {
    const url = `https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang=${language}`;
    const requestConfig = {
        url: url,
        method: 'POST',
        headers: {
            'Content-Type': 'application/octet-stream',
            'X-NCP-APIGW-API-KEY-ID': clientId,
            'X-NCP-APIGW-API-KEY': clientSecret
        },
        body: fs.createReadStream(filePath)
    };

    request(requestConfig, (err, response, body) => {
        if (err) {
            console.log(err);
            return;
        }

        console.log(response.statusCode);
        console.log(body);
    });
}

stt('Kor', '음성 파일 경로 (ex: ./test.wav)');

import sys
import requests
client_id = "YOUR_CLIENT_ID"
client_secret = "YOUR_CLIENT_SECRET"
lang = "Kor" # 언어 코드 ( Kor, Jpn, Eng, Chn )
url = "https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang=" + lang
data = open('음성 파일 경로', 'rb')
headers = {
    "X-NCP-APIGW-API-KEY-ID": client_id,
    "X-NCP-APIGW-API-KEY": client_secret,
    "Content-Type": "application/octet-stream"
}
response = requests.post(url,  data=data, headers=headers)
rescode = response.status_code
if(rescode == 200):
    print (response.text)
else:
    print("Error : " + response.text)

using System;
using System.Net;
using System.Text;
using System.IO;
using System.Collections.Generic;
using System.Collections.Specialized;

namespace NaverAPI_Guide
{
    class APIExamSTT
    {
        static void Main(string[] args)
        {
            string FilePath = "YOUR_FILE_NAME";
            FileStream fs = new FileStream(FilePath, FileMode.Open, FileAccess.Read);
            byte[] fileData = new byte[fs.Length];
            fs.Read(fileData, 0, fileData.Length);
            fs.Close();

            string lang = "Kor";    // 언어 코드 ( Kor, Jpn, Eng, Chn )
            string url = $"https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang={lang}";
            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";
            request.ContentType = "application/octet-stream";
            request.ContentLength = fileData.Length;
            using (Stream requestStream = request.GetRequestStream())
            {
                requestStream.Write(fileData, 0, fileData.Length);
                requestStream.Close();
            }
            HttpWebResponse response = (HttpWebResponse)request.GetResponse();
            Stream stream = response.GetResponseStream();
            StreamReader reader = new StreamReader(stream, Encoding.UTF8);
            string text = reader.ReadToEnd();
            stream.Close();
            response.Close();
            reader.Close();
            Console.WriteLine(text);
        }
    }
}

오류 코드