STT(Speech-to-Text)のユースケース

Classic/VPC環境で利用できます。

CLOVA Speech Recognition(CSR) STT(Speech-to-Text) APIを使用するユースケースを紹介します。

STT (Speech-to-Text) API

音声認識に使用する言語と音声データの入力を受け、その認識結果をテキストに変換する STT(Speech-to-Text) APIのユースケースを説明します。

Java

Javaベースの STT(Speech-to-Text) APIのサンプルコードは次の通りです。

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 = "音声ファイルのパス";
            File voiceFile = new File(imgFile);

            String language = "Kor";        // 言語コード(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) { // 正常な呼び出し
                br = new BufferedReader(new InputStreamReader(conn.getInputStream()));
            } else {  // エラー発生
                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);
        }
    }
}

Python

Pythonベースの STT(Speech-to-Text) APIのサンプルコードは次の通りです。

import sys
import requests
client_id = "YOUR_CLIENT_ID"
client_secret = "YOUR_CLIENT_SECRET"
lang = "Kor" # 言語コード(Kor、Jpn、Eng、Chn)
url = "https://naveropenapi.apigw.ntruss.com/recog/v1/stt?lang=" + lang
data = open('言語ファイルのパス', '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)

PHP

PHPベースの STT(Speech-to-Text) APIのサンプルコードは次の通りです。

<?php

$curl = curl_init();
$file_path = "音声ファイルのパス";

$lang = "Kor";  // 言語コード(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;
}

?>

JavaScript

JavaScriptベースの STT(Speech-to-Text) APIのサンプルコードは次の通りです。

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

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

// language => 言語コード(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', '音声ファイルのパス(例: ./test.wav)');

C#

C# ベースの STT(Speech-to-Text) APIのサンプルコードは次の通りです。

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";    // 言語コード(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);
        }
    }
}