- Cloudmersive Documentation

Node.JS Python C# Java PHP Objective-C Ruby Apex C/C++ cURL Swift JavaScript Go

Run this command to install the SDK:

npm install cloudmersive-speech-api-client --save

Or add this snippet to your package.json:

  "dependencies": {
    "cloudmersive-speech-client": "^1.1.5"
  }

var CloudmersiveSpeechApiClient = require('cloudmersive-speech-api-client');
var defaultClient = CloudmersiveSpeechApiClient.ApiClient.instance;

// Configure API key authorization: Apikey
var Apikey = defaultClient.authentications['Apikey'];
Apikey.apiKey = 'YOUR API KEY';



var apiInstance = new CloudmersiveSpeechApiClient.RecognizeApi();

var speechFile = Buffer.from(fs.readFileSync("C:\\temp\\inputfile").buffer); // File | Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.


var callback = function(error, data, response) {
  if (error) {
    console.error(error);
  } else {
    console.log('API called successfully. Returned data: ' + data);
  }
};
apiInstance.recognizeFile(speechFile, callback);

Run this command to install the SDK:

pip install cloudmersive-voicerecognition-api-client

from __future__ import print_function
import time
import cloudmersive_voicerecognition_api_client
from cloudmersive_voicerecognition_api_client.rest import ApiException
from pprint import pprint

# Configure API key authorization: Apikey
configuration = cloudmersive_voicerecognition_api_client.Configuration()
configuration.api_key['Apikey'] = 'YOUR_API_KEY'



# create an instance of the API class
api_instance = cloudmersive_voicerecognition_api_client.RecognizeApi(cloudmersive_voicerecognition_api_client.ApiClient(configuration))
speech_file = '/path/to/file' # file | Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.

try:
    # Recognize audio input as text using machine learning
    api_response = api_instance.recognize_file(speech_file)
    pprint(api_response)
except ApiException as e:
    print("Exception when calling RecognizeApi->recognize_file: %s\n" % e)

.NET Framework | .NET Core

Run this command to install the SDK:

Install-Package Cloudmersive.APIClient.NET.Speech -Version 4.0.1

using System;
using System.Diagnostics;
using Cloudmersive.APIClient.NET.Speech.Api;
using Cloudmersive.APIClient.NET.Speech.Client;
using Cloudmersive.APIClient.NET.Speech.Model;

namespace Example
{
    public class RecognizeFileExample
    {
        public void main()
        {
            // Configure API key authorization: Apikey
            Configuration.Default.AddApiKey("Apikey", "YOUR_API_KEY");
            
            

            var apiInstance = new RecognizeApi();
            var speechFile = new System.IO.FileStream("C:\\temp\\inputfile", System.IO.FileMode.Open); // System.IO.Stream | Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.

            try
            {
                // Recognize audio input as text using machine learning
                SpeechRecognitionResult result = apiInstance.RecognizeFile(speechFile);
                Debug.WriteLine(result);
            }
            catch (Exception e)
            {
                Debug.Print("Exception when calling RecognizeApi.RecognizeFile: " + e.Message );
            }
        }
    }
}

using System;
using System.Diagnostics;
using Cloudmersive.APIClient.NETCore.Speech.Api;
using Cloudmersive.APIClient.NETCore.Speech.Client;
using Cloudmersive.APIClient.NETCore.Speech.Model;

namespace Example
{
    public class RecognizeFileExample
    {
        public void main()
        {
            // Configure API key authorization: Apikey
            Configuration.Default.AddApiKey("Apikey", "YOUR_API_KEY");
            
            

            var apiInstance = new RecognizeApi();
            var speechFile = new System.IO.FileStream("C:\\temp\\inputfile", System.IO.FileMode.Open); // System.IO.Stream | Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.

            try
            {
                // Recognize audio input as text using machine learning
                SpeechRecognitionResult result = apiInstance.RecognizeFile(speechFile);
                Debug.WriteLine(result);
            }
            catch (Exception e)
            {
                Debug.Print("Exception when calling RecognizeApi.RecognizeFile: " + e.Message );
            }
        }
    }
}

To install with Maven, add a reference to the repository in pom.xml:

And add a reference to the dependency in pom.xml:

To install with Gradle, add it in your root build.gradle at the end of repositories:

And add the dependency in build.gradle:

Run this command to install the SDK:

composer require cloudmersive/cloudmersive_voicerecognition_api_client

<?php
require_once(__DIR__ . '/vendor/autoload.php');

// Configure API key authorization: Apikey
$config = Swagger\Client\Configuration::getDefaultConfiguration()->setApiKey('Apikey', 'YOUR_API_KEY');



$apiInstance = new Swagger\Client\Api\RecognizeApi(
    
    
    new GuzzleHttp\Client(),
    $config
);
$speech_file = "/path/to/file"; // \SplFileObject | Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.

try {
    $result = $apiInstance->recognizeFile($speech_file);
    print_r($result);
} catch (Exception $e) {
    echo 'Exception when calling RecognizeApi->recognizeFile: ', $e->getMessage(), PHP_EOL;
}
?>

Add the Objective-C client to your Podfile:

pod 'CloudmersiveSpeechApiClient', '~> 1.0'

CMDefaultConfiguration *apiConfig = [CMDefaultConfiguration sharedConfig];

// Configure API key authorization: (authentication scheme: Apikey)
[apiConfig setApiKey:@"YOUR_API_KEY" forApiKeyIdentifier:@"Apikey"];




NSURL* speechFile = [NSURL fileURLWithPath:@"/path/to/file"]; // Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.

CMRecognizeApi*apiInstance = [[CMRecognizeApi alloc] init];

// Recognize audio input as text using machine learning
[apiInstance recognizeFileWithSpeechFile:speechFile
          completionHandler: ^(CMSpeechRecognitionResult* output, NSError* error) {
                        if (output) {
                            NSLog(@"%@", output);
                        }
                        if (error) {
                            NSLog(@"Error calling CMRecognizeApi->recognizeFile: %@", error);
                        }
                    }];

Add the Ruby client to your Gemfile:

gem install cloudmersive-voice-recognition-api-client

# load the gem
require 'cloudmersive-voice-recognition-api-client'
# setup authorization
CloudmersiveVoiceRecognitionApiClient.configure do |config|
  # Configure API key authorization: Apikey
  config.api_key['Apikey'] = 'YOUR API KEY'
  # Uncomment the following line to set a prefix for the API key, e.g. 'Bearer' (defaults to nil)
  #config.api_key_prefix['Apikey'] = 'Bearer'
end

api_instance = CloudmersiveVoiceRecognitionApiClient::RecognizeApi.new

speech_file = File.new('/path/to/inputfile') # File | Speech file to perform the operation on.  Common file formats such as WAV, MP3 are supported.


begin
  #Recognize audio input as text using machine learning
  result = api_instance.recognize_file(speech_file)
  p result
rescue CloudmersiveVoiceRecognitionApiClient::ApiError => e
  puts "Exception when calling RecognizeApi->recognize_file: #{e}"
end

Download and copy the /client folder into your Apex project:

Download Apex Client

Install libcurl in your C/C++ project:

libcurl/7.75.0

CURL *curl;
CURLcode res;
curl = curl_easy_init();
if(curl) {
     curl_easy_setopt(curl, CURLOPT_CUSTOMREQUEST, "POST");
     curl_easy_setopt(curl, CURLOPT_URL, "https://api.cloudmersive.com/speech/recognize/file");
     curl_easy_setopt(curl, CURLOPT_FOLLOWLOCATION, 1L);
     curl_easy_setopt(curl, CURLOPT_DEFAULT_PROTOCOL, "https");
     struct curl_slist *headers = NULL;
     headers = curl_slist_append(headers, "Content-Type: multipart/form-data");
     headers = curl_slist_append(headers, "Apikey: YOUR-API-KEY-HERE");
     curl_easy_setopt(curl, CURLOPT_HTTPHEADER, headers);
     curl_mime *mime;
     curl_mimepart *part;
     mime = curl_mime_init(curl);
     part = curl_mime_addpart(mime);
     curl_mime_name(part, "speechFile");
     curl_mime_filedata(part, "/path/to/file");
     curl_easy_setopt(curl, CURLOPT_MIMEPOST, mime);
     res = curl_easy_perform(curl);
     curl_mime_free(mime);
}
curl_easy_cleanup(curl);

curl --location --request POST 'https://api.cloudmersive.com/speech/recognize/file' \
--header 'Content-Type: multipart/form-data' \
--header 'Apikey: YOUR-API-KEY-HERE' \
--form 'speechFile=@"/path/to/file"'

import Foundation
#if canImport(FoundationNetworking)
import FoundationNetworking
#endif

var semaphore = DispatchSemaphore (value: 0)

let parameters = [
     [
          "key": "speechFile",
          "src": "/path/to/file",
          "type": "file"
     ]] as [[String : Any]]

let boundary = "Boundary-\(UUID().uuidString)"
var body = ""
var error: Error? = nil
for param in parameters {
     if param["disabled"] == nil {
          let paramName = param["key"]!
          body += "--\(boundary)\r\n"
          body += "Content-Disposition:form-data; name=\"\(paramName)\""
          if param["contentType"] != nil {
               body += "\r\nContent-Type: \(param["contentType"] as! String)"
          }
          let paramType = param["type"] as! String
          if paramType == "text" {
               let paramValue = param["value"] as! String
               body += "\r\n\r\n\(paramValue)\r\n"
          } else {
               let paramSrc = param["src"] as! String
               let fileData = try NSData(contentsOfFile:paramSrc, options:[]) as Data
               let fileContent = String(data: fileData, encoding: .utf8)!
               body += "; filename=\"\(paramSrc)\"\r\n"
                 + "Content-Type: \"content-type header\"\r\n\r\n\(fileContent)\r\n"
          }
     }
}
body += "--\(boundary)--\r\n";
let postData = body.data(using: .utf8)

var request = URLRequest(url: URL(string: "https://api.cloudmersive.com/speech/recognize/file")!,timeoutInterval: Double.infinity)
request.addValue("multipart/form-data", forHTTPHeaderField: "Content-Type")
request.addValue("YOUR-API-KEY-HERE", forHTTPHeaderField: "Apikey")
request.addValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")

request.httpMethod = "POST"
request.httpBody = postData

let task = URLSession.shared.dataTask(with: request) { data, response, error in 
     guard let data = data else {
          print(String(describing: error))
          semaphore.signal()
          return
     }
     print(String(data: data, encoding: .utf8)!)
     semaphore.signal()
}

task.resume()
semaphore.wait()

XHR | jQuery

This code snippet uses the built-in JavaScript XHR request capability

var data = new FormData();
data.append("speechFile", fileInput.files[0], "file");
 
var xhr = new XMLHttpRequest();
xhr.withCredentials = true;

xhr.addEventListener("readystatechange", function() {
     if(this.readyState === 4) {
          console.log(this.responseText);
     }
});

xhr.open("POST", "https://api.cloudmersive.com/speech/recognize/file");

xhr.setRequestHeader("Apikey", "YOUR-API-KEY-HERE");

xhr.send(data);

var form = new FormData();
form.append("speechFile", fileInput.files[0], "file");

var settings = {
     "url": "https://api.cloudmersive.com/speech/recognize/file",
     "method": "POST",
     "timeout": 0,
     "headers": {
          "Content-Type": "multipart/form-data",
          "Apikey": "YOUR-API-KEY-HERE"
     },
     "processData": false,
     "mimeType": "multipart/form-data",
     "contentType": false,
     "data": form
};

$.ajax(settings).done(function (response) {
     console.log(response);
});

package main

import (
     "fmt"
     "bytes"
     "mime/multipart"
     "os"
     "path/filepath"
     "io"
     "net/http"
     "io/ioutil"
)

func main() {

     url := "https://api.cloudmersive.com/speech/recognize/file"
     method := "POST"

     payload := &bytes.Buffer{}
     writer := multipart.NewWriter(payload)
     file, errFile1 := os.Open("/path/to/file")
     defer file.Close()
     part1,
         errFile1 := writer.CreateFormFile("speechFile",filepath.Base("/path/to/file"))
     _, errFile1 = io.Copy(part1, file)
     if errFile1 != nil {
          fmt.Println(errFile1)
          return
     }
     err := writer.Close()
     if err != nil {
          fmt.Println(err)
          return
     }


     client := &http.Client {
     }
     req, err := http.NewRequest(method, url, payload)

     if err != nil {
          fmt.Println(err)
          return
     }
     req.Header.Add("Content-Type", "multipart/form-data")
     req.Header.Add("Apikey", "YOUR-API-KEY-HERE")

     req.Header.Set("Content-Type", writer.FormDataContentType())
     res, err := client.Do(req)
     if err != nil {
          fmt.Println(err)
          return
     }
     defer res.Body.Close()

     body, err := ioutil.ReadAll(res.Body)
     if err != nil {
          fmt.Println(err)
          return
     }
     fmt.Println(string(body))
}

Walkthrough Video