Android SDK

When integrating multiple SDKs at the same time, "so" file conflicts may occur. Please use decompression software (such as 7-zip) to decompress the aar package and delete conflicting "so" files.
Supports Android 5.0 and above versions.
Before using the SDK, please read the Interface Protocol first. For details, refer to Cloud API.

1 Integration Steps

1.1 Add aar Dependency

Place asr-sdk.aar in the project's libs directory and modify the build.gradle of the app module to add the aar file and okhttp as dependencies.

implementation fileTree(dir: "libs", include: ["*.jar","*.aar"])
implementation 'com.squareup.okhttp3:okhttp:4.10.0'//Here we add okhttp. If the project is relatively old, you can use version 3.14.2.
implementation 'org.java-websocket:Java-WebSocket:1.5.3'
implementation 'com.google.code.gson:gson:2.10.1'

If you are using a 32-bit SDK, you need to add the following code:

defaultConfig {
    //Add the following code
    externalNativeBuild {
        ndk {
            abiFilters  "armeabi-v7a" 
        }
    }
}

Modify the AndroidManifest.xml file

<!--Recording permission must be added-->
<uses-permission android:name="android.permission.RECORD_AUDIO" />
<!--Network permission must be added-->
<uses-permission android:name="android.permission.INTERNET" />

1.3 Invocation Steps/Sample Code

1.3.1 Obtain Recording Permissions

registerForActivityResult(new ActivityResultContracts.RequestPermission(), success -> {
        String msg = "Acquiring recording permission" + (success ? "success" : "error");
        tip(msg);
}).launch(Manifest.permission.RECORD_AUDIO);

1.3.2 Create a Speech Recognition Class

private Recognizer recognizer;//Short Speech Recognition

private BaseAsr getAsr() {
    if (type == Asr.Type.RECOGNIZER) {
         return recognizer;
        }
         return transcriber;
    }

//Initialize the SDK in onCreate
transcriber = Transcriber.getInstance(activity);
recognizer = Recognizer.getInstance(activity);

1.3.3 Initialize the Microphone

getAsr().initRecorder();//Initialize the microphone when creating the recognition class

1.3.4 Set Up Callbacks

(1) Callback Parameter Description

Name	Type	Description	Return Parameters
onStart	Function	Callback method when the engine connection starts	String type of the current task ID
onResult	Function	Callback method for engine result content	String type of result data
onIntermediateResult	Function	Callback method for engine intermediate results	String type of intermediate result data
onWarning	Function	Callback method for engine result warnings	Task ID and Errors type of status code
onError	Function	Callback method for engine result errors	Task ID and Errors type of status code
onGetAudio	Function	Callback method for engine recognition audio data	byte[] type of audio data
onStop	Function	Callback method when the engine ends	None

(2) Parameter Example

getAsr().setListener(new Asr.Listener() {
   @Override
   public void onStart(String taskId) {   
   }

   @Override
   public void onError(String taskId, Errors.Err err) {
   }

   @Override
   public void onResult(String msg) {
   }

   @Override
   public void onIntermediateResult(String msg) {
   }

   @Override
   public void onWarning(String taskId, Errors.Err err) {
   }

   @Override
   public void onGetAudio(byte[] data) {
   }

   @Override
   public void onStop() {
   }
});

1.3.5 Activate Permissions

(1) Configuration Parameters

Name	Type	Description	Default Value
onSuccess	Function	Callback method for successful initialization	None
onFail	Function	Callback method for failed initialization	None

(2) Parameter Example

@NonNull
private Asr.InitListener getInitListener() {
    return new Asr.InitListener() {
        @Override
        public void onSuccess() {
            tip("Initialization successful");
        }
        @Override
        public void onFail(Errors.Err err) {
          
        }
    };
}

Online Authentication

getAsr().initOnline(appId, appSecret, getInitListener());

1.3.6 Set Parameters

Interface Parameter Description

Parameter	Type	Required	Description	Default Value
lang_type	String	Yes	Language option	Required
format	String	No	Audio encoding format	mp3
sample_rate	Integer	No	Audio sampling rate	16000
enable_intermediate_result	Boolean	No	Whether to return intermediate recognition results	true
enable_punctuation_prediction	Boolean	No	Whether to add punctuation in post-processing	true
enable_inverse_text_normalization	Boolean	No	Whether to perform ITN in post-processing	true
max_sentence_silence	Integer	No	Speech sentence breaking detection threshold. Silence longer than this threshold is considered as a sentence break. The valid parameter range is 200～1200. Unit: Milliseconds	450
enable_words	Boolean	No	Whether to enable returning word information	false
enable_modal_particle_filter	Boolean	No	Whether to enable modal particle filtering	true
hotwords_id	String	No	Hotwords ID	None
hotwords_weight	Float	No	Hotwords weight, the range is [0.1, 1.0]	0.4
correction_words_id	String	No	Forced correction vocabulary ID Supports multiple IDs, separated by a vertical bar. All indicates using all IDs.	None
forbidden_words_id	String	No	Forbidden words ID Supports multiple IDs, separated by a vertical bar. All indicates using all IDs.	None

//4.1 Set recognition parameters
JsonObject params = new JsonObject();
params.addProperty("lang_type", langType);//The language type to be recognized (Required)
params.addProperty("sample_rate", 16000);//Audio sampling rate
params.addProperty("enable_intermediate_result", true);//Whether to return intermediate recognition results
params.addProperty("enable_punctuation_prediction", true);//Whether to add punctuation in post-processing
params.addProperty("enable_inverse_text_normalization", true);//Whether to perform ITN in post-processing
params.addProperty("max_sentence_silence", 800);//Speech sentence breaking detection threshold. Silence longer than this threshold is considered as a sentence break. The valid parameter range is 200〜2000(ms), and the default value is 800ms
params.addProperty("enable_words", true);//Whether to enable returning word information

1.3.7 Start/Stop Recognition

Name	Type	Description	Default Value
autoRecording	boolean	Microphone initialized as true	true
onlineAsr	boolean	True for Cloud API, false for On-Device	true
params	JsonObject	Parameter json	None

Start Recognition (SDK Built-in Mic)

getAsr().start(autoRecording, onlineAsr, params);

Start Recognition (SDK External Audio Transfer)

//1. The method of external recording transmission
//1.1 start
getAsr().start(false, onlineAsr, params);
//1.2 feed audio
getAsr().feed(data, false);
//1.3 end
getAsr().stop();

//2. The method of transmitting audio by reading files externally
//2.1 start
getAsr().start(false, onlineAsr, params);
//2.2 feed audio
getAsr().feed(data, false);
//2.3 end(The ending data requires the transmission of tail packet data)
getAsr().feed(data, true);

Start Recognition (File Recognition Method)

getAsr().startPath(onlineAsr,params,"Local audio address");
//No need to manually stop, automatically stops and calls back the onstop method when the file transfer is complete.

Force Sentence Ending

getAsr().sentenceEnd();

Customize Speaker Number

getAsr().speakerStart("speaker_name")

Stop Recognition

getAsr().stop();

Save Recognition Audio

getAsr().setSaveAudio(true);
//By default, saving is not enabled. Set to true to save, with the path being context.getExternalFilesDir(null)/asrCache

2 SDK Download

Android SDK

Android Demo

On this page