Technology Post: How to apply AI natively to Android system

[51CTO.com Quick Translation] Compared to reading the content of the message, it is undoubtedly more convenient to listen to the content directly. Integrating Watson's text-to-speech function into existing Android native applications can help everyone easily achieve this goal.

In today’s article, we will explore how to integrate Watson text-to-speech (TTS) functionality into existing Android native mobile applications.

The first time I tried to submit my own Watbot to GitHub, the experience was simply "dreamlike". Watbot is an Android chatbot built using Watson conversational services. It mainly helps college students learn how to create services on Bluemix and run applications through simulators or physical devices in 30 minutes to achieve learning goals. However, in my opinion, it is obviously more interesting to integrate other Watson services into the application, especially Watson text-to-speech services. Compared with reading the content of the message, it is undoubtedly more convenient to directly listen to its content.

“Text-to-speech converts written text into natural-sounding audio. You can customize and control the pronunciation of specific words, providing your audience with seamless voice interactions for interactive toys for children, automated call center interactions, and hands-free navigation systems.”

Hear messages in different voices

• Create a Watson text-to-speech (TTS) service on Bluemix.
• Go to the Service Credentials tab and click View Credentials.

 curl -X GET -u "{username}":"{password}"
 "https://stream.watsonplatform.net/text-to-speech/api/v1/voices"

The above delegate is used to retrieve a list of all voices available for the service. Information provided includes the voice name, language, gender, etc. To get information about a specific voice, use the "Get a voice" method:

 {
 "voices": [
 {
      "name": "pt-BR_IsabelaVoice",
 "language": "pt-BR",
 "customizable": true,
 "gender": "female",
      "url": "https://stream-s.watsonplatform.net/text-to-speech/api/v1/voices/pt-BR_IsabelaVoice",
 "supported_features": {
        "voice_transformation": false,
        "custom_pronunciation": true
 },
      "description": "Isabela: Brazilian Portuguese (português brasileiro) female voice."
 },
 {
      "name": "es-US_SofiaVoice",
 "language": "es-US",
 "customizable": true,
 "gender": "female",
      "url": "https://stream-s.watsonplatform.net/text-to-speech/api/v1/voices/es-US_SofiaVoice",
 "supported_features": {
        "voice_transformation": false,
        "custom_pronunciation": true
 },
      "description": "Sofia: North American Spanish (español norteamericano) female voice."
 },
 {
      "name": "en-GB_KateVoice",
 "language": "en-GB",
 "customizable": true,
 "gender": "female",
      "url": "https://stream-s.watsonplatform.net/text-to-speech/api/v1/voices/en-GB_KateVoice",
 "supported_features": {
        "voice_transformation": false,
        "custom_pronunciation": true
 },
      "description": "Kate: British English female voice."
 },
 {
      "name": "en-US_LisaVoice",
 "language": "en-US",
 "customizable": true,
 "gender": "female",
      "url": "https://stream-s.watsonplatform.net/text-to-speech/api/v1/voices/en-US_LisaVoice",
 "supported_features": {
        "voice_transformation": true,
        "custom_pronunciation": true
 },
      "description": "Lisa: American English female voice."
 },
 {
      "name": "ja-JP_EmiVoice",
 "language": "ja-JP",
 "customizable": true,
 "gender": "female",
      "url": "https://stream-s.watsonplatform.net/text-to-speech/api/v1/voices/ja-JP_EmiVoice",
 "supported_features": {
        "voice_transformation": false,
        "custom_pronunciation": true
 },
      "description": "Emi: Japanese female voice."
 },
 . . .
 ]
 }

Interested friends can click here to refer to the API reference on Watson Developer Cloud to learn more about TTS API calls.

How do I integrate TTS into my Android native app?

This requires us to add the TTS Gradle entry to our build.gradle (app) file:

 compile 'com.ibm.watson.developer_cloud:text-to-speech:3.5.3'
 compile 'com.ibm.watson.developer_cloud:android-sdk:0.2.1'

Add the following code to your MainActivity.java file and replace the username and password placeholders with your actual TTS service credentials. In addition, after adding the following code, tap a message to convert text to speech:

 recyclerView.addOnItemTouchListener(new RecyclerTouchListener(getApplicationContext(), recyclerView, new ClickListener() {
 @Override
 public void onClick(View view, final int position) {
  Thread thread = new Thread(new Runnable() {
 public void run() {
 Message audioMessage;
 try {
 audioMessage = (Message) messageArrayList.get(position);
 streamPlayer = new StreamPlayer();
     if (audioMessage != null && !audioMessage.getMessage().isEmpty())
     //Change the Voice format and choose from the available choices
      streamPlayer.playStream(service.synthesize(audioMessage.getMessage(), Voice.EN_LISA).execute());
 else
      streamPlayer.playStream(service.synthesize("No Text Specified", Voice.EN_LISA).execute());
 } catch (Exception e) {
 e.printStackTrace();
 }
 }
 });
 thread.start();
 }
 @Override
 public void onLongClick(View view, int position) {
 }
 }));

 git clone https://github.com/VidyasagarMSC/WatBot.git

[Translated by 51CTO. Please indicate the original translator and source as 51CTO.com when reprinting on partner sites]