/*
* Copyright (C) 2009 Google Inc.
*
* Licensed under the Apache License, Version 2.0 (the "License"); you may not
* use this file except in compliance with the License. You may obtain a copy of
* the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
* WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
* License for the specific language governing permissions and limitations under
* the License.
*/
package android.speech.tts;
import android.speech.tts.ITts;
import android.speech.tts.ITtsCallback;
import android.content.ComponentName;
import android.content.Context;
import android.content.Intent;
import android.content.ServiceConnection;
import android.media.AudioManager;
import android.os.IBinder;
import android.os.RemoteException;
import android.util.Log;
import java.util.HashMap;
import java.util.Locale;
/**
*
* Synthesizes speech from text for immediate playback or to create a sound file.
*
*/
//TODO complete javadoc + add links to constants
public class TextToSpeech {
/**
* Denotes a successful operation.
*/
public static final int TTS_SUCCESS = 0;
/**
* Denotes a generic operation failure.
*/
public static final int TTS_ERROR = -1;
/**
* Queue mode where all entries in the playback queue (media to be played
* and text to be synthesized) are dropped and replaced by the new entry.
*/
public static final int TTS_QUEUE_FLUSH = 0;
/**
* Queue mode where the new entry is added at the end of the playback queue.
*/
public static final int TTS_QUEUE_ADD = 1;
/**
* Denotes the language is available exactly as specified by the locale
*/
public static final int TTS_LANG_COUNTRY_VAR_AVAILABLE = 2;
/**
* Denotes the language is available for the language and country specified
* by the locale, but not the variant.
*/
public static final int TTS_LANG_COUNTRY_AVAILABLE = 1;
/**
* Denotes the language is available for the language by the locale,
* but not the country and variant.
*/
public static final int TTS_LANG_AVAILABLE = 0;
/**
* Denotes the language data is missing.
*/
public static final int TTS_LANG_MISSING_DATA = -1;
/**
* Denotes the language is not supported by the current TTS engine.
*/
public static final int TTS_LANG_NOT_SUPPORTED = -2;
/**
* Called when the TTS has initialized.
*
* The InitListener must implement the onInit function. onInit is passed a
* status code indicating the result of the TTS initialization.
*/
public interface OnInitListener {
public void onInit(int status);
}
/**
* Called when the TTS has completed saying something that has an utterance ID set.
*
* The OnUtteranceCompletedListener must implement the onUtteranceCompleted function.
* onUtteranceCompleted is passed a String that is the utteranceId given in
* the original speak call.
*/
public interface OnUtteranceCompletedListener {
public void onUtteranceCompleted(String utteranceId);
}
/**
* Internal constants for the TTS functionality
*
*/
public class Engine {
// default values for a TTS engine when settings are not found in the provider
/**
* {@hide}
*/
public static final int FALLBACK_TTS_DEFAULT_RATE = 100; // 1x
/**
* {@hide}
*/
public static final int FALLBACK_TTS_DEFAULT_PITCH = 100;// 1x
/**
* {@hide}
*/
public static final int FALLBACK_TTS_USE_DEFAULTS = 0; // false
/**
* {@hide}
*/
public static final String FALLBACK_TTS_DEFAULT_SYNTH = "com.svox.pico";
// default values for rendering
public static final int TTS_DEFAULT_STREAM = AudioManager.STREAM_MUSIC;
// return codes for a TTS engine's check data activity
/**
* Indicates success when checking the installation status of the resources used by the
* text-to-speech engine with the android.intent.action.CHECK_TTS_DATA intent.
*/
public static final int CHECK_VOICE_DATA_PASS = 1;
/**
* Indicates failure when checking the installation status of the resources used by the
* text-to-speech engine with the android.intent.action.CHECK_TTS_DATA intent.
*/
public static final int CHECK_VOICE_DATA_FAIL = 0;
/**
* Indicates erroneous data when checking the installation status of the resources used by
* the text-to-speech engine with the android.intent.action.CHECK_TTS_DATA intent.
*/
public static final int CHECK_VOICE_DATA_BAD_DATA = -1;
/**
* Indicates missing resources when checking the installation status of the resources used
* by the text-to-speech engine with the android.intent.action.CHECK_TTS_DATA intent.
*/
public static final int CHECK_VOICE_DATA_MISSING_DATA = -2;
/**
* Indicates missing storage volume when checking the installation status of the resources
* used by the text-to-speech engine with the android.intent.action.CHECK_TTS_DATA intent.
*/
public static final int CHECK_VOICE_DATA_MISSING_VOLUME = -3;
// return codes for a TTS engine's check data activity
/**
* Extra information received with the android.intent.action.CHECK_TTS_DATA intent where
* the text-to-speech engine specifies the path to its resources.
*/
public static final String VOICE_DATA_ROOT_DIRECTORY = "dataRoot";
/**
* Extra information received with the android.intent.action.CHECK_TTS_DATA intent where
* the text-to-speech engine specifies the file names of its resources under the
* resource path.
*/
public static final String VOICE_DATA_FILES = "dataFiles";
/**
* Extra information received with the android.intent.action.CHECK_TTS_DATA intent where
* the text-to-speech engine specifies the locale associated with each resource file.
*/
public static final String VOICE_DATA_FILES_INFO = "dataFilesInfo";
// keys for the parameters passed with speak commands. Hidden keys are used internally
// to maintain engine state for each TextToSpeech instance.
/**
* {@hide}
*/
public static final String TTS_KEY_PARAM_RATE = "rate";
/**
* {@hide}
*/
public static final String TTS_KEY_PARAM_LANGUAGE = "language";
/**
* {@hide}
*/
public static final String TTS_KEY_PARAM_COUNTRY = "country";
/**
* {@hide}
*/
public static final String TTS_KEY_PARAM_VARIANT = "variant";
/**
* Parameter key to specify the audio stream type to be used when speaking text
* or playing back a file.
*/
public static final String TTS_KEY_PARAM_STREAM = "streamType";
/**
* Parameter key to identify an utterance in the completion listener after text has been
* spoken, a file has been played back or a silence duration has elapsed.
*/
public static final String TTS_KEY_PARAM_UTTERANCE_ID = "utteranceId";
// key positions in the array of cached parameters
/**
* {@hide}
*/
protected static final int TTS_PARAM_POSITION_RATE = 0;
/**
* {@hide}
*/
protected static final int TTS_PARAM_POSITION_LANGUAGE = 2;
/**
* {@hide}
*/
protected static final int TTS_PARAM_POSITION_COUNTRY = 4;
/**
* {@hide}
*/
protected static final int TTS_PARAM_POSITION_VARIANT = 6;
/**
* {@hide}
*/
protected static final int TTS_PARAM_POSITION_STREAM = 8;
/**
* {@hide}
*/
protected static final int TTS_PARAM_POSITION_UTTERANCE_ID = 10;
/**
* {@hide}
*/
protected static final int TTS_NB_CACHED_PARAMS = 6;
}
/**
* Connection needed for the TTS.
*/
private ServiceConnection mServiceConnection;
private ITts mITts = null;
private ITtsCallback mITtscallback = null;
private Context mContext = null;
private String mPackageName = "";
private OnInitListener mInitListener = null;
private boolean mStarted = false;
private final Object mStartLock = new Object();
/**
* Used to store the cached parameters sent along with each synthesis request to the
* TTS service.
*/
private String[] mCachedParams;
/**
* The constructor for the TTS.
*
* @param context
* The context
* @param listener
* The InitListener that will be called when the TTS has
* initialized successfully.
*/
public TextToSpeech(Context context, OnInitListener listener) {
mContext = context;
mPackageName = mContext.getPackageName();
mInitListener = listener;
mCachedParams = new String[2*Engine.TTS_NB_CACHED_PARAMS]; // store key and value
mCachedParams[Engine.TTS_PARAM_POSITION_RATE] = Engine.TTS_KEY_PARAM_RATE;
mCachedParams[Engine.TTS_PARAM_POSITION_LANGUAGE] = Engine.TTS_KEY_PARAM_LANGUAGE;
mCachedParams[Engine.TTS_PARAM_POSITION_COUNTRY] = Engine.TTS_KEY_PARAM_COUNTRY;
mCachedParams[Engine.TTS_PARAM_POSITION_VARIANT] = Engine.TTS_KEY_PARAM_VARIANT;
mCachedParams[Engine.TTS_PARAM_POSITION_STREAM] = Engine.TTS_KEY_PARAM_STREAM;
mCachedParams[Engine.TTS_PARAM_POSITION_UTTERANCE_ID] = Engine.TTS_KEY_PARAM_UTTERANCE_ID;
mCachedParams[Engine.TTS_PARAM_POSITION_RATE + 1] =
String.valueOf(Engine.FALLBACK_TTS_DEFAULT_RATE);
// initialize the language cached parameters with the current Locale
Locale defaultLoc = Locale.getDefault();
mCachedParams[Engine.TTS_PARAM_POSITION_LANGUAGE + 1] = defaultLoc.getISO3Language();
mCachedParams[Engine.TTS_PARAM_POSITION_COUNTRY + 1] = defaultLoc.getISO3Country();
mCachedParams[Engine.TTS_PARAM_POSITION_VARIANT + 1] = defaultLoc.getVariant();
mCachedParams[Engine.TTS_PARAM_POSITION_STREAM + 1] =
String.valueOf(Engine.TTS_DEFAULT_STREAM);
mCachedParams[Engine.TTS_PARAM_POSITION_UTTERANCE_ID + 1] = "";
initTts();
}
private void initTts() {
mStarted = false;
// Initialize the TTS, run the callback after the binding is successful
mServiceConnection = new ServiceConnection() {
public void onServiceConnected(ComponentName name, IBinder service) {
synchronized(mStartLock) {
mITts = ITts.Stub.asInterface(service);
mStarted = true;
if (mInitListener != null) {
// TODO manage failures and missing resources
mInitListener.onInit(TTS_SUCCESS);
}
}
}
public void onServiceDisconnected(ComponentName name) {
synchronized(mStartLock) {
mITts = null;
mInitListener = null;
mStarted = false;
}
}
};
Intent intent = new Intent("android.intent.action.START_TTS_SERVICE");
intent.addCategory("android.intent.category.TTS");
mContext.bindService(intent, mServiceConnection,
Context.BIND_AUTO_CREATE);
// TODO handle case where the binding works (should always work) but
// the plugin fails
}
/**
* Shuts down the TTS. It is good practice to call this in the onDestroy
* method of the Activity that is using the TTS so that the TTS is stopped
* cleanly.
*/
public void shutdown() {
try {
mContext.unbindService(mServiceConnection);
} catch (IllegalArgumentException e) {
// Do nothing and fail silently since an error here indicates that
// binding never succeeded in the first place.
}
}
/**
* Adds a mapping between a string of text and a sound resource in a
* package.
*
* @see #TTS.speak(String text, int queueMode, String[] params)
*
* @param text
* Example: "south_south_east"
*
* @param packagename
* Pass the packagename of the application that contains the
* resource. If the resource is in your own application (this is
* the most common case), then put the packagename of your
* application here.
* Example: "com.google.marvin.compass"
* The packagename can be found in the AndroidManifest.xml of
* your application.
*
* <manifest xmlns:android="..."
* package="com.google.marvin.compass">
*
R.raw.south_south_east
*
* @return Code indicating success or failure. See TTS_ERROR and TTS_SUCCESS.
*/
public int addSpeech(String text, String packagename, int resourceId) {
synchronized(mStartLock) {
if (!mStarted) {
return TTS_ERROR;
}
try {
mITts.addSpeech(mPackageName, text, packagename, resourceId);
return TTS_SUCCESS;
} catch (RemoteException e) {
// TTS died; restart it.
Log.e("TextToSpeech.java - addSpeech", "RemoteException");
e.printStackTrace();
mStarted = false;
initTts();
} catch (NullPointerException e) {
// TTS died; restart it.
Log.e("TextToSpeech.java - addSpeech", "NullPointerException");
e.printStackTrace();
mStarted = false;
initTts();
} catch (IllegalStateException e) {
// TTS died; restart it.
Log.e("TextToSpeech.java - addSpeech", "IllegalStateException");
e.printStackTrace();
mStarted = false;
initTts();
}
return TTS_ERROR;
}
}
/**
* Adds a mapping between a string of text and a sound file. Using this, it
* is possible to add custom pronounciations for text.
*
* @param text
* The string of text
* @param filename
* The full path to the sound file (for example:
* "/sdcard/mysounds/hello.wav")
*
* @return Code indicating success or failure. See TTS_ERROR and TTS_SUCCESS.
*/
public int addSpeech(String text, String filename) {
synchronized (mStartLock) {
if (!mStarted) {
return TTS_ERROR;
}
try {
mITts.addSpeechFile(mPackageName, text, filename);
return TTS_SUCCESS;
} catch (RemoteException e) {
// TTS died; restart it.
Log.e("TextToSpeech.java - addSpeech", "RemoteException");
e.printStackTrace();
mStarted = false;
initTts();
} catch (NullPointerException e) {
// TTS died; restart it.
Log.e("TextToSpeech.java - addSpeech", "NullPointerException");
e.printStackTrace();
mStarted = false;
initTts();
} catch (IllegalStateException e) {
// TTS died; restart it.
Log.e("TextToSpeech.java - addSpeech", "IllegalStateException");
e.printStackTrace();
mStarted = false;
initTts();
}
return TTS_ERROR;
}
}
/**
* Speaks the string using the specified queuing strategy and speech
* parameters. Note that the speech parameters are not universally supported
* by all engines and will be treated as a hint. The TTS library will try to
* fulfill these parameters as much as possible, but there is no guarantee
* that the voice used will have the properties specified.
*
* @param text
* The string of text to be spoken.
* @param queueMode
* The queuing strategy to use.
* See TTS_QUEUE_ADD and TTS_QUEUE_FLUSH.
* @param params
* The hashmap of speech parameters to be used.
*
* @return Code indicating success or failure. See TTS_ERROR and TTS_SUCCESS.
*/
public int speak(String text, int queueMode, HashMap