Home | History | Annotate | Download | only in speech
      1 /*
      2  * Copyright (C) 2008 The Android Open Source Project
      3  *
      4  * Licensed under the Apache License, Version 2.0 (the "License");
      5  * you may not use this file except in compliance with the License.
      6  * You may obtain a copy of the License at
      7  *
      8  *      http://www.apache.org/licenses/LICENSE-2.0
      9  *
     10  * Unless required by applicable law or agreed to in writing, software
     11  * distributed under the License is distributed on an "AS IS" BASIS,
     12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     13  * See the License for the specific language governing permissions and
     14  * limitations under the License.
     15  */
     16 
     17 package android.speech;
     18 
     19 import java.util.ArrayList;
     20 
     21 import android.app.Activity;
     22 import android.content.ActivityNotFoundException;
     23 import android.content.BroadcastReceiver;
     24 import android.content.ComponentName;
     25 import android.content.Context;
     26 import android.content.Intent;
     27 import android.content.pm.PackageManager;
     28 import android.content.pm.ResolveInfo;
     29 import android.os.Bundle;
     30 
     31 /**
     32  * Constants for supporting speech recognition through starting an {@link Intent}
     33  */
     34 public class RecognizerIntent {
     35     /**
     36      * The extra key used in an intent to the speech recognizer for voice search. Not
     37      * generally to be used by developers. The system search dialog uses this, for example,
     38      * to set a calling package for identification by a voice search API. If this extra
     39      * is set by anyone but the system process, it should be overridden by the voice search
     40      * implementation.
     41      */
     42     public final static String EXTRA_CALLING_PACKAGE = "calling_package";
     43 
     44     private RecognizerIntent() {
     45         // Not for instantiating.
     46     }
     47 
     48     /**
     49      * Starts an activity that will prompt the user for speech and send it through a
     50      * speech recognizer.  The results will be returned via activity results (in
     51      * {@link Activity#onActivityResult}, if you start the intent using
     52      * {@link Activity#startActivityForResult(Intent, int)}), or forwarded via a PendingIntent
     53      * if one is provided.
     54      *
     55      * <p>Starting this intent with just {@link Activity#startActivity(Intent)} is not supported.
     56      * You must either use {@link Activity#startActivityForResult(Intent, int)}, or provide a
     57      * PendingIntent, to receive recognition results.
     58      *
     59      * <p>The implementation of this API is likely to stream audio to remote servers to perform
     60      * speech recognition which can use a substantial amount of bandwidth.
     61      *
     62      * <p>Required extras:
     63      * <ul>
     64      *   <li>{@link #EXTRA_LANGUAGE_MODEL}
     65      * </ul>
     66      *
     67      * <p>Optional extras:
     68      * <ul>
     69      *   <li>{@link #EXTRA_PROMPT}
     70      *   <li>{@link #EXTRA_LANGUAGE}
     71      *   <li>{@link #EXTRA_MAX_RESULTS}
     72      *   <li>{@link #EXTRA_RESULTS_PENDINGINTENT}
     73      *   <li>{@link #EXTRA_RESULTS_PENDINGINTENT_BUNDLE}
     74      * </ul>
     75      *
     76      * <p> Result extras (returned in the result, not to be specified in the request):
     77      * <ul>
     78      *   <li>{@link #EXTRA_RESULTS}
     79      * </ul>
     80      *
     81      * <p>NOTE: There may not be any applications installed to handle this action, so you should
     82      * make sure to catch {@link ActivityNotFoundException}.
     83      */
     84     public static final String ACTION_RECOGNIZE_SPEECH = "android.speech.action.RECOGNIZE_SPEECH";
     85 
     86     /**
     87      * Starts an activity that will prompt the user for speech, send it through a
     88      * speech recognizer, and either display a web search result or trigger
     89      * another type of action based on the user's speech.
     90      *
     91      * <p>If you want to avoid triggering any type of action besides web search, you can use
     92      * the {@link #EXTRA_WEB_SEARCH_ONLY} extra.
     93      *
     94      * <p>Required extras:
     95      * <ul>
     96      *   <li>{@link #EXTRA_LANGUAGE_MODEL}
     97      * </ul>
     98      *
     99      * <p>Optional extras:
    100      * <ul>
    101      *   <li>{@link #EXTRA_PROMPT}
    102      *   <li>{@link #EXTRA_LANGUAGE}
    103      *   <li>{@link #EXTRA_MAX_RESULTS}
    104      *   <li>{@link #EXTRA_PARTIAL_RESULTS}
    105      *   <li>{@link #EXTRA_WEB_SEARCH_ONLY}
    106      *   <li>{@link #EXTRA_ORIGIN}
    107      * </ul>
    108      *
    109      * <p> Result extras (returned in the result, not to be specified in the request):
    110      * <ul>
    111      *   <li>{@link #EXTRA_RESULTS}
    112      *   <li>{@link #EXTRA_CONFIDENCE_SCORES} (optional)
    113      * </ul>
    114      *
    115      * <p>NOTE: There may not be any applications installed to handle this action, so you should
    116      * make sure to catch {@link ActivityNotFoundException}.
    117      */
    118     public static final String ACTION_WEB_SEARCH = "android.speech.action.WEB_SEARCH";
    119 
    120     /**
    121      * Starts an activity that will prompt the user for speech without requiring the user's
    122      * visual attention or touch input. It will send it through a speech recognizer,
    123      * and either synthesize speech for a web search result or trigger
    124      * another type of action based on the user's speech.
    125      *
    126      * This activity may be launched while device is locked in a secure mode.
    127      * Special care must be taken to ensure that the voice actions that are performed while
    128      * hands free cannot compromise the device's security.
    129      * The activity should check the value of the {@link #EXTRA_SECURE} extra to determine
    130      * whether the device has been securely locked. If so, the activity should either restrict
    131      * the set of voice actions that are permitted or require some form of secure
    132      * authentication before proceeding.
    133      *
    134      * To ensure that the activity's user interface is visible while the lock screen is showing,
    135      * the activity should set the
    136      * {@link android.view.WindowManager.LayoutParams#FLAG_SHOW_WHEN_LOCKED} window flag.
    137      * Otherwise the activity's user interface may be hidden by the lock screen. The activity
    138      * should take care not to leak private information when the device is securely locked.
    139      *
    140      * <p>Optional extras:
    141      * <ul>
    142      *   <li>{@link #EXTRA_SECURE}
    143      * </ul>
    144      */
    145     public static final String ACTION_VOICE_SEARCH_HANDS_FREE =
    146             "android.speech.action.VOICE_SEARCH_HANDS_FREE";
    147 
    148     /**
    149      * Optional boolean to indicate that a "hands free" voice search was performed while the device
    150      * was in a secure mode. An example of secure mode is when the device's screen lock is active,
    151      * and it requires some form of authentication to be unlocked.
    152      *
    153      * When the device is securely locked, the voice search activity should either restrict
    154      * the set of voice actions that are permitted, or require some form of secure authentication
    155      * before proceeding.
    156      */
    157     public static final String EXTRA_SECURE = "android.speech.extras.EXTRA_SECURE";
    158 
    159     /**
    160      * The minimum length of an utterance. We will not stop recording before this amount of time.
    161      *
    162      * Note that it is extremely rare you'd want to specify this value in an intent. If you don't
    163      * have a very good reason to change these, you should leave them as they are. Note also that
    164      * certain values may cause undesired or unexpected results - use judiciously! Additionally,
    165      * depending on the recognizer implementation, these values may have no effect.
    166      */
    167     public static final String EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS =
    168             "android.speech.extras.SPEECH_INPUT_MINIMUM_LENGTH_MILLIS";
    169 
    170     /**
    171      * The amount of time that it should take after we stop hearing speech to consider the input
    172      * complete.
    173      *
    174      * Note that it is extremely rare you'd want to specify this value in an intent. If
    175      * you don't have a very good reason to change these, you should leave them as they are. Note
    176      * also that certain values may cause undesired or unexpected results - use judiciously!
    177      * Additionally, depending on the recognizer implementation, these values may have no effect.
    178      */
    179     public static final String EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS =
    180             "android.speech.extras.SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS";
    181 
    182     /**
    183      * The amount of time that it should take after we stop hearing speech to consider the input
    184      * possibly complete. This is used to prevent the endpointer cutting off during very short
    185      * mid-speech pauses.
    186      *
    187      * Note that it is extremely rare you'd want to specify this value in an intent. If
    188      * you don't have a very good reason to change these, you should leave them as they are. Note
    189      * also that certain values may cause undesired or unexpected results - use judiciously!
    190      * Additionally, depending on the recognizer implementation, these values may have no effect.
    191      */
    192     public static final String EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS =
    193             "android.speech.extras.SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS";
    194 
    195     /**
    196      * Informs the recognizer which speech model to prefer when performing
    197      * {@link #ACTION_RECOGNIZE_SPEECH}. The recognizer uses this
    198      * information to fine tune the results. This extra is required. Activities implementing
    199      * {@link #ACTION_RECOGNIZE_SPEECH} may interpret the values as they see fit.
    200      *
    201      *  @see #LANGUAGE_MODEL_FREE_FORM
    202      *  @see #LANGUAGE_MODEL_WEB_SEARCH
    203      */
    204     public static final String EXTRA_LANGUAGE_MODEL = "android.speech.extra.LANGUAGE_MODEL";
    205 
    206     /**
    207      * Use a language model based on free-form speech recognition.  This is a value to use for
    208      * {@link #EXTRA_LANGUAGE_MODEL}.
    209      * @see #EXTRA_LANGUAGE_MODEL
    210      */
    211     public static final String LANGUAGE_MODEL_FREE_FORM = "free_form";
    212     /**
    213      * Use a language model based on web search terms.  This is a value to use for
    214      * {@link #EXTRA_LANGUAGE_MODEL}.
    215      * @see #EXTRA_LANGUAGE_MODEL
    216      */
    217     public static final String LANGUAGE_MODEL_WEB_SEARCH = "web_search";
    218 
    219     /** Optional text prompt to show to the user when asking them to speak. */
    220     public static final String EXTRA_PROMPT = "android.speech.extra.PROMPT";
    221 
    222     /**
    223      * Optional IETF language tag (as defined by BCP 47), for example "en-US". This tag informs the
    224      * recognizer to perform speech recognition in a language different than the one set in the
    225      * {@link java.util.Locale#getDefault()}.
    226      */
    227     public static final String EXTRA_LANGUAGE = "android.speech.extra.LANGUAGE";
    228 
    229     /**
    230      * Optional value which can be used to indicate the referer url of a page in which
    231      * speech was requested. For example, a web browser may choose to provide this for
    232      * uses of speech on a given page.
    233      */
    234     public static final String EXTRA_ORIGIN = "android.speech.extra.ORIGIN";
    235 
    236     /**
    237      * Optional limit on the maximum number of results to return. If omitted the recognizer
    238      * will choose how many results to return. Must be an integer.
    239      */
    240     public static final String EXTRA_MAX_RESULTS = "android.speech.extra.MAX_RESULTS";
    241 
    242     /**
    243      * Optional boolean, to be used with {@link #ACTION_WEB_SEARCH}, to indicate whether to
    244      * only fire web searches in response to a user's speech. The default is false, meaning
    245      * that other types of actions can be taken based on the user's speech.
    246      */
    247     public static final String EXTRA_WEB_SEARCH_ONLY = "android.speech.extra.WEB_SEARCH_ONLY";
    248 
    249     /**
    250      * Optional boolean to indicate whether partial results should be returned by the recognizer
    251      * as the user speaks (default is false).  The server may ignore a request for partial
    252      * results in some or all cases.
    253      */
    254     public static final String EXTRA_PARTIAL_RESULTS = "android.speech.extra.PARTIAL_RESULTS";
    255 
    256     /**
    257      * When the intent is {@link #ACTION_RECOGNIZE_SPEECH}, the speech input activity will
    258      * return results to you via the activity results mechanism.  Alternatively, if you use this
    259      * extra to supply a PendingIntent, the results will be added to its bundle and the
    260      * PendingIntent will be sent to its target.
    261      */
    262     public static final String EXTRA_RESULTS_PENDINGINTENT =
    263             "android.speech.extra.RESULTS_PENDINGINTENT";
    264 
    265     /**
    266      * If you use {@link #EXTRA_RESULTS_PENDINGINTENT} to supply a forwarding intent, you can
    267      * also use this extra to supply additional extras for the final intent.  The search results
    268      * will be added to this bundle, and the combined bundle will be sent to the target.
    269      */
    270     public static final String EXTRA_RESULTS_PENDINGINTENT_BUNDLE =
    271             "android.speech.extra.RESULTS_PENDINGINTENT_BUNDLE";
    272 
    273     /** Result code returned when no matches are found for the given speech */
    274     public static final int RESULT_NO_MATCH = Activity.RESULT_FIRST_USER;
    275     /** Result code returned when there is a generic client error */
    276     public static final int RESULT_CLIENT_ERROR = Activity.RESULT_FIRST_USER + 1;
    277     /** Result code returned when the recognition server returns an error */
    278     public static final int RESULT_SERVER_ERROR = Activity.RESULT_FIRST_USER + 2;
    279     /** Result code returned when a network error was encountered */
    280     public static final int RESULT_NETWORK_ERROR = Activity.RESULT_FIRST_USER + 3;
    281     /** Result code returned when an audio error was encountered */
    282     public static final int RESULT_AUDIO_ERROR = Activity.RESULT_FIRST_USER + 4;
    283 
    284     /**
    285      * An ArrayList&lt;String&gt; of the recognition results when performing
    286      * {@link #ACTION_RECOGNIZE_SPEECH}. Generally this list should be ordered in
    287      * descending order of speech recognizer confidence. (See {@link #EXTRA_CONFIDENCE_SCORES}).
    288      * Returned in the results; not to be specified in the recognition request. Only present
    289      * when {@link Activity#RESULT_OK} is returned in an activity result. In a PendingIntent,
    290      * the lack of this extra indicates failure.
    291      */
    292     public static final String EXTRA_RESULTS = "android.speech.extra.RESULTS";
    293 
    294     /**
    295      * A float array of confidence scores of the recognition results when performing
    296      * {@link #ACTION_RECOGNIZE_SPEECH}. The array should be the same size as the ArrayList
    297      * returned in {@link #EXTRA_RESULTS}, and should contain values ranging from 0.0 to 1.0,
    298      * or -1 to represent an unavailable confidence score.
    299      * <p>
    300      * Confidence values close to 1.0 indicate high confidence (the speech recognizer is
    301      * confident that the recognition result is correct), while values close to 0.0 indicate
    302      * low confidence.
    303      * <p>
    304      * Returned in the results; not to be specified in the recognition request. This extra is
    305      * optional and might not be provided. Only present when {@link Activity#RESULT_OK} is
    306      * returned in an activity result.
    307      */
    308     public static final String EXTRA_CONFIDENCE_SCORES = "android.speech.extra.CONFIDENCE_SCORES";
    309 
    310     /**
    311      * Returns the broadcast intent to fire with
    312      * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, Bundle)}
    313      * to receive details from the package that implements voice search.
    314      * <p>
    315      * This is based on the value specified by the voice search {@link Activity} in
    316      * {@link #DETAILS_META_DATA}, and if this is not specified, will return null. Also if there
    317      * is no chosen default to resolve for {@link #ACTION_WEB_SEARCH}, this will return null.
    318      * <p>
    319      * If an intent is returned and is fired, a {@link Bundle} of extras will be returned to the
    320      * provided result receiver, and should ideally contain values for
    321      * {@link #EXTRA_LANGUAGE_PREFERENCE} and {@link #EXTRA_SUPPORTED_LANGUAGES}.
    322      * <p>
    323      * (Whether these are actually provided is up to the particular implementation. It is
    324      * recommended that {@link Activity}s implementing {@link #ACTION_WEB_SEARCH} provide this
    325      * information, but it is not required.)
    326      *
    327      * @param context a context object
    328      * @return the broadcast intent to fire or null if not available
    329      */
    330     public static final Intent getVoiceDetailsIntent(Context context) {
    331         Intent voiceSearchIntent = new Intent(ACTION_WEB_SEARCH);
    332         ResolveInfo ri = context.getPackageManager().resolveActivity(
    333                 voiceSearchIntent, PackageManager.GET_META_DATA);
    334         if (ri == null || ri.activityInfo == null || ri.activityInfo.metaData == null) return null;
    335 
    336         String className = ri.activityInfo.metaData.getString(DETAILS_META_DATA);
    337         if (className == null) return null;
    338 
    339         Intent detailsIntent = new Intent(ACTION_GET_LANGUAGE_DETAILS);
    340         detailsIntent.setComponent(new ComponentName(ri.activityInfo.packageName, className));
    341         return detailsIntent;
    342     }
    343 
    344     /**
    345      * Meta-data name under which an {@link Activity} implementing {@link #ACTION_WEB_SEARCH} can
    346      * use to expose the class name of a {@link BroadcastReceiver} which can respond to request for
    347      * more information, from any of the broadcast intents specified in this class.
    348      * <p>
    349      * Broadcast intents can be directed to the class name specified in the meta-data by creating
    350      * an {@link Intent}, setting the component with
    351      * {@link Intent#setComponent(android.content.ComponentName)}, and using
    352      * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, android.os.Bundle)}
    353      * with another {@link BroadcastReceiver} which can receive the results.
    354      * <p>
    355      * The {@link #getVoiceDetailsIntent(Context)} method is provided as a convenience to create
    356      * a broadcast intent based on the value of this meta-data, if available.
    357      * <p>
    358      * This is optional and not all {@link Activity}s which implement {@link #ACTION_WEB_SEARCH}
    359      * are required to implement this. Thus retrieving this meta-data may be null.
    360      */
    361     public static final String DETAILS_META_DATA = "android.speech.DETAILS";
    362 
    363     /**
    364      * A broadcast intent which can be fired to the {@link BroadcastReceiver} component specified
    365      * in the meta-data defined in the {@link #DETAILS_META_DATA} meta-data of an
    366      * {@link Activity} satisfying {@link #ACTION_WEB_SEARCH}.
    367      * <p>
    368      * When fired with
    369      * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, android.os.Bundle)},
    370      * a {@link Bundle} of extras will be returned to the provided result receiver, and should
    371      * ideally contain values for {@link #EXTRA_LANGUAGE_PREFERENCE} and
    372      * {@link #EXTRA_SUPPORTED_LANGUAGES}.
    373      * <p>
    374      * (Whether these are actually provided is up to the particular implementation. It is
    375      * recommended that {@link Activity}s implementing {@link #ACTION_WEB_SEARCH} provide this
    376      * information, but it is not required.)
    377      */
    378     public static final String ACTION_GET_LANGUAGE_DETAILS =
    379             "android.speech.action.GET_LANGUAGE_DETAILS";
    380 
    381     /**
    382      * Specify this boolean extra in a broadcast of {@link #ACTION_GET_LANGUAGE_DETAILS} to
    383      * indicate that only the current language preference is needed in the response. This
    384      * avoids any additional computation if all you need is {@link #EXTRA_LANGUAGE_PREFERENCE}
    385      * in the response.
    386      */
    387     public static final String EXTRA_ONLY_RETURN_LANGUAGE_PREFERENCE =
    388             "android.speech.extra.ONLY_RETURN_LANGUAGE_PREFERENCE";
    389 
    390     /**
    391      * The key to the extra in the {@link Bundle} returned by {@link #ACTION_GET_LANGUAGE_DETAILS}
    392      * which is a {@link String} that represents the current language preference this user has
    393      * specified - a locale string like "en-US".
    394      */
    395     public static final String EXTRA_LANGUAGE_PREFERENCE =
    396             "android.speech.extra.LANGUAGE_PREFERENCE";
    397 
    398     /**
    399      * The key to the extra in the {@link Bundle} returned by {@link #ACTION_GET_LANGUAGE_DETAILS}
    400      * which is an {@link ArrayList} of {@link String}s that represents the languages supported by
    401      * this implementation of voice recognition - a list of strings like "en-US", "cmn-Hans-CN",
    402      * etc.
    403      */
    404     public static final String EXTRA_SUPPORTED_LANGUAGES =
    405             "android.speech.extra.SUPPORTED_LANGUAGES";
    406 
    407     /**
    408      * Optional boolean, to be used with {@link #ACTION_RECOGNIZE_SPEECH},
    409      * {@link #ACTION_VOICE_SEARCH_HANDS_FREE}, {@link #ACTION_WEB_SEARCH} to indicate whether to
    410      * only use an offline speech recognition engine. The default is false, meaning that either
    411      * network or offline recognition engines may be used.
    412      */
    413     public static final String EXTRA_PREFER_OFFLINE = "android.speech.extra.PREFER_OFFLINE";
    414 }
    415