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 android.app.Activity; 20 import android.content.ActivityNotFoundException; 21 import android.content.BroadcastReceiver; 22 import android.content.ComponentName; 23 import android.content.Context; 24 import android.content.Intent; 25 import android.content.pm.PackageManager; 26 import android.content.pm.ResolveInfo; 27 import android.os.Bundle; 28 29 import java.util.ArrayList; 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 static final String EXTRA_CALLING_PACKAGE = "calling_package"; 43 44 /** 45 * The extra key used in an intent which is providing an already opened audio source for the 46 * RecognitionService to use. Data should be a URI to an audio resource. 47 */ 48 public static final String EXTRA_AUDIO_INJECT_SOURCE = 49 "android.speech.extra.AUDIO_INJECT_SOURCE"; 50 RecognizerIntent()51 private RecognizerIntent() { 52 // Not for instantiating. 53 } 54 55 /** 56 * Starts an activity that will prompt the user for speech and send it through a 57 * speech recognizer. The results will be returned via activity results (in 58 * {@link Activity#onActivityResult}, if you start the intent using 59 * {@link Activity#startActivityForResult(Intent, int)}), or forwarded via a PendingIntent 60 * if one is provided. 61 * 62 * <p>Starting this intent with just {@link Activity#startActivity(Intent)} is not supported. 63 * You must either use {@link Activity#startActivityForResult(Intent, int)}, or provide a 64 * PendingIntent, to receive recognition results. 65 * 66 * <p>The implementation of this API is likely to stream audio to remote servers to perform 67 * speech recognition which can use a substantial amount of bandwidth. 68 * 69 * <p>Required extras: 70 * <ul> 71 * <li>{@link #EXTRA_LANGUAGE_MODEL} 72 * </ul> 73 * 74 * <p>Optional extras: 75 * <ul> 76 * <li>{@link #EXTRA_PROMPT} 77 * <li>{@link #EXTRA_LANGUAGE} 78 * <li>{@link #EXTRA_MAX_RESULTS} 79 * <li>{@link #EXTRA_RESULTS_PENDINGINTENT} 80 * <li>{@link #EXTRA_RESULTS_PENDINGINTENT_BUNDLE} 81 * </ul> 82 * 83 * <p> Result extras (returned in the result, not to be specified in the request): 84 * <ul> 85 * <li>{@link #EXTRA_RESULTS} 86 * </ul> 87 * 88 * <p>NOTE: There may not be any applications installed to handle this action, so you should 89 * make sure to catch {@link ActivityNotFoundException}. 90 */ 91 public static final String ACTION_RECOGNIZE_SPEECH = "android.speech.action.RECOGNIZE_SPEECH"; 92 93 /** 94 * Starts an activity that will prompt the user for speech, send it through a 95 * speech recognizer, and either display a web search result or trigger 96 * another type of action based on the user's speech. 97 * 98 * <p>If you want to avoid triggering any type of action besides web search, you can use 99 * the {@link #EXTRA_WEB_SEARCH_ONLY} extra. 100 * 101 * <p>Required extras: 102 * <ul> 103 * <li>{@link #EXTRA_LANGUAGE_MODEL} 104 * </ul> 105 * 106 * <p>Optional extras: 107 * <ul> 108 * <li>{@link #EXTRA_PROMPT} 109 * <li>{@link #EXTRA_LANGUAGE} 110 * <li>{@link #EXTRA_MAX_RESULTS} 111 * <li>{@link #EXTRA_PARTIAL_RESULTS} 112 * <li>{@link #EXTRA_WEB_SEARCH_ONLY} 113 * <li>{@link #EXTRA_ORIGIN} 114 * </ul> 115 * 116 * <p> Result extras (returned in the result, not to be specified in the request): 117 * <ul> 118 * <li>{@link #EXTRA_RESULTS} 119 * <li>{@link #EXTRA_CONFIDENCE_SCORES} (optional) 120 * </ul> 121 * 122 * <p>NOTE: There may not be any applications installed to handle this action, so you should 123 * make sure to catch {@link ActivityNotFoundException}. 124 */ 125 public static final String ACTION_WEB_SEARCH = "android.speech.action.WEB_SEARCH"; 126 127 /** 128 * Starts an activity that will prompt the user for speech without requiring the user's 129 * visual attention or touch input. It will send it through a speech recognizer, 130 * and either synthesize speech for a web search result or trigger 131 * another type of action based on the user's speech. 132 * 133 * This activity may be launched while device is locked in a secure mode. 134 * Special care must be taken to ensure that the voice actions that are performed while 135 * hands free cannot compromise the device's security. 136 * The activity should check the value of the {@link #EXTRA_SECURE} extra to determine 137 * whether the device has been securely locked. If so, the activity should either restrict 138 * the set of voice actions that are permitted or require some form of secure 139 * authentication before proceeding. 140 * 141 * To ensure that the activity's user interface is visible while the lock screen is showing, 142 * the activity should set the 143 * {@link android.view.WindowManager.LayoutParams#FLAG_SHOW_WHEN_LOCKED} window flag. 144 * Otherwise the activity's user interface may be hidden by the lock screen. The activity 145 * should take care not to leak private information when the device is securely locked. 146 * 147 * <p>Optional extras: 148 * <ul> 149 * <li>{@link #EXTRA_SECURE} 150 * </ul> 151 * 152 * <p class="note"> 153 * In some cases, a matching Activity may not exist, so ensure you 154 * safeguard against this. 155 */ 156 public static final String ACTION_VOICE_SEARCH_HANDS_FREE = 157 "android.speech.action.VOICE_SEARCH_HANDS_FREE"; 158 159 /** 160 * Optional boolean to indicate that a "hands free" voice search was performed while the device 161 * was in a secure mode. An example of secure mode is when the device's screen lock is active, 162 * and it requires some form of authentication to be unlocked. 163 * 164 * When the device is securely locked, the voice search activity should either restrict 165 * the set of voice actions that are permitted, or require some form of secure authentication 166 * before proceeding. 167 */ 168 public static final String EXTRA_SECURE = "android.speech.extras.EXTRA_SECURE"; 169 170 /** 171 * The minimum length of an utterance. We will not stop recording before this amount of time. 172 * 173 * Note that it is extremely rare you'd want to specify this value in an intent. If you don't 174 * have a very good reason to change these, you should leave them as they are. Note also that 175 * certain values may cause undesired or unexpected results - use judiciously! Additionally, 176 * depending on the recognizer implementation, these values may have no effect. 177 */ 178 public static final String EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS = 179 "android.speech.extras.SPEECH_INPUT_MINIMUM_LENGTH_MILLIS"; 180 181 /** 182 * The amount of time that it should take after we stop hearing speech to consider the input 183 * complete. 184 * 185 * Note that it is extremely rare you'd want to specify this value in an intent. If 186 * you don't have a very good reason to change these, you should leave them as they are. Note 187 * also that certain values may cause undesired or unexpected results - use judiciously! 188 * Additionally, depending on the recognizer implementation, these values may have no effect. 189 */ 190 public static final String EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS = 191 "android.speech.extras.SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS"; 192 193 /** 194 * The amount of time that it should take after we stop hearing speech to consider the input 195 * possibly complete. This is used to prevent the endpointer cutting off during very short 196 * mid-speech pauses. 197 * 198 * Note that it is extremely rare you'd want to specify this value in an intent. If 199 * you don't have a very good reason to change these, you should leave them as they are. Note 200 * also that certain values may cause undesired or unexpected results - use judiciously! 201 * Additionally, depending on the recognizer implementation, these values may have no effect. 202 */ 203 public static final String EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS = 204 "android.speech.extras.SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS"; 205 206 /** 207 * Informs the recognizer which speech model to prefer when performing 208 * {@link #ACTION_RECOGNIZE_SPEECH}. The recognizer uses this 209 * information to fine tune the results. This extra is required. Activities implementing 210 * {@link #ACTION_RECOGNIZE_SPEECH} may interpret the values as they see fit. 211 * 212 * @see #LANGUAGE_MODEL_FREE_FORM 213 * @see #LANGUAGE_MODEL_WEB_SEARCH 214 */ 215 public static final String EXTRA_LANGUAGE_MODEL = "android.speech.extra.LANGUAGE_MODEL"; 216 217 /** 218 * Use a language model based on free-form speech recognition. This is a value to use for 219 * {@link #EXTRA_LANGUAGE_MODEL}. 220 * @see #EXTRA_LANGUAGE_MODEL 221 */ 222 public static final String LANGUAGE_MODEL_FREE_FORM = "free_form"; 223 /** 224 * Use a language model based on web search terms. This is a value to use for 225 * {@link #EXTRA_LANGUAGE_MODEL}. 226 * @see #EXTRA_LANGUAGE_MODEL 227 */ 228 public static final String LANGUAGE_MODEL_WEB_SEARCH = "web_search"; 229 230 /** Optional text prompt to show to the user when asking them to speak. */ 231 public static final String EXTRA_PROMPT = "android.speech.extra.PROMPT"; 232 233 /** 234 * Optional IETF language tag (as defined by BCP 47), for example "en-US". This tag informs the 235 * recognizer to perform speech recognition in a language different than the one set in the 236 * {@link java.util.Locale#getDefault()}. 237 */ 238 public static final String EXTRA_LANGUAGE = "android.speech.extra.LANGUAGE"; 239 240 /** 241 * Optional value which can be used to indicate the referer url of a page in which 242 * speech was requested. For example, a web browser may choose to provide this for 243 * uses of speech on a given page. 244 */ 245 public static final String EXTRA_ORIGIN = "android.speech.extra.ORIGIN"; 246 247 /** 248 * Optional limit on the maximum number of results to return. If omitted the recognizer 249 * will choose how many results to return. Must be an integer. 250 */ 251 public static final String EXTRA_MAX_RESULTS = "android.speech.extra.MAX_RESULTS"; 252 253 /** 254 * Optional boolean, to be used with {@link #ACTION_WEB_SEARCH}, to indicate whether to 255 * only fire web searches in response to a user's speech. The default is false, meaning 256 * that other types of actions can be taken based on the user's speech. 257 */ 258 public static final String EXTRA_WEB_SEARCH_ONLY = "android.speech.extra.WEB_SEARCH_ONLY"; 259 260 /** 261 * Optional boolean to indicate whether partial results should be returned by the recognizer 262 * as the user speaks (default is false). The server may ignore a request for partial 263 * results in some or all cases. 264 */ 265 public static final String EXTRA_PARTIAL_RESULTS = "android.speech.extra.PARTIAL_RESULTS"; 266 267 /** 268 * When the intent is {@link #ACTION_RECOGNIZE_SPEECH}, the speech input activity will 269 * return results to you via the activity results mechanism. Alternatively, if you use this 270 * extra to supply a PendingIntent, the results will be added to its bundle and the 271 * PendingIntent will be sent to its target. 272 */ 273 public static final String EXTRA_RESULTS_PENDINGINTENT = 274 "android.speech.extra.RESULTS_PENDINGINTENT"; 275 276 /** 277 * If you use {@link #EXTRA_RESULTS_PENDINGINTENT} to supply a forwarding intent, you can 278 * also use this extra to supply additional extras for the final intent. The search results 279 * will be added to this bundle, and the combined bundle will be sent to the target. 280 */ 281 public static final String EXTRA_RESULTS_PENDINGINTENT_BUNDLE = 282 "android.speech.extra.RESULTS_PENDINGINTENT_BUNDLE"; 283 284 /** Result code returned when no matches are found for the given speech */ 285 public static final int RESULT_NO_MATCH = Activity.RESULT_FIRST_USER; 286 /** Result code returned when there is a generic client error */ 287 public static final int RESULT_CLIENT_ERROR = Activity.RESULT_FIRST_USER + 1; 288 /** Result code returned when the recognition server returns an error */ 289 public static final int RESULT_SERVER_ERROR = Activity.RESULT_FIRST_USER + 2; 290 /** Result code returned when a network error was encountered */ 291 public static final int RESULT_NETWORK_ERROR = Activity.RESULT_FIRST_USER + 3; 292 /** Result code returned when an audio error was encountered */ 293 public static final int RESULT_AUDIO_ERROR = Activity.RESULT_FIRST_USER + 4; 294 295 /** 296 * An ArrayList<String> of the recognition results when performing 297 * {@link #ACTION_RECOGNIZE_SPEECH}. Generally this list should be ordered in 298 * descending order of speech recognizer confidence. (See {@link #EXTRA_CONFIDENCE_SCORES}). 299 * Returned in the results; not to be specified in the recognition request. Only present 300 * when {@link Activity#RESULT_OK} is returned in an activity result. In a PendingIntent, 301 * the lack of this extra indicates failure. 302 */ 303 public static final String EXTRA_RESULTS = "android.speech.extra.RESULTS"; 304 305 /** 306 * A float array of confidence scores of the recognition results when performing 307 * {@link #ACTION_RECOGNIZE_SPEECH}. The array should be the same size as the ArrayList 308 * returned in {@link #EXTRA_RESULTS}, and should contain values ranging from 0.0 to 1.0, 309 * or -1 to represent an unavailable confidence score. 310 * <p> 311 * Confidence values close to 1.0 indicate high confidence (the speech recognizer is 312 * confident that the recognition result is correct), while values close to 0.0 indicate 313 * low confidence. 314 * <p> 315 * Returned in the results; not to be specified in the recognition request. This extra is 316 * optional and might not be provided. Only present when {@link Activity#RESULT_OK} is 317 * returned in an activity result. 318 */ 319 public static final String EXTRA_CONFIDENCE_SCORES = "android.speech.extra.CONFIDENCE_SCORES"; 320 321 /** 322 * Returns the broadcast intent to fire with 323 * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, Bundle)} 324 * to receive details from the package that implements voice search. 325 * <p> 326 * This is based on the value specified by the voice search {@link Activity} in 327 * {@link #DETAILS_META_DATA}, and if this is not specified, will return null. Also if there 328 * is no chosen default to resolve for {@link #ACTION_WEB_SEARCH}, this will return null. 329 * <p> 330 * If an intent is returned and is fired, a {@link Bundle} of extras will be returned to the 331 * provided result receiver, and should ideally contain values for 332 * {@link #EXTRA_LANGUAGE_PREFERENCE} and {@link #EXTRA_SUPPORTED_LANGUAGES}. 333 * <p> 334 * (Whether these are actually provided is up to the particular implementation. It is 335 * recommended that {@link Activity}s implementing {@link #ACTION_WEB_SEARCH} provide this 336 * information, but it is not required.) 337 * 338 * @param context a context object 339 * @return the broadcast intent to fire or null if not available 340 */ getVoiceDetailsIntent(Context context)341 public static final Intent getVoiceDetailsIntent(Context context) { 342 Intent voiceSearchIntent = new Intent(ACTION_WEB_SEARCH); 343 ResolveInfo ri = context.getPackageManager().resolveActivity( 344 voiceSearchIntent, PackageManager.GET_META_DATA); 345 if (ri == null || ri.activityInfo == null || ri.activityInfo.metaData == null) return null; 346 347 String className = ri.activityInfo.metaData.getString(DETAILS_META_DATA); 348 if (className == null) return null; 349 350 Intent detailsIntent = new Intent(ACTION_GET_LANGUAGE_DETAILS); 351 detailsIntent.setComponent(new ComponentName(ri.activityInfo.packageName, className)); 352 return detailsIntent; 353 } 354 355 /** 356 * Meta-data name under which an {@link Activity} implementing {@link #ACTION_WEB_SEARCH} can 357 * use to expose the class name of a {@link BroadcastReceiver} which can respond to request for 358 * more information, from any of the broadcast intents specified in this class. 359 * <p> 360 * Broadcast intents can be directed to the class name specified in the meta-data by creating 361 * an {@link Intent}, setting the component with 362 * {@link Intent#setComponent(android.content.ComponentName)}, and using 363 * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, android.os.Bundle)} 364 * with another {@link BroadcastReceiver} which can receive the results. 365 * <p> 366 * The {@link #getVoiceDetailsIntent(Context)} method is provided as a convenience to create 367 * a broadcast intent based on the value of this meta-data, if available. 368 * <p> 369 * This is optional and not all {@link Activity}s which implement {@link #ACTION_WEB_SEARCH} 370 * are required to implement this. Thus retrieving this meta-data may be null. 371 */ 372 public static final String DETAILS_META_DATA = "android.speech.DETAILS"; 373 374 /** 375 * A broadcast intent which can be fired to the {@link BroadcastReceiver} component specified 376 * in the meta-data defined in the {@link #DETAILS_META_DATA} meta-data of an 377 * {@link Activity} satisfying {@link #ACTION_WEB_SEARCH}. 378 * <p> 379 * When fired with 380 * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, android.os.Bundle)}, 381 * a {@link Bundle} of extras will be returned to the provided result receiver, and should 382 * ideally contain values for {@link #EXTRA_LANGUAGE_PREFERENCE} and 383 * {@link #EXTRA_SUPPORTED_LANGUAGES}. 384 * <p> 385 * (Whether these are actually provided is up to the particular implementation. It is 386 * recommended that {@link Activity}s implementing {@link #ACTION_WEB_SEARCH} provide this 387 * information, but it is not required.) 388 */ 389 public static final String ACTION_GET_LANGUAGE_DETAILS = 390 "android.speech.action.GET_LANGUAGE_DETAILS"; 391 392 /** 393 * Specify this boolean extra in a broadcast of {@link #ACTION_GET_LANGUAGE_DETAILS} to 394 * indicate that only the current language preference is needed in the response. This 395 * avoids any additional computation if all you need is {@link #EXTRA_LANGUAGE_PREFERENCE} 396 * in the response. 397 */ 398 public static final String EXTRA_ONLY_RETURN_LANGUAGE_PREFERENCE = 399 "android.speech.extra.ONLY_RETURN_LANGUAGE_PREFERENCE"; 400 401 /** 402 * The key to the extra in the {@link Bundle} returned by {@link #ACTION_GET_LANGUAGE_DETAILS} 403 * which is a {@link String} that represents the current language preference this user has 404 * specified - a locale string like "en-US". 405 */ 406 public static final String EXTRA_LANGUAGE_PREFERENCE = 407 "android.speech.extra.LANGUAGE_PREFERENCE"; 408 409 /** 410 * The key to the extra in the {@link Bundle} returned by {@link #ACTION_GET_LANGUAGE_DETAILS} 411 * which is an {@link ArrayList} of {@link String}s that represents the languages supported by 412 * this implementation of voice recognition - a list of strings like "en-US", "cmn-Hans-CN", 413 * etc. 414 */ 415 public static final String EXTRA_SUPPORTED_LANGUAGES = 416 "android.speech.extra.SUPPORTED_LANGUAGES"; 417 418 /** 419 * Optional boolean, to be used with {@link #ACTION_RECOGNIZE_SPEECH}, 420 * {@link #ACTION_VOICE_SEARCH_HANDS_FREE}, {@link #ACTION_WEB_SEARCH} to indicate whether to 421 * only use an offline speech recognition engine. The default is false, meaning that either 422 * network or offline recognition engines may be used. 423 * 424 * <p>Depending on the recognizer implementation, these values may have 425 * no effect.</p> 426 * 427 */ 428 public static final String EXTRA_PREFER_OFFLINE = "android.speech.extra.PREFER_OFFLINE"; 429 } 430