gecko-dev/dom/media/webspeech/synth/nsISpeechService.idl

/* -*- Mode: IDL; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*- */
/* This Source Code Form is subject to the terms of the Mozilla Public
 * License, v. 2.0. If a copy of the MPL was not distributed with this file,
 * You can obtain one at http://mozilla.org/MPL/2.0/. */

#include "nsISupports.idl"

typedef unsigned short SpeechServiceType;

/**
 * A callback is implemented by the service. For direct audio services, it is
 * required to implement these, although it could be helpful to use the
 * cancel method for shutting down the speech resources.
 */
[scriptable, uuid(408251b0-1d7b-4876-888f-718859ce8c9d)]
interface nsISpeechTaskCallback : nsISupports
{
  /**
   * The user or application has paused the speech.
   */
  void onPause();

  /**
   * The user or application has resumed the speech.
   */
  void onResume();

  /**
   * The user or application has canceled the speech.
   */
  void onCancel();
};


/**
 * A task is associated with a single utterance. It is provided by the browser
 * to the service in the speak() method.
 */
[scriptable, builtinclass, uuid(ad59949c-2437-4b35-8eeb-d760caab75c5)]
interface nsISpeechTask : nsISupports
{
  /**
   * Prepare browser for speech.
   *
   * @param aCallback callback object for mid-speech operations.
   * @param aChannels number of audio channels. Only required
   *                    in direct audio services
   * @param aRate     audio rate. Only required in direct audio services
   */
  [optional_argc] void setup(in nsISpeechTaskCallback aCallback,
                               [optional] in uint32_t aChannels,
                               [optional] in uint32_t aRate);

  /**
   * Send audio data to browser.
   *
   * @param aData     an Int16Array with PCM-16 audio data.
   * @param aLandmarks an array of sample offset and landmark pairs.
   *                     Used for emiting boundary and mark events.
   */
  [implicit_jscontext]
  void sendAudio(in jsval aData, in jsval aLandmarks);

  [noscript]
  void sendAudioNative([array, size_is(aDataLen)] in short aData, in unsigned long aDataLen);

  /**
   * Dispatch start event.
   */
  void dispatchStart();

  /**
   * Dispatch end event.
   *
   * @param aElapsedTime time in seconds since speech has started.
   * @param aCharIndex   offset of spoken characters.
   */
  void dispatchEnd(in float aElapsedTime, in unsigned long aCharIndex);

  /**
   * Dispatch pause event.
   *
   * @param aElapsedTime time in seconds since speech has started.
   * @param aCharIndex   offset of spoken characters.
   */
  void dispatchPause(in float aElapsedTime, in unsigned long aCharIndex);

  /**
   * Dispatch resume event.
   *
   * @param aElapsedTime time in seconds since speech has started.
   * @param aCharIndex   offset of spoken characters.
   */
  void dispatchResume(in float aElapsedTime, in unsigned long aCharIndex);

  /**
   * Dispatch error event.
   *
   * @param aElapsedTime time in seconds since speech has started.
   * @param aCharIndex   offset of spoken characters.
   */
  void dispatchError(in float aElapsedTime, in unsigned long aCharIndex);

  /**
   * Dispatch boundary event.
   *
   * @param aName        name of boundary, 'word' or 'sentence'
   * @param aElapsedTime time in seconds since speech has started.
   * @param aCharIndex   offset of spoken characters.
   */
  void dispatchBoundary(in DOMString aName, in float aElapsedTime,
                        in unsigned long aCharIndex);

  /**
   * Dispatch mark event.
   *
   * @param aName        mark identifier.
   * @param aElapsedTime time in seconds since speech has started.
   * @param aCharIndex   offset of spoken characters.
   */
  void dispatchMark(in DOMString aName, in float aElapsedTime, in unsigned long aCharIndex);
};

/**
 * The main interface of a speech synthesis service.
 *
 * A service's speak method could be implemented in two ways:
 *  1. Indirect audio - the service is responsible for outputting audio.
 *    The service calls the nsISpeechTask.dispatch* methods directly. Starting
 *    with dispatchStart() and ending with dispatchEnd or dispatchError().
 *
 *  2. Direct audio - the service provides us with PCM-16 data, and we output it.
 *    The service does not call the dispatch task methods directly. Instead,
 *    audio information is provided at setup(), and audio data is sent with
 *    sendAudio(). The utterance is terminated with an empty sendAudio().
 */
[scriptable, uuid(9b7d59db-88ff-43d0-b6ee-9f63d042d08f)]
interface nsISpeechService : nsISupports
{
  /**
   * Speak the given text using the voice identified byu the given uri. See
   * W3C Speech API spec for information about pitch and rate.
   * https://dvcs.w3.org/hg/speech-api/raw-file/tip/speechapi.html#utterance-attributes
   *
   * @param aText   text to utter.
   * @param aUri    unique voice identifier.
   * @param aVolume volume to speak voice in. Only relevant for indirect audio.
   * @param aRate   rate to speak voice in.
   * @param aPitch  pitch to speak voice in.
   * @param aTask  task instance for utterance, used for sending events or audio
   *                 data back to browser.
   */
  void speak(in DOMString aText, in DOMString aUri,
             in float aVolume, in float aRate, in float aPitch,
             in nsISpeechTask aTask);

  const SpeechServiceType SERVICETYPE_DIRECT_AUDIO = 1;
  const SpeechServiceType SERVICETYPE_INDIRECT_AUDIO = 2;

  readonly attribute SpeechServiceType serviceType;
};