Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 1 | /* |
| 2 | * Copyright (C) 2011 The Android Open Source Project |
| 3 | * |
| 4 | * Licensed under the Apache License, Version 2.0 (the "License"); you may not |
| 5 | * use this file except in compliance with the License. You may obtain a copy of |
| 6 | * 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, WITHOUT |
| 12 | * WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the |
| 13 | * License for the specific language governing permissions and limitations under |
| 14 | * the License. |
| 15 | */ |
| 16 | package android.speech.tts; |
| 17 | |
| 18 | /** |
| 19 | * A request for speech synthesis given to a TTS engine for processing. |
| 20 | * |
Bjorn Bringert | 71e0b48 | 2011-04-15 14:37:05 +0100 | [diff] [blame] | 21 | * The engine can provide streaming audio by calling |
| 22 | * {@link #start}, then {@link #audioAvailable} until all audio has been provided, then finally |
| 23 | * {@link #done}. |
| 24 | * |
| 25 | * Alternatively, the engine can provide all the audio at once, by using |
| 26 | * {@link #completeAudioAvailable}. |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 27 | */ |
| 28 | public abstract class SynthesisRequest { |
| 29 | |
| 30 | private final String mText; |
| 31 | private String mLanguage; |
| 32 | private String mCountry; |
| 33 | private String mVariant; |
| 34 | private int mSpeechRate; |
| 35 | private int mPitch; |
| 36 | |
| 37 | public SynthesisRequest(String text) { |
| 38 | mText = text; |
| 39 | } |
| 40 | |
| 41 | /** |
| 42 | * Sets the locale for the request. |
| 43 | */ |
| 44 | void setLanguage(String language, String country, String variant) { |
| 45 | mLanguage = language; |
| 46 | mCountry = country; |
| 47 | mVariant = variant; |
| 48 | } |
| 49 | |
| 50 | /** |
| 51 | * Sets the speech rate. |
| 52 | */ |
| 53 | void setSpeechRate(int speechRate) { |
| 54 | mSpeechRate = speechRate; |
| 55 | } |
| 56 | |
| 57 | /** |
| 58 | * Sets the pitch. |
| 59 | */ |
| 60 | void setPitch(int pitch) { |
| 61 | mPitch = pitch; |
| 62 | } |
| 63 | |
| 64 | /** |
| 65 | * Gets the text which should be synthesized. |
| 66 | */ |
| 67 | public String getText() { |
| 68 | return mText; |
| 69 | } |
| 70 | |
| 71 | /** |
| 72 | * Gets the ISO 3-letter language code for the language to use. |
| 73 | */ |
| 74 | public String getLanguage() { |
| 75 | return mLanguage; |
| 76 | } |
| 77 | |
| 78 | /** |
| 79 | * Gets the ISO 3-letter country code for the language to use. |
| 80 | */ |
| 81 | public String getCountry() { |
| 82 | return mCountry; |
| 83 | } |
| 84 | |
| 85 | /** |
| 86 | * Gets the language variant to use. |
| 87 | */ |
| 88 | public String getVariant() { |
| 89 | return mVariant; |
| 90 | } |
| 91 | |
| 92 | /** |
Bjorn Bringert | 4bbca88 | 2011-04-19 18:45:25 +0100 | [diff] [blame] | 93 | * Gets the speech rate to use. The normal rate is 100. |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 94 | */ |
| 95 | public int getSpeechRate() { |
| 96 | return mSpeechRate; |
| 97 | } |
| 98 | |
| 99 | /** |
Bjorn Bringert | 4bbca88 | 2011-04-19 18:45:25 +0100 | [diff] [blame] | 100 | * Gets the pitch to use. The normal pitch is 100. |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 101 | */ |
| 102 | public int getPitch() { |
| 103 | return mPitch; |
| 104 | } |
| 105 | |
| 106 | /** |
Bjorn Bringert | 71e0b48 | 2011-04-15 14:37:05 +0100 | [diff] [blame] | 107 | * Gets the maximum number of bytes that the TTS engine can pass in a single call of |
| 108 | * {@link #audioAvailable}. This does not apply to {@link #completeAudioAvailable}. |
| 109 | */ |
| 110 | public abstract int getMaxBufferSize(); |
| 111 | |
| 112 | /** |
Bjorn Bringert | 360eb16 | 2011-04-19 09:20:35 +0100 | [diff] [blame] | 113 | * Checks whether the synthesis request completed successfully. |
| 114 | */ |
| 115 | abstract boolean isDone(); |
| 116 | |
| 117 | /** |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 118 | * Aborts the speech request. |
| 119 | * |
| 120 | * Can be called from multiple threads. |
| 121 | */ |
| 122 | abstract void stop(); |
| 123 | |
| 124 | /** |
| 125 | * The service should call this when it starts to synthesize audio for this |
| 126 | * request. |
| 127 | * |
| 128 | * This method should only be called on the synthesis thread, |
| 129 | * while in {@link TextToSpeechService#onSynthesizeText}. |
| 130 | * |
| 131 | * @param sampleRateInHz Sample rate in HZ of the generated audio. |
| 132 | * @param audioFormat Audio format of the generated audio. Must be one of |
| 133 | * the ENCODING_ constants defined in {@link android.media.AudioFormat}. |
Bjorn Bringert | 71e0b48 | 2011-04-15 14:37:05 +0100 | [diff] [blame] | 134 | * @param channelCount The number of channels. Must be {@code 1} or {@code 2}. |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 135 | * @return {@link TextToSpeech#SUCCESS} or {@link TextToSpeech#ERROR}. |
| 136 | */ |
| 137 | public abstract int start(int sampleRateInHz, int audioFormat, int channelCount); |
| 138 | |
| 139 | /** |
| 140 | * The service should call this method when synthesized audio is ready for consumption. |
| 141 | * |
| 142 | * This method should only be called on the synthesis thread, |
| 143 | * while in {@link TextToSpeechService#onSynthesizeText}. |
| 144 | * |
| 145 | * @param buffer The generated audio data. This method will not hold on to {@code buffer}, |
| 146 | * so the caller is free to modify it after this method returns. |
| 147 | * @param offset The offset into {@code buffer} where the audio data starts. |
Bjorn Bringert | 71e0b48 | 2011-04-15 14:37:05 +0100 | [diff] [blame] | 148 | * @param length The number of bytes of audio data in {@code buffer}. This must be |
| 149 | * less than or equal to the return value of {@link #getMaxBufferSize}. |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 150 | * @return {@link TextToSpeech#SUCCESS} or {@link TextToSpeech#ERROR}. |
| 151 | */ |
| 152 | public abstract int audioAvailable(byte[] buffer, int offset, int length); |
| 153 | |
| 154 | /** |
| 155 | * The service should call this method when all the synthesized audio for a request has |
| 156 | * been passed to {@link #audioAvailable}. |
| 157 | * |
| 158 | * This method should only be called on the synthesis thread, |
| 159 | * while in {@link TextToSpeechService#onSynthesizeText}. |
| 160 | * |
| 161 | * @return {@link TextToSpeech#SUCCESS} or {@link TextToSpeech#ERROR}. |
| 162 | */ |
| 163 | public abstract int done(); |
| 164 | |
Bjorn Bringert | 71e0b48 | 2011-04-15 14:37:05 +0100 | [diff] [blame] | 165 | /** |
Bjorn Bringert | 360eb16 | 2011-04-19 09:20:35 +0100 | [diff] [blame] | 166 | * The service should call this method if the speech synthesis fails. |
| 167 | * |
| 168 | * This method should only be called on the synthesis thread, |
| 169 | * while in {@link TextToSpeechService#onSynthesizeText}. |
| 170 | */ |
| 171 | public abstract void error(); |
| 172 | |
| 173 | /** |
Bjorn Bringert | 71e0b48 | 2011-04-15 14:37:05 +0100 | [diff] [blame] | 174 | * The service can call this method instead of using {@link #start}, {@link #audioAvailable} |
| 175 | * and {@link #done} if all the audio data is available in a single buffer. |
| 176 | * |
| 177 | * @param sampleRateInHz Sample rate in HZ of the generated audio. |
| 178 | * @param audioFormat Audio format of the generated audio. Must be one of |
| 179 | * the ENCODING_ constants defined in {@link android.media.AudioFormat}. |
| 180 | * @param channelCount The number of channels. Must be {@code 1} or {@code 2}. |
| 181 | * @param buffer The generated audio data. This method will not hold on to {@code buffer}, |
| 182 | * so the caller is free to modify it after this method returns. |
| 183 | * @param offset The offset into {@code buffer} where the audio data starts. |
| 184 | * @param length The number of bytes of audio data in {@code buffer}. |
| 185 | * @return {@link TextToSpeech#SUCCESS} or {@link TextToSpeech#ERROR}. |
| 186 | */ |
| 187 | public abstract int completeAudioAvailable(int sampleRateInHz, int audioFormat, |
| 188 | int channelCount, byte[] buffer, int offset, int length); |
Bjorn Bringert | 50e657b | 2011-03-08 16:00:40 +0000 | [diff] [blame] | 189 | } |