StreamingSynthesize
Performs bidirectional streaming speech synthesis: receive audio while sending text.
Performs bidirectional streaming speech synthesis: receives audio while sending text.
Callable method variants take no parameters and return an immutable API callable object, which can be used to initiate calls to the service.
*Sample code: * diff --git a/java-texttospeech/grpc-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechGrpc.java b/java-texttospeech/grpc-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechGrpc.java index 21afc920a1ac..050b402d6827 100644 --- a/java-texttospeech/grpc-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechGrpc.java +++ b/java-texttospeech/grpc-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechGrpc.java @@ -275,7 +275,7 @@ default void synthesizeSpeech( * * *
- * Performs bidirectional streaming speech synthesis: receive audio while
+ * Performs bidirectional streaming speech synthesis: receives audio while
* sending text.
*
*/
@@ -361,7 +361,7 @@ public void synthesizeSpeech(
*
*
*
- * Performs bidirectional streaming speech synthesis: receive audio while
+ * Performs bidirectional streaming speech synthesis: receives audio while
* sending text.
*
*/
@@ -426,7 +426,7 @@ public com.google.cloud.texttospeech.v1beta1.SynthesizeSpeechResponse synthesize
*
*
*
- * Performs bidirectional streaming speech synthesis: receive audio while
+ * Performs bidirectional streaming speech synthesis: receives audio while
* sending text.
*
*/
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptions.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptions.java
index e76337192eaa..2b34045bf96f 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptions.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptions.java
@@ -70,8 +70,8 @@ public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
@@ -87,8 +87,8 @@ public boolean hasLowLatencyJourneySynthesis() {
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
@@ -457,8 +457,8 @@ public Builder mergeFrom(
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
@@ -474,8 +474,8 @@ public boolean hasLowLatencyJourneySynthesis() {
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
@@ -491,8 +491,8 @@ public boolean getLowLatencyJourneySynthesis() {
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
@@ -512,8 +512,8 @@ public Builder setLowLatencyJourneySynthesis(boolean value) {
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptionsOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptionsOrBuilder.java
index 8c2e56aa16de..e8b6f3b17f5b 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptionsOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AdvancedVoiceOptionsOrBuilder.java
@@ -28,8 +28,8 @@ public interface AdvancedVoiceOptionsOrBuilder
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
@@ -42,8 +42,8 @@ public interface AdvancedVoiceOptionsOrBuilder
*
*
*
- * Only for Journey voices. If false, the synthesis will be context aware
- * and have higher latency.
+ * Only for Journey voices. If false, the synthesis is context aware
+ * and has a higher latency.
*
*
* optional bool low_latency_journey_synthesis = 1;
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfig.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfig.java
index 58fb220994af..e1e15655027e 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfig.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfig.java
@@ -115,10 +115,10 @@ public com.google.cloud.texttospeech.v1beta1.AudioEncoding getAudioEncoding() {
*
*
*
- * Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
* the normal native speed supported by the specific voice. 2.0 is twice as
* fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
- * speed. Any other values < 0.25 or > 4.0 will return an error.
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
*
*
*
@@ -899,10 +899,10 @@ public Builder clearAudioEncoding() {
*
*
*
- * Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
* the normal native speed supported by the specific voice. 2.0 is twice as
* fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
- * speed. Any other values < 0.25 or > 4.0 will return an error.
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
*
*
*
@@ -920,10 +920,10 @@ public double getSpeakingRate() {
*
*
*
- * Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
* the normal native speed supported by the specific voice. 2.0 is twice as
* fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
- * speed. Any other values < 0.25 or > 4.0 will return an error.
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
*
*
*
@@ -945,10 +945,10 @@ public Builder setSpeakingRate(double value) {
*
*
*
- * Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
* the normal native speed supported by the specific voice. 2.0 is twice as
* fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
- * speed. Any other values < 0.25 or > 4.0 will return an error.
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
*
*
*
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfigOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfigOrBuilder.java
index 3ccd85faeaa1..118047e27e80 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfigOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioConfigOrBuilder.java
@@ -58,10 +58,10 @@ public interface AudioConfigOrBuilder
*
*
*
- * Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
* the normal native speed supported by the specific voice. 2.0 is twice as
* fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
- * speed. Any other values < 0.25 or > 4.0 will return an error.
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
*
*
*
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioEncoding.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioEncoding.java
index 1b04d3f7c617..b00f48d07ebe 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioEncoding.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/AudioEncoding.java
@@ -34,7 +34,8 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*
*
*
- * Not specified. Will return result
+ * Not specified. Only used by GenerateVoiceCloningKey. Otherwise, will return
+ * result
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
*
*
@@ -76,7 +77,7 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*
*
*
- * Opus encoded audio wrapped in an ogg container. The result will be a
+ * Opus encoded audio wrapped in an ogg container. The result is a
* file which can be played natively on Android, and in browsers (at least
* Chrome and Firefox). The quality of the encoding is considerably higher
* than MP3 while using approximately the same bitrate.
@@ -112,13 +113,23 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*
*
* Uncompressed 16-bit signed little-endian samples (Linear PCM).
- * Note that as opposed to LINEAR16, audio will not be wrapped in a WAV (or
+ * Note that as opposed to LINEAR16, audio won't be wrapped in a WAV (or
* any other) header.
*
*
* PCM = 7;
*/
PCM(7),
+ /**
+ *
+ *
+ *
+ * M4A audio.
+ *
+ *
+ * M4A = 8;
+ */
+ M4A(8),
UNRECOGNIZED(-1),
;
@@ -126,7 +137,8 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*
*
*
- * Not specified. Will return result
+ * Not specified. Only used by GenerateVoiceCloningKey. Otherwise, will return
+ * result
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
*
*
@@ -172,7 +184,7 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*
*
*
- * Opus encoded audio wrapped in an ogg container. The result will be a
+ * Opus encoded audio wrapped in an ogg container. The result is a
* file which can be played natively on Android, and in browsers (at least
* Chrome and Firefox). The quality of the encoding is considerably higher
* than MP3 while using approximately the same bitrate.
@@ -211,7 +223,7 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*
*
* Uncompressed 16-bit signed little-endian samples (Linear PCM).
- * Note that as opposed to LINEAR16, audio will not be wrapped in a WAV (or
+ * Note that as opposed to LINEAR16, audio won't be wrapped in a WAV (or
* any other) header.
*
*
@@ -219,6 +231,17 @@ public enum AudioEncoding implements com.google.protobuf.ProtocolMessageEnum {
*/
public static final int PCM_VALUE = 7;
+ /**
+ *
+ *
+ *
+ * M4A audio.
+ *
+ *
+ * M4A = 8;
+ */
+ public static final int M4A_VALUE = 8;
+
public final int getNumber() {
if (this == UNRECOGNIZED) {
throw new java.lang.IllegalArgumentException(
@@ -259,6 +282,8 @@ public static AudioEncoding forNumber(int value) {
return ALAW;
case 7:
return PCM;
+ case 8:
+ return M4A;
default:
return null;
}
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParams.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParams.java
index 938ab454bfbd..60af22ffda3c 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParams.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParams.java
@@ -91,7 +91,7 @@ public enum PhoneticEncoding implements com.google.protobuf.ProtocolMessageEnum
*
*
*
- * IPA. (e.g. apple -> ˈæpəl )
+ * IPA, such as apple -> ˈæpəl.
* https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
*
*
@@ -102,13 +102,50 @@ public enum PhoneticEncoding implements com.google.protobuf.ProtocolMessageEnum
*
*
*
- * X-SAMPA (e.g. apple -> "{p@l" )
+ * X-SAMPA, such as apple -> "{p@l".
* https://en.wikipedia.org/wiki/X-SAMPA
*
*
* PHONETIC_ENCODING_X_SAMPA = 2;
*/
PHONETIC_ENCODING_X_SAMPA(2),
+ /**
+ *
+ *
+ *
+ * For reading-to-pron conversion to work well, the `pronunciation` field
+ * should only contain Kanji, Hiragana, and Katakana.
+ *
+ * The pronunciation can also contain pitch accents.
+ * The start of a pitch phrase is specified with `^` and the down-pitch
+ * position is specified with `!`, for example:
+ *
+ * phrase:端 pronunciation:^はし
+ * phrase:箸 pronunciation:^は!し
+ * phrase:橋 pronunciation:^はし!
+ *
+ * We currently only support the Tokyo dialect, which allows at most one
+ * down-pitch per phrase (i.e. at most one `!` between `^`).
+ *
+ *
+ * PHONETIC_ENCODING_JAPANESE_YOMIGANA = 3;
+ */
+ PHONETIC_ENCODING_JAPANESE_YOMIGANA(3),
+ /**
+ *
+ *
+ *
+ * Used to specify pronunciations for Mandarin words. See
+ * https://en.wikipedia.org/wiki/Pinyin.
+ *
+ * For example: 朝阳, the pronunciation is "chao2 yang2". The number
+ * represents the tone, and there is a space between syllables. Neutral
+ * tones are represented by 5, for example 孩子 "hai2 zi5".
+ *
+ *
+ * PHONETIC_ENCODING_PINYIN = 4;
+ */
+ PHONETIC_ENCODING_PINYIN(4),
UNRECOGNIZED(-1),
;
@@ -127,7 +164,7 @@ public enum PhoneticEncoding implements com.google.protobuf.ProtocolMessageEnum
*
*
*
- * IPA. (e.g. apple -> ˈæpəl )
+ * IPA, such as apple -> ˈæpəl.
* https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
*
*
@@ -139,7 +176,7 @@ public enum PhoneticEncoding implements com.google.protobuf.ProtocolMessageEnum
*
*
*
- * X-SAMPA (e.g. apple -> "{p@l" )
+ * X-SAMPA, such as apple -> "{p@l".
* https://en.wikipedia.org/wiki/X-SAMPA
*
*
@@ -147,6 +184,45 @@ public enum PhoneticEncoding implements com.google.protobuf.ProtocolMessageEnum
*/
public static final int PHONETIC_ENCODING_X_SAMPA_VALUE = 2;
+ /**
+ *
+ *
+ *
+ * For reading-to-pron conversion to work well, the `pronunciation` field
+ * should only contain Kanji, Hiragana, and Katakana.
+ *
+ * The pronunciation can also contain pitch accents.
+ * The start of a pitch phrase is specified with `^` and the down-pitch
+ * position is specified with `!`, for example:
+ *
+ * phrase:端 pronunciation:^はし
+ * phrase:箸 pronunciation:^は!し
+ * phrase:橋 pronunciation:^はし!
+ *
+ * We currently only support the Tokyo dialect, which allows at most one
+ * down-pitch per phrase (i.e. at most one `!` between `^`).
+ *
+ *
+ * PHONETIC_ENCODING_JAPANESE_YOMIGANA = 3;
+ */
+ public static final int PHONETIC_ENCODING_JAPANESE_YOMIGANA_VALUE = 3;
+
+ /**
+ *
+ *
+ *
+ * Used to specify pronunciations for Mandarin words. See
+ * https://en.wikipedia.org/wiki/Pinyin.
+ *
+ * For example: 朝阳, the pronunciation is "chao2 yang2". The number
+ * represents the tone, and there is a space between syllables. Neutral
+ * tones are represented by 5, for example 孩子 "hai2 zi5".
+ *
+ *
+ * PHONETIC_ENCODING_PINYIN = 4;
+ */
+ public static final int PHONETIC_ENCODING_PINYIN_VALUE = 4;
+
public final int getNumber() {
if (this == UNRECOGNIZED) {
throw new java.lang.IllegalArgumentException(
@@ -177,6 +253,10 @@ public static PhoneticEncoding forNumber(int value) {
return PHONETIC_ENCODING_IPA;
case 2:
return PHONETIC_ENCODING_X_SAMPA;
+ case 3:
+ return PHONETIC_ENCODING_JAPANESE_YOMIGANA;
+ case 4:
+ return PHONETIC_ENCODING_PINYIN;
default:
return null;
}
@@ -244,9 +324,9 @@ private PhoneticEncoding(int value) {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -262,9 +342,9 @@ public boolean hasPhrase() {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -288,9 +368,9 @@ public java.lang.String getPhrase() {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -866,9 +946,9 @@ public Builder mergeFrom(
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -883,9 +963,9 @@ public boolean hasPhrase() {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -908,9 +988,9 @@ public java.lang.String getPhrase() {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -933,9 +1013,9 @@ public com.google.protobuf.ByteString getPhraseBytes() {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -957,9 +1037,9 @@ public Builder setPhrase(java.lang.String value) {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -977,9 +1057,9 @@ public Builder clearPhrase() {
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParamsOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParamsOrBuilder.java
index a053c3639e23..7c0b9e416fac 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParamsOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationParamsOrBuilder.java
@@ -28,9 +28,9 @@ public interface CustomPronunciationParamsOrBuilder
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -43,9 +43,9 @@ public interface CustomPronunciationParamsOrBuilder
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
@@ -58,9 +58,9 @@ public interface CustomPronunciationParamsOrBuilder
*
*
*
- * The phrase to which the customization will be applied.
- * The phrase can be multiple words (in the case of proper nouns etc), but
- * should not span to a whole sentence.
+ * The phrase to which the customization is applied.
+ * The phrase can be multiple words, such as proper nouns, but shouldn't span
+ * the length of the sentence.
*
*
* optional string phrase = 1;
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciations.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciations.java
index e3fe2d57db13..3cfa00dbeae6 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciations.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciations.java
@@ -74,7 +74,7 @@ public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -90,7 +90,7 @@ public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -107,7 +107,7 @@ public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -122,7 +122,7 @@ public int getPronunciationsCount() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -138,7 +138,7 @@ public com.google.cloud.texttospeech.v1beta1.CustomPronunciationParams getPronun
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -565,7 +565,7 @@ private void ensurePronunciationsIsMutable() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -585,7 +585,7 @@ private void ensurePronunciationsIsMutable() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -604,7 +604,7 @@ public int getPronunciationsCount() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -624,7 +624,7 @@ public com.google.cloud.texttospeech.v1beta1.CustomPronunciationParams getPronun
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -650,7 +650,7 @@ public Builder setPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -674,7 +674,7 @@ public Builder setPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -700,7 +700,7 @@ public Builder addPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -726,7 +726,7 @@ public Builder addPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -749,7 +749,7 @@ public Builder addPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -773,7 +773,7 @@ public Builder addPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -798,7 +798,7 @@ public Builder addAllPronunciations(
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -820,7 +820,7 @@ public Builder clearPronunciations() {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -842,7 +842,7 @@ public Builder removePronunciations(int index) {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -858,7 +858,7 @@ public Builder removePronunciations(int index) {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -878,7 +878,7 @@ public Builder removePronunciations(int index) {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -899,7 +899,7 @@ public Builder removePronunciations(int index) {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -917,7 +917,7 @@ public Builder removePronunciations(int index) {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
@@ -936,7 +936,7 @@ public Builder removePronunciations(int index) {
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
*
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationsOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationsOrBuilder.java
index 6be9b64d7dde..71a5c81640dd 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationsOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomPronunciationsOrBuilder.java
@@ -28,7 +28,7 @@ public interface CustomPronunciationsOrBuilder
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -41,7 +41,7 @@ public interface CustomPronunciationsOrBuilder
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -53,7 +53,7 @@ public interface CustomPronunciationsOrBuilder
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -65,7 +65,7 @@ public interface CustomPronunciationsOrBuilder
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
@@ -78,7 +78,7 @@ public interface CustomPronunciationsOrBuilder
*
*
*
- * The pronunciation customizations to be applied.
+ * The pronunciation customizations are applied.
*
*
* repeated .google.cloud.texttospeech.v1beta1.CustomPronunciationParams pronunciations = 1;
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParams.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParams.java
index c66403384689..54ee242cb3c3 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParams.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParams.java
@@ -305,7 +305,7 @@ public com.google.protobuf.ByteString getModelBytes() {
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return The enum numeric value on the wire for reportedUsage.
*/
@java.lang.Override
@@ -326,7 +326,7 @@ public int getReportedUsageValue() {
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return The reportedUsage.
*/
@java.lang.Override
@@ -847,7 +847,7 @@ public Builder setModelBytes(com.google.protobuf.ByteString value) {
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return The enum numeric value on the wire for reportedUsage.
*/
@java.lang.Override
@@ -868,7 +868,7 @@ public int getReportedUsageValue() {
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @param value The enum numeric value on the wire for reportedUsage to set.
* @return This builder for chaining.
*/
@@ -892,7 +892,7 @@ public Builder setReportedUsageValue(int value) {
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return The reportedUsage.
*/
@java.lang.Override
@@ -919,7 +919,7 @@ public Builder setReportedUsageValue(int value) {
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @param value The reportedUsage to set.
* @return This builder for chaining.
*/
@@ -947,7 +947,7 @@ public Builder setReportedUsage(
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return This builder for chaining.
*/
@java.lang.Deprecated
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParamsOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParamsOrBuilder.java
index d770e563d83c..37c84e2e78fb 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParamsOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/CustomVoiceParamsOrBuilder.java
@@ -66,7 +66,7 @@ public interface CustomVoiceParamsOrBuilder
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return The enum numeric value on the wire for reportedUsage.
*/
@java.lang.Deprecated
@@ -84,7 +84,7 @@ public interface CustomVoiceParamsOrBuilder
*
*
* @deprecated google.cloud.texttospeech.v1beta1.CustomVoiceParams.reported_usage is deprecated.
- * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=402
+ * See google/cloud/texttospeech/v1beta1/cloud_tts.proto;l=435
* @return The reportedUsage.
*/
@java.lang.Deprecated
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/MultiSpeakerMarkup.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/MultiSpeakerMarkup.java
index 7a9150f04736..39bb3c016c71 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/MultiSpeakerMarkup.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/MultiSpeakerMarkup.java
@@ -128,7 +128,7 @@ public interface TurnOrBuilder
*
*
*
- * A Multi-speaker turn.
+ * A multi-speaker turn.
*
*
* Protobuf type {@code google.cloud.texttospeech.v1beta1.MultiSpeakerMarkup.Turn}
@@ -453,7 +453,7 @@ protected Builder newBuilderForType(
*
*
*
- * A Multi-speaker turn.
+ * A multi-speaker turn.
*
*
* Protobuf type {@code google.cloud.texttospeech.v1beta1.MultiSpeakerMarkup.Turn}
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfig.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfig.java
index 494faedc0b48..1e116b757595 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfig.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfig.java
@@ -72,8 +72,8 @@ public static final com.google.protobuf.Descriptors.Descriptor getDescriptor() {
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -92,8 +92,8 @@ public int getAudioEncodingValue() {
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -130,6 +130,30 @@ public int getSampleRateHertz() {
return sampleRateHertz_;
}
+ public static final int SPEAKING_RATE_FIELD_NUMBER = 3;
+ private double speakingRate_ = 0D;
+
+ /**
+ *
+ *
+ *
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
+ * the normal native speed supported by the specific voice. 2.0 is twice as
+ * fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
+ *
+ *
+ *
+ * double speaking_rate = 3 [(.google.api.field_behavior) = INPUT_ONLY, (.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return The speakingRate.
+ */
+ @java.lang.Override
+ public double getSpeakingRate() {
+ return speakingRate_;
+ }
+
private byte memoizedIsInitialized = -1;
@java.lang.Override
@@ -152,6 +176,9 @@ public void writeTo(com.google.protobuf.CodedOutputStream output) throws java.io
if (sampleRateHertz_ != 0) {
output.writeInt32(2, sampleRateHertz_);
}
+ if (java.lang.Double.doubleToRawLongBits(speakingRate_) != 0) {
+ output.writeDouble(3, speakingRate_);
+ }
getUnknownFields().writeTo(output);
}
@@ -169,6 +196,9 @@ public int getSerializedSize() {
if (sampleRateHertz_ != 0) {
size += com.google.protobuf.CodedOutputStream.computeInt32Size(2, sampleRateHertz_);
}
+ if (java.lang.Double.doubleToRawLongBits(speakingRate_) != 0) {
+ size += com.google.protobuf.CodedOutputStream.computeDoubleSize(3, speakingRate_);
+ }
size += getUnknownFields().getSerializedSize();
memoizedSize = size;
return size;
@@ -187,6 +217,8 @@ public boolean equals(final java.lang.Object obj) {
if (audioEncoding_ != other.audioEncoding_) return false;
if (getSampleRateHertz() != other.getSampleRateHertz()) return false;
+ if (java.lang.Double.doubleToLongBits(getSpeakingRate())
+ != java.lang.Double.doubleToLongBits(other.getSpeakingRate())) return false;
if (!getUnknownFields().equals(other.getUnknownFields())) return false;
return true;
}
@@ -202,6 +234,11 @@ public int hashCode() {
hash = (53 * hash) + audioEncoding_;
hash = (37 * hash) + SAMPLE_RATE_HERTZ_FIELD_NUMBER;
hash = (53 * hash) + getSampleRateHertz();
+ hash = (37 * hash) + SPEAKING_RATE_FIELD_NUMBER;
+ hash =
+ (53 * hash)
+ + com.google.protobuf.Internal.hashLong(
+ java.lang.Double.doubleToLongBits(getSpeakingRate()));
hash = (29 * hash) + getUnknownFields().hashCode();
memoizedHashCode = hash;
return hash;
@@ -345,6 +382,7 @@ public Builder clear() {
bitField0_ = 0;
audioEncoding_ = 0;
sampleRateHertz_ = 0;
+ speakingRate_ = 0D;
return this;
}
@@ -387,6 +425,9 @@ private void buildPartial0(com.google.cloud.texttospeech.v1beta1.StreamingAudioC
if (((from_bitField0_ & 0x00000002) != 0)) {
result.sampleRateHertz_ = sampleRateHertz_;
}
+ if (((from_bitField0_ & 0x00000004) != 0)) {
+ result.speakingRate_ = speakingRate_;
+ }
}
@java.lang.Override
@@ -441,6 +482,9 @@ public Builder mergeFrom(com.google.cloud.texttospeech.v1beta1.StreamingAudioCon
if (other.getSampleRateHertz() != 0) {
setSampleRateHertz(other.getSampleRateHertz());
}
+ if (other.getSpeakingRate() != 0D) {
+ setSpeakingRate(other.getSpeakingRate());
+ }
this.mergeUnknownFields(other.getUnknownFields());
onChanged();
return this;
@@ -479,6 +523,12 @@ public Builder mergeFrom(
bitField0_ |= 0x00000002;
break;
} // case 16
+ case 25:
+ {
+ speakingRate_ = input.readDouble();
+ bitField0_ |= 0x00000004;
+ break;
+ } // case 25
default:
{
if (!super.parseUnknownField(input, extensionRegistry, tag)) {
@@ -505,8 +555,8 @@ public Builder mergeFrom(
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -525,8 +575,8 @@ public int getAudioEncodingValue() {
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -548,8 +598,8 @@ public Builder setAudioEncodingValue(int value) {
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -572,8 +622,8 @@ public com.google.cloud.texttospeech.v1beta1.AudioEncoding getAudioEncoding() {
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -598,8 +648,8 @@ public Builder setAudioEncoding(com.google.cloud.texttospeech.v1beta1.AudioEncod
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -671,6 +721,77 @@ public Builder clearSampleRateHertz() {
return this;
}
+ private double speakingRate_;
+
+ /**
+ *
+ *
+ *
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
+ * the normal native speed supported by the specific voice. 2.0 is twice as
+ * fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
+ *
+ *
+ *
+ * double speaking_rate = 3 [(.google.api.field_behavior) = INPUT_ONLY, (.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return The speakingRate.
+ */
+ @java.lang.Override
+ public double getSpeakingRate() {
+ return speakingRate_;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
+ * the normal native speed supported by the specific voice. 2.0 is twice as
+ * fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
+ *
+ *
+ *
+ * double speaking_rate = 3 [(.google.api.field_behavior) = INPUT_ONLY, (.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @param value The speakingRate to set.
+ * @return This builder for chaining.
+ */
+ public Builder setSpeakingRate(double value) {
+
+ speakingRate_ = value;
+ bitField0_ |= 0x00000004;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
+ * the normal native speed supported by the specific voice. 2.0 is twice as
+ * fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
+ *
+ *
+ *
+ * double speaking_rate = 3 [(.google.api.field_behavior) = INPUT_ONLY, (.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return This builder for chaining.
+ */
+ public Builder clearSpeakingRate() {
+ bitField0_ = (bitField0_ & ~0x00000004);
+ speakingRate_ = 0D;
+ onChanged();
+ return this;
+ }
+
@java.lang.Override
public final Builder setUnknownFields(final com.google.protobuf.UnknownFieldSet unknownFields) {
return super.setUnknownFields(unknownFields);
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfigOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfigOrBuilder.java
index 5fc35ab1c5aa..554858757e18 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfigOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingAudioConfigOrBuilder.java
@@ -29,8 +29,8 @@ public interface StreamingAudioConfigOrBuilder
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -46,8 +46,8 @@ public interface StreamingAudioConfigOrBuilder
*
*
* Required. The format of the audio byte stream.
- * For now, streaming only supports PCM and OGG_OPUS. All other encodings
- * will return an error.
+ * Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ * return an error.
*
*
*
@@ -70,4 +70,22 @@ public interface StreamingAudioConfigOrBuilder
* @return The sampleRateHertz.
*/
int getSampleRateHertz();
+
+ /**
+ *
+ *
+ *
+ * Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
+ * the normal native speed supported by the specific voice. 2.0 is twice as
+ * fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
+ * speed. Any other values < 0.25 or > 2.0 will return an error.
+ *
+ *
+ *
+ * double speaking_rate = 3 [(.google.api.field_behavior) = INPUT_ONLY, (.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return The speakingRate.
+ */
+ double getSpeakingRate();
}
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInput.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInput.java
index 213e8170aa7b..1de63ec338c2 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInput.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInput.java
@@ -39,7 +39,9 @@ private StreamingSynthesisInput(com.google.protobuf.GeneratedMessageV3.Builder
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -134,9 +139,8 @@ public boolean hasText() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -165,9 +169,8 @@ public java.lang.String getText() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -191,6 +194,151 @@ public com.google.protobuf.ByteString getTextBytes() {
}
}
+ public static final int MARKUP_FIELD_NUMBER = 5;
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return Whether the markup field is set.
+ */
+ public boolean hasMarkup() {
+ return inputSourceCase_ == 5;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The markup.
+ */
+ public java.lang.String getMarkup() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (ref instanceof java.lang.String) {
+ return (java.lang.String) ref;
+ } else {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ if (inputSourceCase_ == 5) {
+ inputSource_ = s;
+ }
+ return s;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The bytes for markup.
+ */
+ public com.google.protobuf.ByteString getMarkupBytes() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (ref instanceof java.lang.String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ if (inputSourceCase_ == 5) {
+ inputSource_ = b;
+ }
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
+ public static final int PROMPT_FIELD_NUMBER = 6;
+
+ @SuppressWarnings("serial")
+ private volatile java.lang.Object prompt_ = "";
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return Whether the prompt field is set.
+ */
+ @java.lang.Override
+ public boolean hasPrompt() {
+ return ((bitField0_ & 0x00000001) != 0);
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return The prompt.
+ */
+ @java.lang.Override
+ public java.lang.String getPrompt() {
+ java.lang.Object ref = prompt_;
+ if (ref instanceof java.lang.String) {
+ return (java.lang.String) ref;
+ } else {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ prompt_ = s;
+ return s;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return The bytes for prompt.
+ */
+ @java.lang.Override
+ public com.google.protobuf.ByteString getPromptBytes() {
+ java.lang.Object ref = prompt_;
+ if (ref instanceof java.lang.String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ prompt_ = b;
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
private byte memoizedIsInitialized = -1;
@java.lang.Override
@@ -208,6 +356,12 @@ public void writeTo(com.google.protobuf.CodedOutputStream output) throws java.io
if (inputSourceCase_ == 1) {
com.google.protobuf.GeneratedMessageV3.writeString(output, 1, inputSource_);
}
+ if (inputSourceCase_ == 5) {
+ com.google.protobuf.GeneratedMessageV3.writeString(output, 5, inputSource_);
+ }
+ if (((bitField0_ & 0x00000001) != 0)) {
+ com.google.protobuf.GeneratedMessageV3.writeString(output, 6, prompt_);
+ }
getUnknownFields().writeTo(output);
}
@@ -220,6 +374,12 @@ public int getSerializedSize() {
if (inputSourceCase_ == 1) {
size += com.google.protobuf.GeneratedMessageV3.computeStringSize(1, inputSource_);
}
+ if (inputSourceCase_ == 5) {
+ size += com.google.protobuf.GeneratedMessageV3.computeStringSize(5, inputSource_);
+ }
+ if (((bitField0_ & 0x00000001) != 0)) {
+ size += com.google.protobuf.GeneratedMessageV3.computeStringSize(6, prompt_);
+ }
size += getUnknownFields().getSerializedSize();
memoizedSize = size;
return size;
@@ -236,11 +396,18 @@ public boolean equals(final java.lang.Object obj) {
com.google.cloud.texttospeech.v1beta1.StreamingSynthesisInput other =
(com.google.cloud.texttospeech.v1beta1.StreamingSynthesisInput) obj;
+ if (hasPrompt() != other.hasPrompt()) return false;
+ if (hasPrompt()) {
+ if (!getPrompt().equals(other.getPrompt())) return false;
+ }
if (!getInputSourceCase().equals(other.getInputSourceCase())) return false;
switch (inputSourceCase_) {
case 1:
if (!getText().equals(other.getText())) return false;
break;
+ case 5:
+ if (!getMarkup().equals(other.getMarkup())) return false;
+ break;
case 0:
default:
}
@@ -255,11 +422,19 @@ public int hashCode() {
}
int hash = 41;
hash = (19 * hash) + getDescriptor().hashCode();
+ if (hasPrompt()) {
+ hash = (37 * hash) + PROMPT_FIELD_NUMBER;
+ hash = (53 * hash) + getPrompt().hashCode();
+ }
switch (inputSourceCase_) {
case 1:
hash = (37 * hash) + TEXT_FIELD_NUMBER;
hash = (53 * hash) + getText().hashCode();
break;
+ case 5:
+ hash = (37 * hash) + MARKUP_FIELD_NUMBER;
+ hash = (53 * hash) + getMarkup().hashCode();
+ break;
case 0:
default:
}
@@ -404,6 +579,7 @@ private Builder(com.google.protobuf.GeneratedMessageV3.BuilderParent parent) {
public Builder clear() {
super.clear();
bitField0_ = 0;
+ prompt_ = "";
inputSourceCase_ = 0;
inputSource_ = null;
return this;
@@ -445,6 +621,12 @@ public com.google.cloud.texttospeech.v1beta1.StreamingSynthesisInput buildPartia
private void buildPartial0(
com.google.cloud.texttospeech.v1beta1.StreamingSynthesisInput result) {
int from_bitField0_ = bitField0_;
+ int to_bitField0_ = 0;
+ if (((from_bitField0_ & 0x00000004) != 0)) {
+ result.prompt_ = prompt_;
+ to_bitField0_ |= 0x00000001;
+ }
+ result.bitField0_ |= to_bitField0_;
}
private void buildPartialOneofs(
@@ -500,6 +682,11 @@ public Builder mergeFrom(com.google.cloud.texttospeech.v1beta1.StreamingSynthesi
if (other
== com.google.cloud.texttospeech.v1beta1.StreamingSynthesisInput.getDefaultInstance())
return this;
+ if (other.hasPrompt()) {
+ prompt_ = other.prompt_;
+ bitField0_ |= 0x00000004;
+ onChanged();
+ }
switch (other.getInputSourceCase()) {
case TEXT:
{
@@ -508,6 +695,13 @@ public Builder mergeFrom(com.google.cloud.texttospeech.v1beta1.StreamingSynthesi
onChanged();
break;
}
+ case MARKUP:
+ {
+ inputSourceCase_ = 5;
+ inputSource_ = other.inputSource_;
+ onChanged();
+ break;
+ }
case INPUTSOURCE_NOT_SET:
{
break;
@@ -546,6 +740,19 @@ public Builder mergeFrom(
inputSource_ = s;
break;
} // case 10
+ case 42:
+ {
+ java.lang.String s = input.readStringRequireUtf8();
+ inputSourceCase_ = 5;
+ inputSource_ = s;
+ break;
+ } // case 42
+ case 50:
+ {
+ prompt_ = input.readStringRequireUtf8();
+ bitField0_ |= 0x00000004;
+ break;
+ } // case 50
default:
{
if (!super.parseUnknownField(input, extensionRegistry, tag)) {
@@ -584,9 +791,8 @@ public Builder clearInputSource() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -603,9 +809,8 @@ public boolean hasText() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -635,9 +840,8 @@ public java.lang.String getText() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -667,9 +871,8 @@ public com.google.protobuf.ByteString getTextBytes() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -692,9 +895,8 @@ public Builder setText(java.lang.String value) {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -715,9 +917,8 @@ public Builder clearText() {
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -736,6 +937,277 @@ public Builder setTextBytes(com.google.protobuf.ByteString value) {
return this;
}
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return Whether the markup field is set.
+ */
+ @java.lang.Override
+ public boolean hasMarkup() {
+ return inputSourceCase_ == 5;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The markup.
+ */
+ @java.lang.Override
+ public java.lang.String getMarkup() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (!(ref instanceof java.lang.String)) {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ if (inputSourceCase_ == 5) {
+ inputSource_ = s;
+ }
+ return s;
+ } else {
+ return (java.lang.String) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The bytes for markup.
+ */
+ @java.lang.Override
+ public com.google.protobuf.ByteString getMarkupBytes() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (ref instanceof String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ if (inputSourceCase_ == 5) {
+ inputSource_ = b;
+ }
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @param value The markup to set.
+ * @return This builder for chaining.
+ */
+ public Builder setMarkup(java.lang.String value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ inputSourceCase_ = 5;
+ inputSource_ = value;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return This builder for chaining.
+ */
+ public Builder clearMarkup() {
+ if (inputSourceCase_ == 5) {
+ inputSourceCase_ = 0;
+ inputSource_ = null;
+ onChanged();
+ }
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @param value The bytes for markup to set.
+ * @return This builder for chaining.
+ */
+ public Builder setMarkupBytes(com.google.protobuf.ByteString value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ checkByteStringIsUtf8(value);
+ inputSourceCase_ = 5;
+ inputSource_ = value;
+ onChanged();
+ return this;
+ }
+
+ private java.lang.Object prompt_ = "";
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return Whether the prompt field is set.
+ */
+ public boolean hasPrompt() {
+ return ((bitField0_ & 0x00000004) != 0);
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return The prompt.
+ */
+ public java.lang.String getPrompt() {
+ java.lang.Object ref = prompt_;
+ if (!(ref instanceof java.lang.String)) {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ prompt_ = s;
+ return s;
+ } else {
+ return (java.lang.String) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return The bytes for prompt.
+ */
+ public com.google.protobuf.ByteString getPromptBytes() {
+ java.lang.Object ref = prompt_;
+ if (ref instanceof String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ prompt_ = b;
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @param value The prompt to set.
+ * @return This builder for chaining.
+ */
+ public Builder setPrompt(java.lang.String value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ prompt_ = value;
+ bitField0_ |= 0x00000004;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return This builder for chaining.
+ */
+ public Builder clearPrompt() {
+ prompt_ = getDefaultInstance().getPrompt();
+ bitField0_ = (bitField0_ & ~0x00000004);
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @param value The bytes for prompt to set.
+ * @return This builder for chaining.
+ */
+ public Builder setPromptBytes(com.google.protobuf.ByteString value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ checkByteStringIsUtf8(value);
+ prompt_ = value;
+ bitField0_ |= 0x00000004;
+ onChanged();
+ return this;
+ }
+
@java.lang.Override
public final Builder setUnknownFields(final com.google.protobuf.UnknownFieldSet unknownFields) {
return super.setUnknownFields(unknownFields);
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInputOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInputOrBuilder.java
index 9aa5f2b75cd5..793efa2ed3b8 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInputOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesisInputOrBuilder.java
@@ -29,9 +29,8 @@ public interface StreamingSynthesisInputOrBuilder
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -45,9 +44,8 @@ public interface StreamingSynthesisInputOrBuilder
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -61,9 +59,8 @@ public interface StreamingSynthesisInputOrBuilder
*
*
* The raw text to be synthesized. It is recommended that each input
- * contains complete, terminating sentences, as this will likely result in
- * better prosody in the output audio. That being said, users are free to
- * input text however they please.
+ * contains complete, terminating sentences, which results in better prosody
+ * in the output audio.
*
*
* string text = 1;
@@ -72,6 +69,87 @@ public interface StreamingSynthesisInputOrBuilder
*/
com.google.protobuf.ByteString getTextBytes();
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return Whether the markup field is set.
+ */
+ boolean hasMarkup();
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The markup.
+ */
+ java.lang.String getMarkup();
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The bytes for markup.
+ */
+ com.google.protobuf.ByteString getMarkupBytes();
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return Whether the prompt field is set.
+ */
+ boolean hasPrompt();
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return The prompt.
+ */
+ java.lang.String getPrompt();
+
+ /**
+ *
+ *
+ *
+ * This is system instruction supported only for controllable voice models.
+ *
+ *
+ * optional string prompt = 6;
+ *
+ * @return The bytes for prompt.
+ */
+ com.google.protobuf.ByteString getPromptBytes();
+
com.google.cloud.texttospeech.v1beta1.StreamingSynthesisInput.InputSourceCase
getInputSourceCase();
}
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfig.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfig.java
index 206782e70a8c..c523ade03557 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfig.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfig.java
@@ -182,6 +182,93 @@ public com.google.cloud.texttospeech.v1beta1.StreamingAudioConfig getStreamingAu
: streamingAudioConfig_;
}
+ public static final int CUSTOM_PRONUNCIATIONS_FIELD_NUMBER = 5;
+ private com.google.cloud.texttospeech.v1beta1.CustomPronunciations customPronunciations_;
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return Whether the customPronunciations field is set.
+ */
+ @java.lang.Override
+ public boolean hasCustomPronunciations() {
+ return ((bitField0_ & 0x00000004) != 0);
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return The customPronunciations.
+ */
+ @java.lang.Override
+ public com.google.cloud.texttospeech.v1beta1.CustomPronunciations getCustomPronunciations() {
+ return customPronunciations_ == null
+ ? com.google.cloud.texttospeech.v1beta1.CustomPronunciations.getDefaultInstance()
+ : customPronunciations_;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ @java.lang.Override
+ public com.google.cloud.texttospeech.v1beta1.CustomPronunciationsOrBuilder
+ getCustomPronunciationsOrBuilder() {
+ return customPronunciations_ == null
+ ? com.google.cloud.texttospeech.v1beta1.CustomPronunciations.getDefaultInstance()
+ : customPronunciations_;
+ }
+
private byte memoizedIsInitialized = -1;
@java.lang.Override
@@ -202,6 +289,9 @@ public void writeTo(com.google.protobuf.CodedOutputStream output) throws java.io
if (((bitField0_ & 0x00000002) != 0)) {
output.writeMessage(4, getStreamingAudioConfig());
}
+ if (((bitField0_ & 0x00000004) != 0)) {
+ output.writeMessage(5, getCustomPronunciations());
+ }
getUnknownFields().writeTo(output);
}
@@ -218,6 +308,10 @@ public int getSerializedSize() {
size +=
com.google.protobuf.CodedOutputStream.computeMessageSize(4, getStreamingAudioConfig());
}
+ if (((bitField0_ & 0x00000004) != 0)) {
+ size +=
+ com.google.protobuf.CodedOutputStream.computeMessageSize(5, getCustomPronunciations());
+ }
size += getUnknownFields().getSerializedSize();
memoizedSize = size;
return size;
@@ -242,6 +336,10 @@ public boolean equals(final java.lang.Object obj) {
if (hasStreamingAudioConfig()) {
if (!getStreamingAudioConfig().equals(other.getStreamingAudioConfig())) return false;
}
+ if (hasCustomPronunciations() != other.hasCustomPronunciations()) return false;
+ if (hasCustomPronunciations()) {
+ if (!getCustomPronunciations().equals(other.getCustomPronunciations())) return false;
+ }
if (!getUnknownFields().equals(other.getUnknownFields())) return false;
return true;
}
@@ -261,6 +359,10 @@ public int hashCode() {
hash = (37 * hash) + STREAMING_AUDIO_CONFIG_FIELD_NUMBER;
hash = (53 * hash) + getStreamingAudioConfig().hashCode();
}
+ if (hasCustomPronunciations()) {
+ hash = (37 * hash) + CUSTOM_PRONUNCIATIONS_FIELD_NUMBER;
+ hash = (53 * hash) + getCustomPronunciations().hashCode();
+ }
hash = (29 * hash) + getUnknownFields().hashCode();
memoizedHashCode = hash;
return hash;
@@ -405,6 +507,7 @@ private void maybeForceBuilderInitialization() {
if (com.google.protobuf.GeneratedMessageV3.alwaysUseFieldBuilders) {
getVoiceFieldBuilder();
getStreamingAudioConfigFieldBuilder();
+ getCustomPronunciationsFieldBuilder();
}
}
@@ -422,6 +525,11 @@ public Builder clear() {
streamingAudioConfigBuilder_.dispose();
streamingAudioConfigBuilder_ = null;
}
+ customPronunciations_ = null;
+ if (customPronunciationsBuilder_ != null) {
+ customPronunciationsBuilder_.dispose();
+ customPronunciationsBuilder_ = null;
+ }
return this;
}
@@ -472,6 +580,13 @@ private void buildPartial0(
: streamingAudioConfigBuilder_.build();
to_bitField0_ |= 0x00000002;
}
+ if (((from_bitField0_ & 0x00000004) != 0)) {
+ result.customPronunciations_ =
+ customPronunciationsBuilder_ == null
+ ? customPronunciations_
+ : customPronunciationsBuilder_.build();
+ to_bitField0_ |= 0x00000004;
+ }
result.bitField0_ |= to_bitField0_;
}
@@ -529,6 +644,9 @@ public Builder mergeFrom(
if (other.hasStreamingAudioConfig()) {
mergeStreamingAudioConfig(other.getStreamingAudioConfig());
}
+ if (other.hasCustomPronunciations()) {
+ mergeCustomPronunciations(other.getCustomPronunciations());
+ }
this.mergeUnknownFields(other.getUnknownFields());
onChanged();
return this;
@@ -568,6 +686,13 @@ public Builder mergeFrom(
bitField0_ |= 0x00000002;
break;
} // case 34
+ case 42:
+ {
+ input.readMessage(
+ getCustomPronunciationsFieldBuilder().getBuilder(), extensionRegistry);
+ bitField0_ |= 0x00000004;
+ break;
+ } // case 42
default:
{
if (!super.parseUnknownField(input, extensionRegistry, tag)) {
@@ -1021,6 +1146,306 @@ public Builder clearStreamingAudioConfig() {
return streamingAudioConfigBuilder_;
}
+ private com.google.cloud.texttospeech.v1beta1.CustomPronunciations customPronunciations_;
+ private com.google.protobuf.SingleFieldBuilderV3<
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations,
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations.Builder,
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciationsOrBuilder>
+ customPronunciationsBuilder_;
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return Whether the customPronunciations field is set.
+ */
+ public boolean hasCustomPronunciations() {
+ return ((bitField0_ & 0x00000004) != 0);
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return The customPronunciations.
+ */
+ public com.google.cloud.texttospeech.v1beta1.CustomPronunciations getCustomPronunciations() {
+ if (customPronunciationsBuilder_ == null) {
+ return customPronunciations_ == null
+ ? com.google.cloud.texttospeech.v1beta1.CustomPronunciations.getDefaultInstance()
+ : customPronunciations_;
+ } else {
+ return customPronunciationsBuilder_.getMessage();
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ public Builder setCustomPronunciations(
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations value) {
+ if (customPronunciationsBuilder_ == null) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ customPronunciations_ = value;
+ } else {
+ customPronunciationsBuilder_.setMessage(value);
+ }
+ bitField0_ |= 0x00000004;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ public Builder setCustomPronunciations(
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations.Builder builderForValue) {
+ if (customPronunciationsBuilder_ == null) {
+ customPronunciations_ = builderForValue.build();
+ } else {
+ customPronunciationsBuilder_.setMessage(builderForValue.build());
+ }
+ bitField0_ |= 0x00000004;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ public Builder mergeCustomPronunciations(
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations value) {
+ if (customPronunciationsBuilder_ == null) {
+ if (((bitField0_ & 0x00000004) != 0)
+ && customPronunciations_ != null
+ && customPronunciations_
+ != com.google.cloud.texttospeech.v1beta1.CustomPronunciations
+ .getDefaultInstance()) {
+ getCustomPronunciationsBuilder().mergeFrom(value);
+ } else {
+ customPronunciations_ = value;
+ }
+ } else {
+ customPronunciationsBuilder_.mergeFrom(value);
+ }
+ if (customPronunciations_ != null) {
+ bitField0_ |= 0x00000004;
+ onChanged();
+ }
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ public Builder clearCustomPronunciations() {
+ bitField0_ = (bitField0_ & ~0x00000004);
+ customPronunciations_ = null;
+ if (customPronunciationsBuilder_ != null) {
+ customPronunciationsBuilder_.dispose();
+ customPronunciationsBuilder_ = null;
+ }
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ public com.google.cloud.texttospeech.v1beta1.CustomPronunciations.Builder
+ getCustomPronunciationsBuilder() {
+ bitField0_ |= 0x00000004;
+ onChanged();
+ return getCustomPronunciationsFieldBuilder().getBuilder();
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ public com.google.cloud.texttospeech.v1beta1.CustomPronunciationsOrBuilder
+ getCustomPronunciationsOrBuilder() {
+ if (customPronunciationsBuilder_ != null) {
+ return customPronunciationsBuilder_.getMessageOrBuilder();
+ } else {
+ return customPronunciations_ == null
+ ? com.google.cloud.texttospeech.v1beta1.CustomPronunciations.getDefaultInstance()
+ : customPronunciations_;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ private com.google.protobuf.SingleFieldBuilderV3<
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations,
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations.Builder,
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciationsOrBuilder>
+ getCustomPronunciationsFieldBuilder() {
+ if (customPronunciationsBuilder_ == null) {
+ customPronunciationsBuilder_ =
+ new com.google.protobuf.SingleFieldBuilderV3<
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations,
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations.Builder,
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciationsOrBuilder>(
+ getCustomPronunciations(), getParentForChildren(), isClean());
+ customPronunciations_ = null;
+ }
+ return customPronunciationsBuilder_;
+ }
+
@java.lang.Override
public final Builder setUnknownFields(final com.google.protobuf.UnknownFieldSet unknownFields) {
return super.setUnknownFields(unknownFields);
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfigOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfigOrBuilder.java
index cc325e3c7b25..e3c6ea93c016 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfigOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/StreamingSynthesizeConfigOrBuilder.java
@@ -110,4 +110,75 @@ public interface StreamingSynthesizeConfigOrBuilder
*/
com.google.cloud.texttospeech.v1beta1.StreamingAudioConfigOrBuilder
getStreamingAudioConfigOrBuilder();
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return Whether the customPronunciations field is set.
+ */
+ boolean hasCustomPronunciations();
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ *
+ * @return The customPronunciations.
+ */
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciations getCustomPronunciations();
+
+ /**
+ *
+ *
+ *
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
+ * customizations.
+ *
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
+ *
+ * In order to customize the pronunciation of a phrase, there must be an exact
+ * match of the phrase in the input types. If using SSML, the phrase must not
+ * be inside a phoneme tag.
+ *
+ *
+ *
+ * .google.cloud.texttospeech.v1beta1.CustomPronunciations custom_pronunciations = 5 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ */
+ com.google.cloud.texttospeech.v1beta1.CustomPronunciationsOrBuilder
+ getCustomPronunciationsOrBuilder();
}
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInput.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInput.java
index df509343e9d0..372e7933134f 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInput.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInput.java
@@ -76,6 +76,7 @@ public enum InputSourceCase
com.google.protobuf.Internal.EnumLite,
com.google.protobuf.AbstractMessage.InternalOneOfEnum {
TEXT(1),
+ MARKUP(5),
SSML(2),
MULTI_SPEAKER_MARKUP(4),
INPUTSOURCE_NOT_SET(0);
@@ -99,6 +100,8 @@ public static InputSourceCase forNumber(int value) {
switch (value) {
case 1:
return TEXT;
+ case 5:
+ return MARKUP;
case 2:
return SSML;
case 4:
@@ -192,6 +195,82 @@ public com.google.protobuf.ByteString getTextBytes() {
}
}
+ public static final int MARKUP_FIELD_NUMBER = 5;
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return Whether the markup field is set.
+ */
+ public boolean hasMarkup() {
+ return inputSourceCase_ == 5;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The markup.
+ */
+ public java.lang.String getMarkup() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (ref instanceof java.lang.String) {
+ return (java.lang.String) ref;
+ } else {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ if (inputSourceCase_ == 5) {
+ inputSource_ = s;
+ }
+ return s;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The bytes for markup.
+ */
+ public com.google.protobuf.ByteString getMarkupBytes() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (ref instanceof java.lang.String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ if (inputSourceCase_ == 5) {
+ inputSource_ = b;
+ }
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
public static final int SSML_FIELD_NUMBER = 2;
/**
@@ -342,18 +421,16 @@ public com.google.cloud.texttospeech.v1beta1.MultiSpeakerMarkup getMultiSpeakerM
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -371,18 +448,16 @@ public boolean hasCustomPronunciations() {
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -402,18 +477,16 @@ public com.google.cloud.texttospeech.v1beta1.CustomPronunciations getCustomPronu
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -455,6 +528,9 @@ public void writeTo(com.google.protobuf.CodedOutputStream output) throws java.io
output.writeMessage(
4, (com.google.cloud.texttospeech.v1beta1.MultiSpeakerMarkup) inputSource_);
}
+ if (inputSourceCase_ == 5) {
+ com.google.protobuf.GeneratedMessageV3.writeString(output, 5, inputSource_);
+ }
getUnknownFields().writeTo(output);
}
@@ -479,6 +555,9 @@ public int getSerializedSize() {
com.google.protobuf.CodedOutputStream.computeMessageSize(
4, (com.google.cloud.texttospeech.v1beta1.MultiSpeakerMarkup) inputSource_);
}
+ if (inputSourceCase_ == 5) {
+ size += com.google.protobuf.GeneratedMessageV3.computeStringSize(5, inputSource_);
+ }
size += getUnknownFields().getSerializedSize();
memoizedSize = size;
return size;
@@ -504,6 +583,9 @@ public boolean equals(final java.lang.Object obj) {
case 1:
if (!getText().equals(other.getText())) return false;
break;
+ case 5:
+ if (!getMarkup().equals(other.getMarkup())) return false;
+ break;
case 2:
if (!getSsml().equals(other.getSsml())) return false;
break;
@@ -533,6 +615,10 @@ public int hashCode() {
hash = (37 * hash) + TEXT_FIELD_NUMBER;
hash = (53 * hash) + getText().hashCode();
break;
+ case 5:
+ hash = (37 * hash) + MARKUP_FIELD_NUMBER;
+ hash = (53 * hash) + getMarkup().hashCode();
+ break;
case 2:
hash = (37 * hash) + SSML_FIELD_NUMBER;
hash = (53 * hash) + getSsml().hashCode();
@@ -744,7 +830,7 @@ public com.google.cloud.texttospeech.v1beta1.SynthesisInput buildPartial() {
private void buildPartial0(com.google.cloud.texttospeech.v1beta1.SynthesisInput result) {
int from_bitField0_ = bitField0_;
int to_bitField0_ = 0;
- if (((from_bitField0_ & 0x00000008) != 0)) {
+ if (((from_bitField0_ & 0x00000010) != 0)) {
result.customPronunciations_ =
customPronunciationsBuilder_ == null
? customPronunciations_
@@ -819,6 +905,13 @@ public Builder mergeFrom(com.google.cloud.texttospeech.v1beta1.SynthesisInput ot
onChanged();
break;
}
+ case MARKUP:
+ {
+ inputSourceCase_ = 5;
+ inputSource_ = other.inputSource_;
+ onChanged();
+ break;
+ }
case SSML:
{
inputSourceCase_ = 2;
@@ -880,7 +973,7 @@ public Builder mergeFrom(
{
input.readMessage(
getCustomPronunciationsFieldBuilder().getBuilder(), extensionRegistry);
- bitField0_ |= 0x00000008;
+ bitField0_ |= 0x00000010;
break;
} // case 26
case 34:
@@ -890,6 +983,13 @@ public Builder mergeFrom(
inputSourceCase_ = 4;
break;
} // case 34
+ case 42:
+ {
+ java.lang.String s = input.readStringRequireUtf8();
+ inputSourceCase_ = 5;
+ inputSource_ = s;
+ break;
+ } // case 42
default:
{
if (!super.parseUnknownField(input, extensionRegistry, tag)) {
@@ -1062,6 +1162,151 @@ public Builder setTextBytes(com.google.protobuf.ByteString value) {
return this;
}
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return Whether the markup field is set.
+ */
+ @java.lang.Override
+ public boolean hasMarkup() {
+ return inputSourceCase_ == 5;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The markup.
+ */
+ @java.lang.Override
+ public java.lang.String getMarkup() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (!(ref instanceof java.lang.String)) {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ if (inputSourceCase_ == 5) {
+ inputSource_ = s;
+ }
+ return s;
+ } else {
+ return (java.lang.String) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The bytes for markup.
+ */
+ @java.lang.Override
+ public com.google.protobuf.ByteString getMarkupBytes() {
+ java.lang.Object ref = "";
+ if (inputSourceCase_ == 5) {
+ ref = inputSource_;
+ }
+ if (ref instanceof String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ if (inputSourceCase_ == 5) {
+ inputSource_ = b;
+ }
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @param value The markup to set.
+ * @return This builder for chaining.
+ */
+ public Builder setMarkup(java.lang.String value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ inputSourceCase_ = 5;
+ inputSource_ = value;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return This builder for chaining.
+ */
+ public Builder clearMarkup() {
+ if (inputSourceCase_ == 5) {
+ inputSourceCase_ = 0;
+ inputSource_ = null;
+ onChanged();
+ }
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @param value The bytes for markup to set.
+ * @return This builder for chaining.
+ */
+ public Builder setMarkupBytes(com.google.protobuf.ByteString value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ checkByteStringIsUtf8(value);
+ inputSourceCase_ = 5;
+ inputSource_ = value;
+ onChanged();
+ return this;
+ }
+
/**
*
*
@@ -1469,18 +1714,16 @@ public Builder clearMultiSpeakerMarkup() {
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1490,25 +1733,23 @@ public Builder clearMultiSpeakerMarkup() {
* @return Whether the customPronunciations field is set.
*/
public boolean hasCustomPronunciations() {
- return ((bitField0_ & 0x00000008) != 0);
+ return ((bitField0_ & 0x00000010) != 0);
}
/**
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1531,18 +1772,16 @@ public com.google.cloud.texttospeech.v1beta1.CustomPronunciations getCustomPronu
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1559,7 +1798,7 @@ public Builder setCustomPronunciations(
} else {
customPronunciationsBuilder_.setMessage(value);
}
- bitField0_ |= 0x00000008;
+ bitField0_ |= 0x00000010;
onChanged();
return this;
}
@@ -1568,18 +1807,16 @@ public Builder setCustomPronunciations(
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1593,7 +1830,7 @@ public Builder setCustomPronunciations(
} else {
customPronunciationsBuilder_.setMessage(builderForValue.build());
}
- bitField0_ |= 0x00000008;
+ bitField0_ |= 0x00000010;
onChanged();
return this;
}
@@ -1602,18 +1839,16 @@ public Builder setCustomPronunciations(
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1623,7 +1858,7 @@ public Builder setCustomPronunciations(
public Builder mergeCustomPronunciations(
com.google.cloud.texttospeech.v1beta1.CustomPronunciations value) {
if (customPronunciationsBuilder_ == null) {
- if (((bitField0_ & 0x00000008) != 0)
+ if (((bitField0_ & 0x00000010) != 0)
&& customPronunciations_ != null
&& customPronunciations_
!= com.google.cloud.texttospeech.v1beta1.CustomPronunciations
@@ -1636,7 +1871,7 @@ public Builder mergeCustomPronunciations(
customPronunciationsBuilder_.mergeFrom(value);
}
if (customPronunciations_ != null) {
- bitField0_ |= 0x00000008;
+ bitField0_ |= 0x00000010;
onChanged();
}
return this;
@@ -1646,18 +1881,16 @@ public Builder mergeCustomPronunciations(
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1665,7 +1898,7 @@ public Builder mergeCustomPronunciations(
*
*/
public Builder clearCustomPronunciations() {
- bitField0_ = (bitField0_ & ~0x00000008);
+ bitField0_ = (bitField0_ & ~0x00000010);
customPronunciations_ = null;
if (customPronunciationsBuilder_ != null) {
customPronunciationsBuilder_.dispose();
@@ -1679,18 +1912,16 @@ public Builder clearCustomPronunciations() {
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1699,7 +1930,7 @@ public Builder clearCustomPronunciations() {
*/
public com.google.cloud.texttospeech.v1beta1.CustomPronunciations.Builder
getCustomPronunciationsBuilder() {
- bitField0_ |= 0x00000008;
+ bitField0_ |= 0x00000010;
onChanged();
return getCustomPronunciationsFieldBuilder().getBuilder();
}
@@ -1708,18 +1939,16 @@ public Builder clearCustomPronunciations() {
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -1741,18 +1970,16 @@ public Builder clearCustomPronunciations() {
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInputOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInputOrBuilder.java
index 8f27b3476b7f..8e6a92c92b3e 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInputOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/SynthesisInputOrBuilder.java
@@ -63,6 +63,48 @@ public interface SynthesisInputOrBuilder
*/
com.google.protobuf.ByteString getTextBytes();
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return Whether the markup field is set.
+ */
+ boolean hasMarkup();
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The markup.
+ */
+ java.lang.String getMarkup();
+
+ /**
+ *
+ *
+ *
+ * Markup for HD voices specifically. This field may not be used with any
+ * other voices.
+ *
+ *
+ * string markup = 5;
+ *
+ * @return The bytes for markup.
+ */
+ com.google.protobuf.ByteString getMarkupBytes();
+
/**
*
*
@@ -159,18 +201,16 @@ public interface SynthesisInputOrBuilder
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -185,18 +225,16 @@ public interface SynthesisInputOrBuilder
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
@@ -211,18 +249,16 @@ public interface SynthesisInputOrBuilder
*
*
*
- * Optional. The pronunciation customizations to be applied to the input. If
- * this is set, the input will be synthesized using the given pronunciation
+ * Optional. The pronunciation customizations are applied to the input. If
+ * this is set, the input is synthesized using the given pronunciation
* customizations.
*
- * The initial support will be for EFIGS (English, French,
- * Italian, German, Spanish) languages, as provided in
- * VoiceSelectionParams. Journey and Instant Clone voices are
- * not supported yet.
+ * The initial support is for en-us, with plans to expand to other locales in
+ * the future. Instant Clone voices aren't supported.
*
* In order to customize the pronunciation of a phrase, there must be an exact
* match of the phrase in the input types. If using SSML, the phrase must not
- * be inside a phoneme tag (entirely or partially).
+ * be inside a phoneme tag.
*
*
*
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechProto.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechProto.java
index cebb0973ca76..212f06d36ed1 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechProto.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/TextToSpeechProto.java
@@ -154,48 +154,52 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
+ "TimepointType\022\036\n"
+ "\032TIMEPOINT_TYPE_UNSPECIFIED\020\000\022\r\n"
+ "\tSSML_MARK\020\001B\031\n"
- + "\027_advanced_voice_options\"\337\002\n"
+ + "\027_advanced_voice_options\"\247\003\n"
+ "\031CustomPronunciationParams\022\023\n"
+ "\006phrase\030\001 \001(\tH\000\210\001\001\022m\n"
+ "\021phonetic_encoding\030\002 \001(\0162M.google.cloud.texttospeech.v1bet"
+ "a1.CustomPronunciationParams.PhoneticEncodingH\001\210\001\001\022\032\n\r"
- + "pronunciation\030\003 \001(\tH\002\210\001\001\"o\n"
+ + "pronunciation\030\003 \001(\tH\002\210\001\001\"\266\001\n"
+ "\020PhoneticEncoding\022!\n"
+ "\035PHONETIC_ENCODING_UNSPECIFIED\020\000\022\031\n"
+ "\025PHONETIC_ENCODING_IPA\020\001\022\035\n"
- + "\031PHONETIC_ENCODING_X_SAMPA\020\002B\t\n"
+ + "\031PHONETIC_ENCODING_X_SAMPA\020\002\022\'\n"
+ + "#PHONETIC_ENCODING_JAPANESE_YOMIGANA\020\003\022\034\n"
+ + "\030PHONETIC_ENCODING_PINYIN\020\004B\t\n"
+ "\007_phraseB\024\n"
+ "\022_phonetic_encodingB\020\n"
+ "\016_pronunciation\"l\n"
+ "\024CustomPronunciations\022T\n"
- + "\016pronunciations\030\001"
- + " \003(\0132<.google.cloud.texttospeech.v1beta1.CustomPronunciationParams\"\225\001\n"
+ + "\016pronunciations\030\001 \003"
+ + "(\0132<.google.cloud.texttospeech.v1beta1.CustomPronunciationParams\"\225\001\n"
+ "\022MultiSpeakerMarkup\022N\n"
- + "\005turns\030\001 \003(\0132:.google."
- + "cloud.texttospeech.v1beta1.MultiSpeakerMarkup.TurnB\003\340A\002\032/\n"
+ + "\005turns\030\001 \003(\0132:.google.cloud.te"
+ + "xttospeech.v1beta1.MultiSpeakerMarkup.TurnB\003\340A\002\032/\n"
+ "\004Turn\022\024\n"
+ "\007speaker\030\001 \001(\tB\003\340A\002\022\021\n"
- + "\004text\030\002 \001(\tB\003\340A\002\"\364\001\n"
+ + "\004text\030\002 \001(\tB\003\340A\002\"\206\002\n"
+ "\016SynthesisInput\022\016\n"
- + "\004text\030\001 \001(\tH\000\022\016\n"
+ + "\004text\030\001 \001(\tH\000\022\020\n"
+ + "\006markup\030\005 \001(\tH\000\022\016\n"
+ "\004ssml\030\002 \001(\tH\000\022U\n"
- + "\024multi_speaker_markup\030\004 \001(\01325.google.cloud"
- + ".texttospeech.v1beta1.MultiSpeakerMarkupH\000\022[\n"
- + "\025custom_pronunciations\030\003 \001(\01327.goog"
- + "le.cloud.texttospeech.v1beta1.CustomPronunciationsB\003\340A\001B\016\n"
- + "\014input_source\"\244\002\n"
+ + "\024multi_speaker_markup\030\004 \001(\01325.go"
+ + "ogle.cloud.texttospeech.v1beta1.MultiSpeakerMarkupH\000\022[\n"
+ + "\025custom_pronunciations\030\003 "
+ + "\001(\01327.google.cloud.texttospeech.v1beta1.CustomPronunciationsB\003\340A\001B\016\n"
+ + "\014input_source\"\275\002\n"
+ "\024VoiceSelectionParams\022\032\n\r"
+ "language_code\030\001 \001(\tB\003\340A\002\022\014\n"
+ "\004name\030\002 \001(\t\022G\n"
- + "\013ssml_gender\030\003 \001(\0162"
- + "2.google.cloud.texttospeech.v1beta1.SsmlVoiceGender\022J\n"
- + "\014custom_voice\030\004 \001(\01324.goog"
- + "le.cloud.texttospeech.v1beta1.CustomVoiceParams\022M\n"
- + "\013voice_clone\030\005 \001(\01323.google.cl"
- + "oud.texttospeech.v1beta1.VoiceCloneParamsB\003\340A\001\"\366\001\n"
+ + "\013ssml_gender\030\003"
+ + " \001(\01622.google.cloud.texttospeech.v1beta1.SsmlVoiceGender\022J\n"
+ + "\014custom_voice\030\004 "
+ + "\001(\01324.google.cloud.texttospeech.v1beta1.CustomVoiceParams\022M\n"
+ + "\013voice_clone\030\005 \001(\01323"
+ + ".google.cloud.texttospeech.v1beta1.VoiceCloneParamsB\003\340A\001\022\027\n\n"
+ + "model_name\030\006 \001(\tB\003\340A\001\"\366\001\n"
+ "\013AudioConfig\022M\n"
- + "\016audio_encoding\030\001"
- + " \001(\01620.google.cloud.texttospeech.v1beta1.AudioEncodingB\003\340A\002\022\035\n\r"
+ + "\016audio_encoding\030\001 \001("
+ + "\01620.google.cloud.texttospeech.v1beta1.AudioEncodingB\003\340A\002\022\035\n\r"
+ "speaking_rate\030\002 \001(\001B\006\340A\004\340A\001\022\025\n"
+ "\005pitch\030\003 \001(\001B\006\340A\004\340A\001\022\036\n"
+ "\016volume_gain_db\030\004 \001(\001B\006\340A\004\340A\001\022\036\n"
@@ -204,8 +208,8 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
+ "\021CustomVoiceParams\0222\n"
+ "\005model\030\001 \001(\tB#\340A\002\372A\035\n"
+ "\033automl.googleapis.com/Model\022a\n"
- + "\016reported_usage\030\003 \001(\0162B.goog"
- + "le.cloud.texttospeech.v1beta1.CustomVoiceParams.ReportedUsageB\005\030\001\340A\001\"J\n\r"
+ + "\016reported_usage\030\003 \001(\0162B.google.cl"
+ + "oud.texttospeech.v1beta1.CustomVoiceParams.ReportedUsageB\005\030\001\340A\001\"J\n\r"
+ "ReportedUsage\022\036\n"
+ "\032REPORTED_USAGE_UNSPECIFIED\020\000\022\014\n"
+ "\010REALTIME\020\001\022\013\n"
@@ -219,24 +223,30 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
+ " \001(\0132..google.cloud.texttospeech.v1beta1.AudioConfig\"4\n"
+ "\tTimepoint\022\021\n"
+ "\tmark_name\030\004 \001(\t\022\024\n"
- + "\014time_seconds\030\003 \001(\001\"\205\001\n"
+ + "\014time_seconds\030\003 \001(\001\"\244\001\n"
+ "\024StreamingAudioConfig\022M\n"
- + "\016audio_encoding\030\001"
- + " \001(\01620.google.cloud.texttospeech.v1beta1.AudioEncodingB\003\340A\002\022\036\n"
- + "\021sample_rate_hertz\030\002 \001(\005B\003\340A\001\"\306\001\n"
+ + "\016audio_encoding\030\001 \001"
+ + "(\01620.google.cloud.texttospeech.v1beta1.AudioEncodingB\003\340A\002\022\036\n"
+ + "\021sample_rate_hertz\030\002 \001(\005B\003\340A\001\022\035\n\r"
+ + "speaking_rate\030\003 \001(\001B\006\340A\004\340A\001\"\243\002\n"
+ "\031StreamingSynthesizeConfig\022K\n"
- + "\005voice\030\001 \001(\01327.google.cloud.textt"
- + "ospeech.v1beta1.VoiceSelectionParamsB\003\340A\002\022\\\n"
- + "\026streaming_audio_config\030\004 \001(\01327.goog"
- + "le.cloud.texttospeech.v1beta1.StreamingAudioConfigB\003\340A\001\"9\n"
+ + "\005voice\030\001"
+ + " \001(\01327.google.cloud.texttospeech.v1beta1.VoiceSelectionParamsB\003\340A\002\022\\\n"
+ + "\026streaming_audio_config\030\004 \001(\01327.google.cloud.textt"
+ + "ospeech.v1beta1.StreamingAudioConfigB\003\340A\001\022[\n"
+ + "\025custom_pronunciations\030\005 \001(\01327.googl"
+ + "e.cloud.texttospeech.v1beta1.CustomPronunciationsB\003\340A\001\"k\n"
+ "\027StreamingSynthesisInput\022\016\n"
- + "\004text\030\001 \001(\tH\000B\016\n"
- + "\014input_source\"\330\001\n"
+ + "\004text\030\001 \001(\tH\000\022\020\n"
+ + "\006markup\030\005 \001(\tH\000\022\023\n"
+ + "\006prompt\030\006 \001(\tH\001\210\001\001B\016\n"
+ + "\014input_sourceB\t\n"
+ + "\007_prompt\"\330\001\n"
+ "\032StreamingSynthesizeRequest\022X\n"
- + "\020streaming_config\030\001"
- + " \001(\0132<.google.cloud.texttospeech.v1beta1.StreamingSynthesizeConfigH\000\022K\n"
- + "\005input\030\002"
- + " \001(\0132:.google.cloud.texttospeech.v1beta1.StreamingSynthesisInputH\000B\023\n"
+ + "\020streaming_config\030\001 \001(\0132<.google.cloud.text"
+ + "tospeech.v1beta1.StreamingSynthesizeConfigH\000\022K\n"
+ + "\005input\030\002 \001(\0132:.google.cloud.textt"
+ + "ospeech.v1beta1.StreamingSynthesisInputH\000B\023\n"
+ "\021streaming_request\"4\n"
+ "\033StreamingSynthesizeResponse\022\025\n\r"
+ "audio_content\030\001 \001(\014*W\n"
@@ -244,8 +254,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
+ "\035SSML_VOICE_GENDER_UNSPECIFIED\020\000\022\010\n"
+ "\004MALE\020\001\022\n\n"
+ "\006FEMALE\020\002\022\013\n"
- + "\007NEUTRAL\020\003*\203\001\n"
- + "\r"
+ + "\007NEUTRAL\020\003*\214\001\n\r"
+ "AudioEncoding\022\036\n"
+ "\032AUDIO_ENCODING_UNSPECIFIED\020\000\022\014\n"
+ "\010LINEAR16\020\001\022\007\n"
@@ -254,26 +263,27 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
+ "\010OGG_OPUS\020\003\022\t\n"
+ "\005MULAW\020\005\022\010\n"
+ "\004ALAW\020\006\022\007\n"
- + "\003PCM\020\0072\357\004\n"
+ + "\003PCM\020\007\022\007\n"
+ + "\003M4A\020\0102\357\004\n"
+ "\014TextToSpeech\022\242\001\n\n"
- + "ListVoices\0224.google.cloud.texttospeech.v1beta1.L"
- + "istVoicesRequest\0325.google.cloud.texttospeech.v1beta1.ListVoicesResponse\"\'\332A\r"
+ + "ListVoices\0224.google.cloud.texttospeech.v1beta1.ListVoicesRequest\0325.goo"
+ + "gle.cloud.texttospeech.v1beta1.ListVoicesResponse\"\'\332A\r"
+ "language_code\202\323\344\223\002\021\022\017/v1beta1/voices\022\313\001\n"
- + "\020SynthesizeSpeech\022:.google.cloud.texttospeec"
- + "h.v1beta1.SynthesizeSpeechRequest\032;.google.cloud.texttospeech.v1beta1.Synthesize"
- + "SpeechResponse\">\332A\030input,voice,audio_con"
- + "fig\202\323\344\223\002\035\"\030/v1beta1/text:synthesize:\001*\022\232\001\n"
- + "\023StreamingSynthesize\022=.google.cloud.texttospeech.v1beta1.StreamingSynthesizeRe"
- + "quest\032>.google.cloud.texttospeech.v1beta"
- + "1.StreamingSynthesizeResponse\"\000(\0010\001\032O\312A\033"
- + "texttospeech.googleapis.com\322A.https://www.googleapis.com/auth/cloud-platformB\325\002\n"
- + "%com.google.cloud.texttospeech.v1beta1B\021TextToSpeechProtoP\001ZIcloud.google.com/go"
- + "/texttospeech/apiv1beta1/texttospeechpb;"
- + "texttospeechpb\242\002\004CTTS\252\002!Google.Cloud.Tex"
- + "tToSpeech.V1Beta1\312\002!Google\\Cloud\\TextToS"
- + "peech\\V1beta1\352\002$Google::Cloud::TextToSpeech::V1beta1\352AU\n"
- + "\033automl.googleapis.com/Model\0226projects/{project}/locations/{loca"
- + "tion}/models/{model}b\006proto3"
+ + "\020SynthesizeSpeech\022:.google.cloud.texttospeech.v1beta1.SynthesizeSp"
+ + "eechRequest\032;.google.cloud.texttospeech."
+ + "v1beta1.SynthesizeSpeechResponse\">\332A\030inp"
+ + "ut,voice,audio_config\202\323\344\223\002\035\"\030/v1beta1/text:synthesize:\001*\022\232\001\n"
+ + "\023StreamingSynthesize\022=.google.cloud.texttospeech.v1beta1.Str"
+ + "eamingSynthesizeRequest\032>.google.cloud.texttospeech.v1beta1.StreamingSynthesizeR"
+ + "esponse\"\000(\0010\001\032O\312A\033texttospeech.googleapi"
+ + "s.com\322A.https://www.googleapis.com/auth/cloud-platformB\325\002\n"
+ + "%com.google.cloud.texttospeech.v1beta1B\021TextToSpeechProtoP\001ZIc"
+ + "loud.google.com/go/texttospeech/apiv1bet"
+ + "a1/texttospeechpb;texttospeechpb\242\002\004CTTS\252"
+ + "\002!Google.Cloud.TextToSpeech.V1Beta1\312\002!Go"
+ + "ogle\\Cloud\\TextToSpeech\\V1beta1\352\002$Google::Cloud::TextToSpeech::V1beta1\352AU\n"
+ + "\033automl.googleapis.com/Model\0226projects/{projec"
+ + "t}/locations/{location}/models/{model}b\006proto3"
};
descriptor =
com.google.protobuf.Descriptors.FileDescriptor.internalBuildGeneratedFileFrom(
@@ -364,7 +374,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
new com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
internal_static_google_cloud_texttospeech_v1beta1_SynthesisInput_descriptor,
new java.lang.String[] {
- "Text", "Ssml", "MultiSpeakerMarkup", "CustomPronunciations", "InputSource",
+ "Text", "Markup", "Ssml", "MultiSpeakerMarkup", "CustomPronunciations", "InputSource",
});
internal_static_google_cloud_texttospeech_v1beta1_VoiceSelectionParams_descriptor =
getDescriptor().getMessageTypes().get(9);
@@ -372,7 +382,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
new com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
internal_static_google_cloud_texttospeech_v1beta1_VoiceSelectionParams_descriptor,
new java.lang.String[] {
- "LanguageCode", "Name", "SsmlGender", "CustomVoice", "VoiceClone",
+ "LanguageCode", "Name", "SsmlGender", "CustomVoice", "VoiceClone", "ModelName",
});
internal_static_google_cloud_texttospeech_v1beta1_AudioConfig_descriptor =
getDescriptor().getMessageTypes().get(10);
@@ -425,7 +435,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
new com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
internal_static_google_cloud_texttospeech_v1beta1_StreamingAudioConfig_descriptor,
new java.lang.String[] {
- "AudioEncoding", "SampleRateHertz",
+ "AudioEncoding", "SampleRateHertz", "SpeakingRate",
});
internal_static_google_cloud_texttospeech_v1beta1_StreamingSynthesizeConfig_descriptor =
getDescriptor().getMessageTypes().get(16);
@@ -433,7 +443,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
new com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
internal_static_google_cloud_texttospeech_v1beta1_StreamingSynthesizeConfig_descriptor,
new java.lang.String[] {
- "Voice", "StreamingAudioConfig",
+ "Voice", "StreamingAudioConfig", "CustomPronunciations",
});
internal_static_google_cloud_texttospeech_v1beta1_StreamingSynthesisInput_descriptor =
getDescriptor().getMessageTypes().get(17);
@@ -441,7 +451,7 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
new com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
internal_static_google_cloud_texttospeech_v1beta1_StreamingSynthesisInput_descriptor,
new java.lang.String[] {
- "Text", "InputSource",
+ "Text", "Markup", "Prompt", "InputSource",
});
internal_static_google_cloud_texttospeech_v1beta1_StreamingSynthesizeRequest_descriptor =
getDescriptor().getMessageTypes().get(18);
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParams.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParams.java
index a03d28c85186..076cc65b234a 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParams.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParams.java
@@ -43,6 +43,7 @@ private VoiceSelectionParams() {
languageCode_ = "";
name_ = "";
ssmlGender_ = 0;
+ modelName_ = "";
}
@java.lang.Override
@@ -312,8 +313,8 @@ public com.google.cloud.texttospeech.v1beta1.CustomVoiceParams getCustomVoice()
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -332,8 +333,8 @@ public boolean hasVoiceClone() {
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -354,8 +355,8 @@ public com.google.cloud.texttospeech.v1beta1.VoiceCloneParams getVoiceClone() {
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -369,6 +370,61 @@ public com.google.cloud.texttospeech.v1beta1.VoiceCloneParamsOrBuilder getVoiceC
: voiceClone_;
}
+ public static final int MODEL_NAME_FIELD_NUMBER = 6;
+
+ @SuppressWarnings("serial")
+ private volatile java.lang.Object modelName_ = "";
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return The modelName.
+ */
+ @java.lang.Override
+ public java.lang.String getModelName() {
+ java.lang.Object ref = modelName_;
+ if (ref instanceof java.lang.String) {
+ return (java.lang.String) ref;
+ } else {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ modelName_ = s;
+ return s;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return The bytes for modelName.
+ */
+ @java.lang.Override
+ public com.google.protobuf.ByteString getModelNameBytes() {
+ java.lang.Object ref = modelName_;
+ if (ref instanceof java.lang.String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ modelName_ = b;
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
private byte memoizedIsInitialized = -1;
@java.lang.Override
@@ -400,6 +456,9 @@ public void writeTo(com.google.protobuf.CodedOutputStream output) throws java.io
if (((bitField0_ & 0x00000002) != 0)) {
output.writeMessage(5, getVoiceClone());
}
+ if (!com.google.protobuf.GeneratedMessageV3.isStringEmpty(modelName_)) {
+ com.google.protobuf.GeneratedMessageV3.writeString(output, 6, modelName_);
+ }
getUnknownFields().writeTo(output);
}
@@ -426,6 +485,9 @@ public int getSerializedSize() {
if (((bitField0_ & 0x00000002) != 0)) {
size += com.google.protobuf.CodedOutputStream.computeMessageSize(5, getVoiceClone());
}
+ if (!com.google.protobuf.GeneratedMessageV3.isStringEmpty(modelName_)) {
+ size += com.google.protobuf.GeneratedMessageV3.computeStringSize(6, modelName_);
+ }
size += getUnknownFields().getSerializedSize();
memoizedSize = size;
return size;
@@ -453,6 +515,7 @@ public boolean equals(final java.lang.Object obj) {
if (hasVoiceClone()) {
if (!getVoiceClone().equals(other.getVoiceClone())) return false;
}
+ if (!getModelName().equals(other.getModelName())) return false;
if (!getUnknownFields().equals(other.getUnknownFields())) return false;
return true;
}
@@ -478,6 +541,8 @@ public int hashCode() {
hash = (37 * hash) + VOICE_CLONE_FIELD_NUMBER;
hash = (53 * hash) + getVoiceClone().hashCode();
}
+ hash = (37 * hash) + MODEL_NAME_FIELD_NUMBER;
+ hash = (53 * hash) + getModelName().hashCode();
hash = (29 * hash) + getUnknownFields().hashCode();
memoizedHashCode = hash;
return hash;
@@ -642,6 +707,7 @@ public Builder clear() {
voiceCloneBuilder_.dispose();
voiceCloneBuilder_ = null;
}
+ modelName_ = "";
return this;
}
@@ -697,6 +763,9 @@ private void buildPartial0(com.google.cloud.texttospeech.v1beta1.VoiceSelectionP
result.voiceClone_ = voiceCloneBuilder_ == null ? voiceClone_ : voiceCloneBuilder_.build();
to_bitField0_ |= 0x00000002;
}
+ if (((from_bitField0_ & 0x00000020) != 0)) {
+ result.modelName_ = modelName_;
+ }
result.bitField0_ |= to_bitField0_;
}
@@ -765,6 +834,11 @@ public Builder mergeFrom(com.google.cloud.texttospeech.v1beta1.VoiceSelectionPar
if (other.hasVoiceClone()) {
mergeVoiceClone(other.getVoiceClone());
}
+ if (!other.getModelName().isEmpty()) {
+ modelName_ = other.modelName_;
+ bitField0_ |= 0x00000020;
+ onChanged();
+ }
this.mergeUnknownFields(other.getUnknownFields());
onChanged();
return this;
@@ -821,6 +895,12 @@ public Builder mergeFrom(
bitField0_ |= 0x00000010;
break;
} // case 42
+ case 50:
+ {
+ modelName_ = input.readStringRequireUtf8();
+ bitField0_ |= 0x00000020;
+ break;
+ } // case 50
default:
{
if (!super.parseUnknownField(input, extensionRegistry, tag)) {
@@ -1466,8 +1546,8 @@ public com.google.cloud.texttospeech.v1beta1.CustomVoiceParams.Builder getCustom
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1485,8 +1565,8 @@ public boolean hasVoiceClone() {
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1510,8 +1590,8 @@ public com.google.cloud.texttospeech.v1beta1.VoiceCloneParams getVoiceClone() {
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1537,8 +1617,8 @@ public Builder setVoiceClone(com.google.cloud.texttospeech.v1beta1.VoiceClonePar
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1562,8 +1642,8 @@ public Builder setVoiceClone(
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1595,8 +1675,8 @@ public Builder mergeVoiceClone(com.google.cloud.texttospeech.v1beta1.VoiceCloneP
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1619,8 +1699,8 @@ public Builder clearVoiceClone() {
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1638,8 +1718,8 @@ public com.google.cloud.texttospeech.v1beta1.VoiceCloneParams.Builder getVoiceCl
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1662,8 +1742,8 @@ public com.google.cloud.texttospeech.v1beta1.VoiceCloneParams.Builder getVoiceCl
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -1687,6 +1767,122 @@ public com.google.cloud.texttospeech.v1beta1.VoiceCloneParams.Builder getVoiceCl
return voiceCloneBuilder_;
}
+ private java.lang.Object modelName_ = "";
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return The modelName.
+ */
+ public java.lang.String getModelName() {
+ java.lang.Object ref = modelName_;
+ if (!(ref instanceof java.lang.String)) {
+ com.google.protobuf.ByteString bs = (com.google.protobuf.ByteString) ref;
+ java.lang.String s = bs.toStringUtf8();
+ modelName_ = s;
+ return s;
+ } else {
+ return (java.lang.String) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return The bytes for modelName.
+ */
+ public com.google.protobuf.ByteString getModelNameBytes() {
+ java.lang.Object ref = modelName_;
+ if (ref instanceof String) {
+ com.google.protobuf.ByteString b =
+ com.google.protobuf.ByteString.copyFromUtf8((java.lang.String) ref);
+ modelName_ = b;
+ return b;
+ } else {
+ return (com.google.protobuf.ByteString) ref;
+ }
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @param value The modelName to set.
+ * @return This builder for chaining.
+ */
+ public Builder setModelName(java.lang.String value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ modelName_ = value;
+ bitField0_ |= 0x00000020;
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return This builder for chaining.
+ */
+ public Builder clearModelName() {
+ modelName_ = getDefaultInstance().getModelName();
+ bitField0_ = (bitField0_ & ~0x00000020);
+ onChanged();
+ return this;
+ }
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @param value The bytes for modelName to set.
+ * @return This builder for chaining.
+ */
+ public Builder setModelNameBytes(com.google.protobuf.ByteString value) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ checkByteStringIsUtf8(value);
+ modelName_ = value;
+ bitField0_ |= 0x00000020;
+ onChanged();
+ return this;
+ }
+
@java.lang.Override
public final Builder setUnknownFields(final com.google.protobuf.UnknownFieldSet unknownFields) {
return super.setUnknownFields(unknownFields);
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParamsOrBuilder.java b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParamsOrBuilder.java
index f0f99b202cfc..52b22d249088 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParamsOrBuilder.java
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/java/com/google/cloud/texttospeech/v1beta1/VoiceSelectionParamsOrBuilder.java
@@ -182,8 +182,8 @@ public interface VoiceSelectionParamsOrBuilder
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -199,8 +199,8 @@ public interface VoiceSelectionParamsOrBuilder
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -216,8 +216,8 @@ public interface VoiceSelectionParamsOrBuilder
*
*
* Optional. The configuration for a voice clone. If
- * [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- * voice clone matching the specified configuration.
+ * [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ * clone matching the specified configuration.
*
*
*
@@ -225,4 +225,32 @@ public interface VoiceSelectionParamsOrBuilder
*
*/
com.google.cloud.texttospeech.v1beta1.VoiceCloneParamsOrBuilder getVoiceCloneOrBuilder();
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return The modelName.
+ */
+ java.lang.String getModelName();
+
+ /**
+ *
+ *
+ *
+ * Optional. The name of the model. If set, the service will choose the model
+ * matching the specified configuration.
+ *
+ *
+ * string model_name = 6 [(.google.api.field_behavior) = OPTIONAL];
+ *
+ * @return The bytes for modelName.
+ */
+ com.google.protobuf.ByteString getModelNameBytes();
}
diff --git a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/proto/google/cloud/texttospeech/v1beta1/cloud_tts.proto b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/proto/google/cloud/texttospeech/v1beta1/cloud_tts.proto
index eeec64655f1a..204a159d94ac 100644
--- a/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/proto/google/cloud/texttospeech/v1beta1/cloud_tts.proto
+++ b/java-texttospeech/proto-google-cloud-texttospeech-v1beta1/src/main/proto/google/cloud/texttospeech/v1beta1/cloud_tts.proto
@@ -59,7 +59,7 @@ service TextToSpeech {
option (google.api.method_signature) = "input,voice,audio_config";
}
- // Performs bidirectional streaming speech synthesis: receive audio while
+ // Performs bidirectional streaming speech synthesis: receives audio while
// sending text.
rpc StreamingSynthesize(stream StreamingSynthesizeRequest)
returns (stream StreamingSynthesizeResponse) {}
@@ -88,7 +88,8 @@ enum SsmlVoiceGender {
// Configuration to set up audio encoder. The encoding determines the output
// audio format that we'd like.
enum AudioEncoding {
- // Not specified. Will return result
+ // Not specified. Only used by GenerateVoiceCloningKey. Otherwise, will return
+ // result
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
AUDIO_ENCODING_UNSPECIFIED = 0;
@@ -102,7 +103,7 @@ enum AudioEncoding {
// MP3 at 64kbps.
MP3_64_KBPS = 4;
- // Opus encoded audio wrapped in an ogg container. The result will be a
+ // Opus encoded audio wrapped in an ogg container. The result is a
// file which can be played natively on Android, and in browsers (at least
// Chrome and Firefox). The quality of the encoding is considerably higher
// than MP3 while using approximately the same bitrate.
@@ -117,9 +118,12 @@ enum AudioEncoding {
ALAW = 6;
// Uncompressed 16-bit signed little-endian samples (Linear PCM).
- // Note that as opposed to LINEAR16, audio will not be wrapped in a WAV (or
+ // Note that as opposed to LINEAR16, audio won't be wrapped in a WAV (or
// any other) header.
PCM = 7;
+
+ // M4A audio.
+ M4A = 8;
}
// The top-level message sent by the client for the `ListVoices` method.
@@ -160,8 +164,8 @@ message Voice {
// Used for advanced voice options.
message AdvancedVoiceOptions {
- // Only for Journey voices. If false, the synthesis will be context aware
- // and have higher latency.
+ // Only for Journey voices. If false, the synthesis is context aware
+ // and has a higher latency.
optional bool low_latency_journey_synthesis = 1;
}
@@ -199,18 +203,41 @@ message CustomPronunciationParams {
// Not specified.
PHONETIC_ENCODING_UNSPECIFIED = 0;
- // IPA. (e.g. apple -> ˈæpəl )
+ // IPA, such as apple -> ˈæpəl.
// https://en.wikipedia.org/wiki/International_Phonetic_Alphabet
PHONETIC_ENCODING_IPA = 1;
- // X-SAMPA (e.g. apple -> "{p@l" )
+ // X-SAMPA, such as apple -> "{p@l".
// https://en.wikipedia.org/wiki/X-SAMPA
PHONETIC_ENCODING_X_SAMPA = 2;
+
+ // For reading-to-pron conversion to work well, the `pronunciation` field
+ // should only contain Kanji, Hiragana, and Katakana.
+ //
+ // The pronunciation can also contain pitch accents.
+ // The start of a pitch phrase is specified with `^` and the down-pitch
+ // position is specified with `!`, for example:
+ //
+ // phrase:端 pronunciation:^はし
+ // phrase:箸 pronunciation:^は!し
+ // phrase:橋 pronunciation:^はし!
+ //
+ // We currently only support the Tokyo dialect, which allows at most one
+ // down-pitch per phrase (i.e. at most one `!` between `^`).
+ PHONETIC_ENCODING_JAPANESE_YOMIGANA = 3;
+
+ // Used to specify pronunciations for Mandarin words. See
+ // https://en.wikipedia.org/wiki/Pinyin.
+ //
+ // For example: 朝阳, the pronunciation is "chao2 yang2". The number
+ // represents the tone, and there is a space between syllables. Neutral
+ // tones are represented by 5, for example 孩子 "hai2 zi5".
+ PHONETIC_ENCODING_PINYIN = 4;
}
- // The phrase to which the customization will be applied.
- // The phrase can be multiple words (in the case of proper nouns etc), but
- // should not span to a whole sentence.
+ // The phrase to which the customization is applied.
+ // The phrase can be multiple words, such as proper nouns, but shouldn't span
+ // the length of the sentence.
optional string phrase = 1;
// The phonetic encoding of the phrase.
@@ -223,13 +250,13 @@ message CustomPronunciationParams {
// A collection of pronunciation customizations.
message CustomPronunciations {
- // The pronunciation customizations to be applied.
+ // The pronunciation customizations are applied.
repeated CustomPronunciationParams pronunciations = 1;
}
// A collection of turns for multi-speaker synthesis.
message MultiSpeakerMarkup {
- // A Multi-speaker turn.
+ // A multi-speaker turn.
message Turn {
// Required. The speaker of the turn, for example, 'O' or 'Q'. Please refer
// to documentation for available speakers.
@@ -253,6 +280,10 @@ message SynthesisInput {
// The raw text to be synthesized.
string text = 1;
+ // Markup for HD voices specifically. This field may not be used with any
+ // other voices.
+ string markup = 5;
+
// The SSML document to be synthesized. The SSML document must be valid
// and well-formed. Otherwise the RPC will fail and return
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. For
@@ -265,18 +296,16 @@ message SynthesisInput {
MultiSpeakerMarkup multi_speaker_markup = 4;
}
- // Optional. The pronunciation customizations to be applied to the input. If
- // this is set, the input will be synthesized using the given pronunciation
+ // Optional. The pronunciation customizations are applied to the input. If
+ // this is set, the input is synthesized using the given pronunciation
// customizations.
//
- // The initial support will be for EFIGS (English, French,
- // Italian, German, Spanish) languages, as provided in
- // VoiceSelectionParams. Journey and Instant Clone voices are
- // not supported yet.
+ // The initial support is for en-us, with plans to expand to other locales in
+ // the future. Instant Clone voices aren't supported.
//
// In order to customize the pronunciation of a phrase, there must be an exact
// match of the phrase in the input types. If using SSML, the phrase must not
- // be inside a phoneme tag (entirely or partially).
+ // be inside a phoneme tag.
CustomPronunciations custom_pronunciations = 3
[(google.api.field_behavior) = OPTIONAL];
}
@@ -314,9 +343,13 @@ message VoiceSelectionParams {
CustomVoiceParams custom_voice = 4;
// Optional. The configuration for a voice clone. If
- // [VoiceCloneParams.voice_clone_key] is set, the service will choose the
- // voice clone matching the specified configuration.
+ // [VoiceCloneParams.voice_clone_key] is set, the service chooses the voice
+ // clone matching the specified configuration.
VoiceCloneParams voice_clone = 5 [(google.api.field_behavior) = OPTIONAL];
+
+ // Optional. The name of the model. If set, the service will choose the model
+ // matching the specified configuration.
+ string model_name = 6 [(google.api.field_behavior) = OPTIONAL];
}
// Description of audio data to be synthesized.
@@ -324,10 +357,10 @@ message AudioConfig {
// Required. The format of the audio byte stream.
AudioEncoding audio_encoding = 1 [(google.api.field_behavior) = REQUIRED];
- // Optional. Input only. Speaking rate/speed, in the range [0.25, 4.0]. 1.0 is
+ // Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
// the normal native speed supported by the specific voice. 2.0 is twice as
// fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
- // speed. Any other values < 0.25 or > 4.0 will return an error.
+ // speed. Any other values < 0.25 or > 2.0 will return an error.
double speaking_rate = 2 [
(google.api.field_behavior) = INPUT_ONLY,
(google.api.field_behavior) = OPTIONAL
@@ -440,12 +473,21 @@ message Timepoint {
// Description of the desired output audio data.
message StreamingAudioConfig {
// Required. The format of the audio byte stream.
- // For now, streaming only supports PCM and OGG_OPUS. All other encodings
- // will return an error.
+ // Streaming supports PCM, ALAW, MULAW and OGG_OPUS. All other encodings
+ // return an error.
AudioEncoding audio_encoding = 1 [(google.api.field_behavior) = REQUIRED];
// Optional. The synthesis sample rate (in hertz) for this audio.
int32 sample_rate_hertz = 2 [(google.api.field_behavior) = OPTIONAL];
+
+ // Optional. Input only. Speaking rate/speed, in the range [0.25, 2.0]. 1.0 is
+ // the normal native speed supported by the specific voice. 2.0 is twice as
+ // fast, and 0.5 is half as fast. If unset(0.0), defaults to the native 1.0
+ // speed. Any other values < 0.25 or > 2.0 will return an error.
+ double speaking_rate = 3 [
+ (google.api.field_behavior) = INPUT_ONLY,
+ (google.api.field_behavior) = OPTIONAL
+ ];
}
// Provides configuration information for the StreamingSynthesize request.
@@ -456,17 +498,36 @@ message StreamingSynthesizeConfig {
// Optional. The configuration of the synthesized audio.
StreamingAudioConfig streaming_audio_config = 4
[(google.api.field_behavior) = OPTIONAL];
+
+ // Optional. The pronunciation customizations are applied to the input. If
+ // this is set, the input is synthesized using the given pronunciation
+ // customizations.
+ //
+ // The initial support is for en-us, with plans to expand to other locales in
+ // the future. Instant Clone voices aren't supported.
+ //
+ // In order to customize the pronunciation of a phrase, there must be an exact
+ // match of the phrase in the input types. If using SSML, the phrase must not
+ // be inside a phoneme tag.
+ CustomPronunciations custom_pronunciations = 5
+ [(google.api.field_behavior) = OPTIONAL];
}
// Input to be synthesized.
message StreamingSynthesisInput {
oneof input_source {
// The raw text to be synthesized. It is recommended that each input
- // contains complete, terminating sentences, as this will likely result in
- // better prosody in the output audio. That being said, users are free to
- // input text however they please.
+ // contains complete, terminating sentences, which results in better prosody
+ // in the output audio.
string text = 1;
+
+ // Markup for HD voices specifically. This field may not be used with any
+ // other voices.
+ string markup = 5;
}
+
+ // This is system instruction supported only for controllable voice models.
+ optional string prompt = 6;
}
// Request message for the `StreamingSynthesize` method. Multiple