diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudio.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudio.java
index cf2b2ac1e08c..e69a6267355d 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudio.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudio.java
@@ -8,7 +8,7 @@
* Contains audio data in the encoding specified in the `RecognitionConfig`.
* Either `content` or `uri` must be supplied. Supplying both or neither
* returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* Protobuf type {@code google.cloud.speech.v1p1beta1.RecognitionAudio}
@@ -151,7 +151,8 @@ public com.google.protobuf.ByteString getContent() {
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -180,7 +181,8 @@ public java.lang.String getUri() {
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -400,7 +402,7 @@ protected Builder newBuilderForType(
* Contains audio data in the encoding specified in the `RecognitionConfig`.
* Either `content` or `uri` must be supplied. Supplying both or neither
* returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* Protobuf type {@code google.cloud.speech.v1p1beta1.RecognitionAudio}
@@ -636,7 +638,8 @@ public Builder clearContent() {
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -665,7 +668,8 @@ public java.lang.String getUri() {
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -695,7 +699,8 @@ public java.lang.String getUri() {
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -717,7 +722,8 @@ public Builder setUri(
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -737,7 +743,8 @@ public Builder clearUri() {
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudioOrBuilder.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudioOrBuilder.java
index e0127eb4a88a..445c0b83402a 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudioOrBuilder.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionAudioOrBuilder.java
@@ -21,7 +21,8 @@ public interface RecognitionAudioOrBuilder extends
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -34,7 +35,8 @@ public interface RecognitionAudioOrBuilder extends
/**
*
* URI that points to a file that contains audio data bytes as specified in
- * `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ * `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ * Currently, only Google Cloud Storage URIs are
* supported, which must be specified in the following format:
* `gs://bucket_name/object_name` (other URI formats return
* [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java
index 16a15615eba4..31952c628671 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfig.java
@@ -538,9 +538,9 @@ public int getSampleRateHertz() {
* Valid values for OGG_OPUS are '1'-'254'.
* Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
* If `0` or omitted, defaults to one channel (mono).
- * NOTE: We only recognize the first channel by default.
+ * Note: We only recognize the first channel by default.
* To perform independent recognition on each channel set
- * enable_separate_recognition_per_channel to 'true'.
+ * `enable_separate_recognition_per_channel` to 'true'.
*
*
* int32 audio_channel_count = 7;
@@ -553,12 +553,12 @@ public int getAudioChannelCount() {
private boolean enableSeparateRecognitionPerChannel_;
/**
*
- * This needs to be set to ‘true’ explicitly and audio_channel_count > 1
+ * This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
* to get each channel recognized separately. The recognition result will
- * contain a channel_tag field to state which channel that result belongs to.
- * If this is not ‘true’, we will only recognize the first channel.
- * NOTE: The request is also billed cumulatively for all channels recognized:
- * (audio_channel_count times the audio length)
+ * contain a `channel_tag` field to state which channel that result belongs
+ * to. If this is not true, we will only recognize the first channel. The
+ * request is billed cumulatively for all channels recognized:
+ * `audio_channel_count` multiplied by the length of the audio.
*
*
* bool enable_separate_recognition_per_channel = 12;
@@ -574,7 +574,7 @@ public boolean getEnableSeparateRecognitionPerChannel() {
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -597,7 +597,7 @@ public java.lang.String getLanguageCode() {
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -624,13 +624,13 @@ public java.lang.String getLanguageCode() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -646,13 +646,13 @@ public java.lang.String getLanguageCode() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -667,13 +667,13 @@ public int getAlternativeLanguageCodesCount() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -688,13 +688,13 @@ public java.lang.String getAlternativeLanguageCodes(int index) {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -744,7 +744,9 @@ public boolean getProfanityFilter() {
private java.util.List speechContexts_;
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -754,7 +756,9 @@ public java.util.List getSpeech
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -765,7 +769,9 @@ public java.util.List getSpeech
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -775,7 +781,9 @@ public int getSpeechContextsCount() {
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -785,7 +793,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContext getSpeechContexts(int ind
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -834,9 +844,9 @@ public boolean getEnableWordConfidence() {
* This feature is only available in select languages. Setting this for
* requests in other languages has no effect at all.
* The default 'false' value does not add punctuation to result hypotheses.
- * NOTE: "This is currently offered as an experimental service, complimentary
+ * Note: This is currently offered as an experimental service, complimentary
* to all users. In the future this may be exclusively available as a
- * premium feature."
+ * premium feature.
*
*
* bool enable_automatic_punctuation = 11;
@@ -853,9 +863,11 @@ public boolean getEnableAutomaticPunctuation() {
* the top alternative of the recognition result using a speaker_tag provided
* in the WordInfo.
* Note: When this is true, we send all the words from the beginning of the
- * audio for the top alternative in every consecutive responses.
+ * audio for the top alternative in every consecutive STREAMING responses.
* This is done in order to improve our speaker tags as our models learn to
* identify the speakers in the conversation over time.
+ * For non-streaming requests, the diarization results will be provided only
+ * in the top alternative of the FINAL SpeechRecognitionResult.
*
*
* bool enable_speaker_diarization = 16;
@@ -1022,13 +1034,16 @@ public java.lang.String getModel() {
/**
*
* *Optional* Set to true to use an enhanced model for speech recognition.
- * You must also set the `model` field to a valid, enhanced model. If
- * `use_enhanced` is set to true and the `model` field is not set, then
- * `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
- * version of the specified model does not exist, then the speech is
- * recognized using the standard version of the specified model.
- * Enhanced speech models require that you opt-in to the audio logging using
- * instructions in the [alpha documentation](/speech/data-sharing). If you set
+ * If `use_enhanced` is set to true and the `model` field is not set, then
+ * an appropriate enhanced model is chosen if:
+ * 1. project is eligible for requesting enhanced models
+ * 2. an enhanced model exists for the audio
+ * If `use_enhanced` is true and an enhanced version of the specified model
+ * does not exist, then the speech is recognized using the standard version
+ * of the specified model.
+ * Enhanced speech models require that you opt-in to data logging using
+ * instructions in the
+ * [documentation](/speech-to-text/docs/enable-data-logging). If you set
* `use_enhanced` to true and you have not enabled audio logging, then you
* will receive an error.
*
@@ -1837,9 +1852,9 @@ public Builder clearSampleRateHertz() {
* Valid values for OGG_OPUS are '1'-'254'.
* Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
* If `0` or omitted, defaults to one channel (mono).
- * NOTE: We only recognize the first channel by default.
+ * Note: We only recognize the first channel by default.
* To perform independent recognition on each channel set
- * enable_separate_recognition_per_channel to 'true'.
+ * `enable_separate_recognition_per_channel` to 'true'.
*
*
* int32 audio_channel_count = 7;
@@ -1855,9 +1870,9 @@ public int getAudioChannelCount() {
* Valid values for OGG_OPUS are '1'-'254'.
* Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
* If `0` or omitted, defaults to one channel (mono).
- * NOTE: We only recognize the first channel by default.
+ * Note: We only recognize the first channel by default.
* To perform independent recognition on each channel set
- * enable_separate_recognition_per_channel to 'true'.
+ * `enable_separate_recognition_per_channel` to 'true'.
*
*
* int32 audio_channel_count = 7;
@@ -1876,9 +1891,9 @@ public Builder setAudioChannelCount(int value) {
* Valid values for OGG_OPUS are '1'-'254'.
* Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
* If `0` or omitted, defaults to one channel (mono).
- * NOTE: We only recognize the first channel by default.
+ * Note: We only recognize the first channel by default.
* To perform independent recognition on each channel set
- * enable_separate_recognition_per_channel to 'true'.
+ * `enable_separate_recognition_per_channel` to 'true'.
*
*
* int32 audio_channel_count = 7;
@@ -1893,12 +1908,12 @@ public Builder clearAudioChannelCount() {
private boolean enableSeparateRecognitionPerChannel_ ;
/**
*
- * This needs to be set to ‘true’ explicitly and audio_channel_count > 1
+ * This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
* to get each channel recognized separately. The recognition result will
- * contain a channel_tag field to state which channel that result belongs to.
- * If this is not ‘true’, we will only recognize the first channel.
- * NOTE: The request is also billed cumulatively for all channels recognized:
- * (audio_channel_count times the audio length)
+ * contain a `channel_tag` field to state which channel that result belongs
+ * to. If this is not true, we will only recognize the first channel. The
+ * request is billed cumulatively for all channels recognized:
+ * `audio_channel_count` multiplied by the length of the audio.
*
*
* bool enable_separate_recognition_per_channel = 12;
@@ -1908,12 +1923,12 @@ public boolean getEnableSeparateRecognitionPerChannel() {
}
/**
*
- * This needs to be set to ‘true’ explicitly and audio_channel_count > 1
+ * This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
* to get each channel recognized separately. The recognition result will
- * contain a channel_tag field to state which channel that result belongs to.
- * If this is not ‘true’, we will only recognize the first channel.
- * NOTE: The request is also billed cumulatively for all channels recognized:
- * (audio_channel_count times the audio length)
+ * contain a `channel_tag` field to state which channel that result belongs
+ * to. If this is not true, we will only recognize the first channel. The
+ * request is billed cumulatively for all channels recognized:
+ * `audio_channel_count` multiplied by the length of the audio.
*
*
* bool enable_separate_recognition_per_channel = 12;
@@ -1926,12 +1941,12 @@ public Builder setEnableSeparateRecognitionPerChannel(boolean value) {
}
/**
*
- * This needs to be set to ‘true’ explicitly and audio_channel_count > 1
+ * This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
* to get each channel recognized separately. The recognition result will
- * contain a channel_tag field to state which channel that result belongs to.
- * If this is not ‘true’, we will only recognize the first channel.
- * NOTE: The request is also billed cumulatively for all channels recognized:
- * (audio_channel_count times the audio length)
+ * contain a `channel_tag` field to state which channel that result belongs
+ * to. If this is not true, we will only recognize the first channel. The
+ * request is billed cumulatively for all channels recognized:
+ * `audio_channel_count` multiplied by the length of the audio.
*
*
* bool enable_separate_recognition_per_channel = 12;
@@ -1949,7 +1964,7 @@ public Builder clearEnableSeparateRecognitionPerChannel() {
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -1972,7 +1987,7 @@ public java.lang.String getLanguageCode() {
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -1996,7 +2011,7 @@ public java.lang.String getLanguageCode() {
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -2017,7 +2032,7 @@ public Builder setLanguageCode(
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -2034,7 +2049,7 @@ public Builder clearLanguageCode() {
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -2064,13 +2079,13 @@ private void ensureAlternativeLanguageCodesIsMutable() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2086,13 +2101,13 @@ private void ensureAlternativeLanguageCodesIsMutable() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2107,13 +2122,13 @@ public int getAlternativeLanguageCodesCount() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2128,13 +2143,13 @@ public java.lang.String getAlternativeLanguageCodes(int index) {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2150,13 +2165,13 @@ public java.lang.String getAlternativeLanguageCodes(int index) {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2178,13 +2193,13 @@ public Builder setAlternativeLanguageCodes(
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2206,13 +2221,13 @@ public Builder addAlternativeLanguageCodes(
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2232,13 +2247,13 @@ public Builder addAllAlternativeLanguageCodes(
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2256,13 +2271,13 @@ public Builder clearAlternativeLanguageCodes() {
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -2395,7 +2410,9 @@ private void ensureSpeechContextsIsMutable() {
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2409,7 +2426,9 @@ public java.util.List getSpeech
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2423,7 +2442,9 @@ public int getSpeechContextsCount() {
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2437,7 +2458,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContext getSpeechContexts(int ind
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2458,7 +2481,9 @@ public Builder setSpeechContexts(
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2476,7 +2501,9 @@ public Builder setSpeechContexts(
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2496,7 +2523,9 @@ public Builder addSpeechContexts(com.google.cloud.speech.v1p1beta1.SpeechContext
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2517,7 +2546,9 @@ public Builder addSpeechContexts(
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2535,7 +2566,9 @@ public Builder addSpeechContexts(
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2553,7 +2586,9 @@ public Builder addSpeechContexts(
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2572,7 +2607,9 @@ public Builder addAllSpeechContexts(
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2589,7 +2626,9 @@ public Builder clearSpeechContexts() {
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2606,7 +2645,9 @@ public Builder removeSpeechContexts(int index) {
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2617,7 +2658,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContext.Builder getSpeechContexts
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2631,7 +2674,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder getSpeechContext
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2646,7 +2691,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder getSpeechContext
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2657,7 +2704,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContext.Builder addSpeechContexts
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2669,7 +2718,9 @@ public com.google.cloud.speech.v1p1beta1.SpeechContext.Builder addSpeechContexts
}
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -2791,9 +2842,9 @@ public Builder clearEnableWordConfidence() {
* This feature is only available in select languages. Setting this for
* requests in other languages has no effect at all.
* The default 'false' value does not add punctuation to result hypotheses.
- * NOTE: "This is currently offered as an experimental service, complimentary
+ * Note: This is currently offered as an experimental service, complimentary
* to all users. In the future this may be exclusively available as a
- * premium feature."
+ * premium feature.
*
*
* bool enable_automatic_punctuation = 11;
@@ -2807,9 +2858,9 @@ public boolean getEnableAutomaticPunctuation() {
* This feature is only available in select languages. Setting this for
* requests in other languages has no effect at all.
* The default 'false' value does not add punctuation to result hypotheses.
- * NOTE: "This is currently offered as an experimental service, complimentary
+ * Note: This is currently offered as an experimental service, complimentary
* to all users. In the future this may be exclusively available as a
- * premium feature."
+ * premium feature.
*
*
* bool enable_automatic_punctuation = 11;
@@ -2826,9 +2877,9 @@ public Builder setEnableAutomaticPunctuation(boolean value) {
* This feature is only available in select languages. Setting this for
* requests in other languages has no effect at all.
* The default 'false' value does not add punctuation to result hypotheses.
- * NOTE: "This is currently offered as an experimental service, complimentary
+ * Note: This is currently offered as an experimental service, complimentary
* to all users. In the future this may be exclusively available as a
- * premium feature."
+ * premium feature.
*
*
* bool enable_automatic_punctuation = 11;
@@ -2847,9 +2898,11 @@ public Builder clearEnableAutomaticPunctuation() {
* the top alternative of the recognition result using a speaker_tag provided
* in the WordInfo.
* Note: When this is true, we send all the words from the beginning of the
- * audio for the top alternative in every consecutive responses.
+ * audio for the top alternative in every consecutive STREAMING responses.
* This is done in order to improve our speaker tags as our models learn to
* identify the speakers in the conversation over time.
+ * For non-streaming requests, the diarization results will be provided only
+ * in the top alternative of the FINAL SpeechRecognitionResult.
*
*
* bool enable_speaker_diarization = 16;
@@ -2863,9 +2916,11 @@ public boolean getEnableSpeakerDiarization() {
* the top alternative of the recognition result using a speaker_tag provided
* in the WordInfo.
* Note: When this is true, we send all the words from the beginning of the
- * audio for the top alternative in every consecutive responses.
+ * audio for the top alternative in every consecutive STREAMING responses.
* This is done in order to improve our speaker tags as our models learn to
* identify the speakers in the conversation over time.
+ * For non-streaming requests, the diarization results will be provided only
+ * in the top alternative of the FINAL SpeechRecognitionResult.
*
*
* bool enable_speaker_diarization = 16;
@@ -2882,9 +2937,11 @@ public Builder setEnableSpeakerDiarization(boolean value) {
* the top alternative of the recognition result using a speaker_tag provided
* in the WordInfo.
* Note: When this is true, we send all the words from the beginning of the
- * audio for the top alternative in every consecutive responses.
+ * audio for the top alternative in every consecutive STREAMING responses.
* This is done in order to improve our speaker tags as our models learn to
* identify the speakers in the conversation over time.
+ * For non-streaming requests, the diarization results will be provided only
+ * in the top alternative of the FINAL SpeechRecognitionResult.
*
*
* bool enable_speaker_diarization = 16;
@@ -3344,13 +3401,16 @@ public Builder setModelBytes(
/**
*
* *Optional* Set to true to use an enhanced model for speech recognition.
- * You must also set the `model` field to a valid, enhanced model. If
- * `use_enhanced` is set to true and the `model` field is not set, then
- * `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
- * version of the specified model does not exist, then the speech is
- * recognized using the standard version of the specified model.
- * Enhanced speech models require that you opt-in to the audio logging using
- * instructions in the [alpha documentation](/speech/data-sharing). If you set
+ * If `use_enhanced` is set to true and the `model` field is not set, then
+ * an appropriate enhanced model is chosen if:
+ * 1. project is eligible for requesting enhanced models
+ * 2. an enhanced model exists for the audio
+ * If `use_enhanced` is true and an enhanced version of the specified model
+ * does not exist, then the speech is recognized using the standard version
+ * of the specified model.
+ * Enhanced speech models require that you opt-in to data logging using
+ * instructions in the
+ * [documentation](/speech-to-text/docs/enable-data-logging). If you set
* `use_enhanced` to true and you have not enabled audio logging, then you
* will receive an error.
*
@@ -3363,13 +3423,16 @@ public boolean getUseEnhanced() {
/**
*
* *Optional* Set to true to use an enhanced model for speech recognition.
- * You must also set the `model` field to a valid, enhanced model. If
- * `use_enhanced` is set to true and the `model` field is not set, then
- * `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
- * version of the specified model does not exist, then the speech is
- * recognized using the standard version of the specified model.
- * Enhanced speech models require that you opt-in to the audio logging using
- * instructions in the [alpha documentation](/speech/data-sharing). If you set
+ * If `use_enhanced` is set to true and the `model` field is not set, then
+ * an appropriate enhanced model is chosen if:
+ * 1. project is eligible for requesting enhanced models
+ * 2. an enhanced model exists for the audio
+ * If `use_enhanced` is true and an enhanced version of the specified model
+ * does not exist, then the speech is recognized using the standard version
+ * of the specified model.
+ * Enhanced speech models require that you opt-in to data logging using
+ * instructions in the
+ * [documentation](/speech-to-text/docs/enable-data-logging). If you set
* `use_enhanced` to true and you have not enabled audio logging, then you
* will receive an error.
*
@@ -3385,13 +3448,16 @@ public Builder setUseEnhanced(boolean value) {
/**
*
* *Optional* Set to true to use an enhanced model for speech recognition.
- * You must also set the `model` field to a valid, enhanced model. If
- * `use_enhanced` is set to true and the `model` field is not set, then
- * `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
- * version of the specified model does not exist, then the speech is
- * recognized using the standard version of the specified model.
- * Enhanced speech models require that you opt-in to the audio logging using
- * instructions in the [alpha documentation](/speech/data-sharing). If you set
+ * If `use_enhanced` is set to true and the `model` field is not set, then
+ * an appropriate enhanced model is chosen if:
+ * 1. project is eligible for requesting enhanced models
+ * 2. an enhanced model exists for the audio
+ * If `use_enhanced` is true and an enhanced version of the specified model
+ * does not exist, then the speech is recognized using the standard version
+ * of the specified model.
+ * Enhanced speech models require that you opt-in to data logging using
+ * instructions in the
+ * [documentation](/speech-to-text/docs/enable-data-logging). If you set
* `use_enhanced` to true and you have not enabled audio logging, then you
* will receive an error.
*
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java
index 31216fcceb26..bc1c1e942597 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/RecognitionConfigOrBuilder.java
@@ -51,9 +51,9 @@ public interface RecognitionConfigOrBuilder extends
* Valid values for OGG_OPUS are '1'-'254'.
* Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
* If `0` or omitted, defaults to one channel (mono).
- * NOTE: We only recognize the first channel by default.
+ * Note: We only recognize the first channel by default.
* To perform independent recognition on each channel set
- * enable_separate_recognition_per_channel to 'true'.
+ * `enable_separate_recognition_per_channel` to 'true'.
*
*
* int32 audio_channel_count = 7;
@@ -62,12 +62,12 @@ public interface RecognitionConfigOrBuilder extends
/**
*
- * This needs to be set to ‘true’ explicitly and audio_channel_count > 1
+ * This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
* to get each channel recognized separately. The recognition result will
- * contain a channel_tag field to state which channel that result belongs to.
- * If this is not ‘true’, we will only recognize the first channel.
- * NOTE: The request is also billed cumulatively for all channels recognized:
- * (audio_channel_count times the audio length)
+ * contain a `channel_tag` field to state which channel that result belongs
+ * to. If this is not true, we will only recognize the first channel. The
+ * request is billed cumulatively for all channels recognized:
+ * `audio_channel_count` multiplied by the length of the audio.
*
*
* bool enable_separate_recognition_per_channel = 12;
@@ -79,7 +79,7 @@ public interface RecognitionConfigOrBuilder extends
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -91,7 +91,7 @@ public interface RecognitionConfigOrBuilder extends
* *Required* The language of the supplied audio as a
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
* Example: "en-US".
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
*
*
@@ -105,13 +105,13 @@ public interface RecognitionConfigOrBuilder extends
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -125,13 +125,13 @@ public interface RecognitionConfigOrBuilder extends
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -144,13 +144,13 @@ public interface RecognitionConfigOrBuilder extends
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -163,13 +163,13 @@ public interface RecognitionConfigOrBuilder extends
* *Optional* A list of up to 3 additional
* [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
* listing possible alternative languages of the supplied audio.
- * See [Language Support](https://cloud.google.com/speech/docs/languages)
+ * See [Language Support](/speech-to-text/docs/languages)
* for a list of the currently supported language codes.
* If alternative languages are listed, recognition result will contain
* recognition in the most likely language detected including the main
* language_code. The recognition result will include the language tag
* of the language detected in the audio.
- * NOTE: This feature is only supported for Voice Command and Voice Search
+ * Note: This feature is only supported for Voice Command and Voice Search
* use cases and performance may vary for other use cases (e.g., phone call
* transcription).
*
@@ -207,7 +207,9 @@ public interface RecognitionConfigOrBuilder extends
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -216,7 +218,9 @@ public interface RecognitionConfigOrBuilder extends
getSpeechContextsList();
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -224,7 +228,9 @@ public interface RecognitionConfigOrBuilder extends
com.google.cloud.speech.v1p1beta1.SpeechContext getSpeechContexts(int index);
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -232,7 +238,9 @@ public interface RecognitionConfigOrBuilder extends
int getSpeechContextsCount();
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -241,7 +249,9 @@ public interface RecognitionConfigOrBuilder extends
getSpeechContextsOrBuilderList();
/**
*
- * *Optional* A means to provide context to assist the speech recognition.
+ * *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ * A means to provide context to assist the speech recognition. For more
+ * information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
*
*
* repeated .google.cloud.speech.v1p1beta1.SpeechContext speech_contexts = 6;
@@ -278,9 +288,9 @@ com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder getSpeechContextsOrBuil
* This feature is only available in select languages. Setting this for
* requests in other languages has no effect at all.
* The default 'false' value does not add punctuation to result hypotheses.
- * NOTE: "This is currently offered as an experimental service, complimentary
+ * Note: This is currently offered as an experimental service, complimentary
* to all users. In the future this may be exclusively available as a
- * premium feature."
+ * premium feature.
*
*
* bool enable_automatic_punctuation = 11;
@@ -293,9 +303,11 @@ com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder getSpeechContextsOrBuil
* the top alternative of the recognition result using a speaker_tag provided
* in the WordInfo.
* Note: When this is true, we send all the words from the beginning of the
- * audio for the top alternative in every consecutive responses.
+ * audio for the top alternative in every consecutive STREAMING responses.
* This is done in order to improve our speaker tags as our models learn to
* identify the speakers in the conversation over time.
+ * For non-streaming requests, the diarization results will be provided only
+ * in the top alternative of the FINAL SpeechRecognitionResult.
*
*
* bool enable_speaker_diarization = 16;
@@ -422,13 +434,16 @@ com.google.cloud.speech.v1p1beta1.SpeechContextOrBuilder getSpeechContextsOrBuil
/**
*
* *Optional* Set to true to use an enhanced model for speech recognition.
- * You must also set the `model` field to a valid, enhanced model. If
- * `use_enhanced` is set to true and the `model` field is not set, then
- * `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
- * version of the specified model does not exist, then the speech is
- * recognized using the standard version of the specified model.
- * Enhanced speech models require that you opt-in to the audio logging using
- * instructions in the [alpha documentation](/speech/data-sharing). If you set
+ * If `use_enhanced` is set to true and the `model` field is not set, then
+ * an appropriate enhanced model is chosen if:
+ * 1. project is eligible for requesting enhanced models
+ * 2. an enhanced model exists for the audio
+ * If `use_enhanced` is true and an enhanced version of the specified model
+ * does not exist, then the speech is recognized using the standard version
+ * of the specified model.
+ * Enhanced speech models require that you opt-in to data logging using
+ * instructions in the
+ * [documentation](/speech-to-text/docs/enable-data-logging). If you set
* `use_enhanced` to true and you have not enabled audio logging, then you
* will receive an error.
*
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContext.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContext.java
index 88bf669987cb..1b0569d7f588 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContext.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContext.java
@@ -101,7 +101,7 @@ private SpeechContext(
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -117,7 +117,7 @@ private SpeechContext(
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -132,7 +132,7 @@ public int getPhrasesCount() {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -147,7 +147,7 @@ public java.lang.String getPhrases(int index) {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -498,7 +498,7 @@ private void ensurePhrasesIsMutable() {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -514,7 +514,7 @@ private void ensurePhrasesIsMutable() {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -529,7 +529,7 @@ public int getPhrasesCount() {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -544,7 +544,7 @@ public java.lang.String getPhrases(int index) {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -560,7 +560,7 @@ public java.lang.String getPhrases(int index) {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -582,7 +582,7 @@ public Builder setPhrases(
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -604,7 +604,7 @@ public Builder addPhrases(
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -624,7 +624,7 @@ public Builder addAllPhrases(
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -642,7 +642,7 @@ public Builder clearPhrases() {
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContextOrBuilder.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContextOrBuilder.java
index 3d5250046cf9..f9ddb6724147 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContextOrBuilder.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechContextOrBuilder.java
@@ -14,7 +14,7 @@ public interface SpeechContextOrBuilder extends
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -28,7 +28,7 @@ public interface SpeechContextOrBuilder extends
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -41,7 +41,7 @@ public interface SpeechContextOrBuilder extends
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
@@ -54,7 +54,7 @@ public interface SpeechContextOrBuilder extends
* to improve the accuracy for specific words and phrases, for example, if
* specific commands are typically spoken by the user. This can also be used
* to add additional words to the vocabulary of the recognizer. See
- * [usage limits](https://cloud.google.com/speech/limits#content).
+ * [usage limits](/speech-to-text/quotas#content).
*
*
* repeated string phrases = 1;
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java
index f64d1ab6b196..85229ebb9003 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechProto.java
@@ -108,123 +108,125 @@ public static void registerAllExtensions(
"1\032\034google/api/annotations.proto\032#google/" +
"longrunning/operations.proto\032\031google/pro" +
"tobuf/any.proto\032\036google/protobuf/duratio" +
- "n.proto\032\037google/protobuf/timestamp.proto" +
- "\032\027google/rpc/status.proto\"\224\001\n\020RecognizeR" +
- "equest\022@\n\006config\030\001 \001(\01320.google.cloud.sp" +
- "eech.v1p1beta1.RecognitionConfig\022>\n\005audi" +
- "o\030\002 \001(\0132/.google.cloud.speech.v1p1beta1." +
- "RecognitionAudio\"\237\001\n\033LongRunningRecogniz" +
- "eRequest\022@\n\006config\030\001 \001(\01320.google.cloud." +
- "speech.v1p1beta1.RecognitionConfig\022>\n\005au" +
- "dio\030\002 \001(\0132/.google.cloud.speech.v1p1beta" +
- "1.RecognitionAudio\"\240\001\n\031StreamingRecogniz" +
- "eRequest\022U\n\020streaming_config\030\001 \001(\01329.goo" +
- "gle.cloud.speech.v1p1beta1.StreamingReco" +
- "gnitionConfigH\000\022\027\n\raudio_content\030\002 \001(\014H\000" +
- "B\023\n\021streaming_request\"\221\001\n\032StreamingRecog" +
- "nitionConfig\022@\n\006config\030\001 \001(\01320.google.cl" +
- "oud.speech.v1p1beta1.RecognitionConfig\022\030" +
- "\n\020single_utterance\030\002 \001(\010\022\027\n\017interim_resu" +
- "lts\030\003 \001(\010\"\254\006\n\021RecognitionConfig\022P\n\010encod" +
- "ing\030\001 \001(\0162>.google.cloud.speech.v1p1beta" +
- "1.RecognitionConfig.AudioEncoding\022\031\n\021sam" +
- "ple_rate_hertz\030\002 \001(\005\022\033\n\023audio_channel_co" +
- "unt\030\007 \001(\005\022/\n\'enable_separate_recognition" +
- "_per_channel\030\014 \001(\010\022\025\n\rlanguage_code\030\003 \001(" +
- "\t\022\"\n\032alternative_language_codes\030\022 \003(\t\022\030\n" +
- "\020max_alternatives\030\004 \001(\005\022\030\n\020profanity_fil" +
- "ter\030\005 \001(\010\022E\n\017speech_contexts\030\006 \003(\0132,.goo" +
- "gle.cloud.speech.v1p1beta1.SpeechContext" +
- "\022 \n\030enable_word_time_offsets\030\010 \001(\010\022\036\n\026en" +
- "able_word_confidence\030\017 \001(\010\022$\n\034enable_aut" +
- "omatic_punctuation\030\013 \001(\010\022\"\n\032enable_speak" +
- "er_diarization\030\020 \001(\010\022!\n\031diarization_spea" +
- "ker_count\030\021 \001(\005\022D\n\010metadata\030\t \001(\01322.goog" +
- "le.cloud.speech.v1p1beta1.RecognitionMet" +
- "adata\022\r\n\005model\030\r \001(\t\022\024\n\014use_enhanced\030\016 \001" +
- "(\010\"\213\001\n\rAudioEncoding\022\030\n\024ENCODING_UNSPECI" +
- "FIED\020\000\022\014\n\010LINEAR16\020\001\022\010\n\004FLAC\020\002\022\t\n\005MULAW\020" +
- "\003\022\007\n\003AMR\020\004\022\n\n\006AMR_WB\020\005\022\014\n\010OGG_OPUS\020\006\022\032\n\026" +
- "SPEEX_WITH_HEADER_BYTE\020\007\"\323\010\n\023Recognition" +
- "Metadata\022\\\n\020interaction_type\030\001 \001(\0162B.goo" +
- "gle.cloud.speech.v1p1beta1.RecognitionMe" +
- "tadata.InteractionType\022$\n\034industry_naics" +
- "_code_of_audio\030\003 \001(\r\022b\n\023microphone_dista" +
- "nce\030\004 \001(\0162E.google.cloud.speech.v1p1beta" +
- "1.RecognitionMetadata.MicrophoneDistance" +
- "\022a\n\023original_media_type\030\005 \001(\0162D.google.c" +
- "loud.speech.v1p1beta1.RecognitionMetadat" +
- "a.OriginalMediaType\022e\n\025recording_device_" +
- "type\030\006 \001(\0162F.google.cloud.speech.v1p1bet" +
- "a1.RecognitionMetadata.RecordingDeviceTy" +
- "pe\022\035\n\025recording_device_name\030\007 \001(\t\022\032\n\022ori" +
- "ginal_mime_type\030\010 \001(\t\022\025\n\robfuscated_id\030\t" +
- " \001(\003\022\023\n\013audio_topic\030\n \001(\t\"\305\001\n\017Interactio" +
- "nType\022 \n\034INTERACTION_TYPE_UNSPECIFIED\020\000\022" +
- "\016\n\nDISCUSSION\020\001\022\020\n\014PRESENTATION\020\002\022\016\n\nPHO" +
- "NE_CALL\020\003\022\r\n\tVOICEMAIL\020\004\022\033\n\027PROFESSIONAL" +
- "LY_PRODUCED\020\005\022\020\n\014VOICE_SEARCH\020\006\022\021\n\rVOICE" +
- "_COMMAND\020\007\022\r\n\tDICTATION\020\010\"d\n\022MicrophoneD" +
- "istance\022#\n\037MICROPHONE_DISTANCE_UNSPECIFI" +
- "ED\020\000\022\r\n\tNEARFIELD\020\001\022\014\n\010MIDFIELD\020\002\022\014\n\010FAR" +
- "FIELD\020\003\"N\n\021OriginalMediaType\022#\n\037ORIGINAL" +
- "_MEDIA_TYPE_UNSPECIFIED\020\000\022\t\n\005AUDIO\020\001\022\t\n\005" +
- "VIDEO\020\002\"\244\001\n\023RecordingDeviceType\022%\n!RECOR" +
- "DING_DEVICE_TYPE_UNSPECIFIED\020\000\022\016\n\nSMARTP" +
- "HONE\020\001\022\006\n\002PC\020\002\022\016\n\nPHONE_LINE\020\003\022\013\n\007VEHICL" +
- "E\020\004\022\030\n\024OTHER_OUTDOOR_DEVICE\020\005\022\027\n\023OTHER_I" +
- "NDOOR_DEVICE\020\006\" \n\rSpeechContext\022\017\n\007phras" +
- "es\030\001 \003(\t\"D\n\020RecognitionAudio\022\021\n\007content\030" +
- "\001 \001(\014H\000\022\r\n\003uri\030\002 \001(\tH\000B\016\n\014audio_source\"\\" +
- "\n\021RecognizeResponse\022G\n\007results\030\002 \003(\01326.g" +
- "oogle.cloud.speech.v1p1beta1.SpeechRecog" +
- "nitionResult\"g\n\034LongRunningRecognizeResp" +
- "onse\022G\n\007results\030\002 \003(\01326.google.cloud.spe" +
- "ech.v1p1beta1.SpeechRecognitionResult\"\236\001" +
- "\n\034LongRunningRecognizeMetadata\022\030\n\020progre" +
- "ss_percent\030\001 \001(\005\022.\n\nstart_time\030\002 \001(\0132\032.g" +
- "oogle.protobuf.Timestamp\0224\n\020last_update_" +
- "time\030\003 \001(\0132\032.google.protobuf.Timestamp\"\277" +
- "\002\n\032StreamingRecognizeResponse\022!\n\005error\030\001" +
- " \001(\0132\022.google.rpc.Status\022J\n\007results\030\002 \003(" +
- "\01329.google.cloud.speech.v1p1beta1.Stream" +
- "ingRecognitionResult\022d\n\021speech_event_typ" +
- "e\030\004 \001(\0162I.google.cloud.speech.v1p1beta1." +
- "StreamingRecognizeResponse.SpeechEventTy" +
- "pe\"L\n\017SpeechEventType\022\034\n\030SPEECH_EVENT_UN" +
- "SPECIFIED\020\000\022\033\n\027END_OF_SINGLE_UTTERANCE\020\001" +
- "\"\300\001\n\032StreamingRecognitionResult\022Q\n\014alter" +
- "natives\030\001 \003(\0132;.google.cloud.speech.v1p1" +
- "beta1.SpeechRecognitionAlternative\022\020\n\010is" +
- "_final\030\002 \001(\010\022\021\n\tstability\030\003 \001(\002\022\023\n\013chann" +
- "el_tag\030\005 \001(\005\022\025\n\rlanguage_code\030\006 \001(\t\"\230\001\n\027" +
- "SpeechRecognitionResult\022Q\n\014alternatives\030" +
- "\001 \003(\0132;.google.cloud.speech.v1p1beta1.Sp" +
- "eechRecognitionAlternative\022\023\n\013channel_ta" +
- "g\030\002 \001(\005\022\025\n\rlanguage_code\030\005 \001(\t\"~\n\034Speech" +
- "RecognitionAlternative\022\022\n\ntranscript\030\001 \001" +
- "(\t\022\022\n\nconfidence\030\002 \001(\002\0226\n\005words\030\003 \003(\0132\'." +
- "google.cloud.speech.v1p1beta1.WordInfo\"\235" +
- "\001\n\010WordInfo\022-\n\nstart_time\030\001 \001(\0132\031.google" +
- ".protobuf.Duration\022+\n\010end_time\030\002 \001(\0132\031.g" +
- "oogle.protobuf.Duration\022\014\n\004word\030\003 \001(\t\022\022\n" +
- "\nconfidence\030\004 \001(\002\022\023\n\013speaker_tag\030\005 \001(\0052\330" +
- "\003\n\006Speech\022\226\001\n\tRecognize\022/.google.cloud.s" +
- "peech.v1p1beta1.RecognizeRequest\0320.googl" +
- "e.cloud.speech.v1p1beta1.RecognizeRespon" +
- "se\"&\202\323\344\223\002 \"\033/v1p1beta1/speech:recognize:" +
- "\001*\022\244\001\n\024LongRunningRecognize\022:.google.clo" +
- "ud.speech.v1p1beta1.LongRunningRecognize" +
- "Request\032\035.google.longrunning.Operation\"1" +
- "\202\323\344\223\002+\"&/v1p1beta1/speech:longrunningrec" +
- "ognize:\001*\022\215\001\n\022StreamingRecognize\0228.googl" +
- "e.cloud.speech.v1p1beta1.StreamingRecogn" +
- "izeRequest\0329.google.cloud.speech.v1p1bet" +
- "a1.StreamingRecognizeResponse(\0010\001Bz\n!com" +
- ".google.cloud.speech.v1p1beta1B\013SpeechPr" +
- "otoP\001ZCgoogle.golang.org/genproto/google" +
- "apis/cloud/speech/v1p1beta1;speech\370\001\001b\006p" +
- "roto3"
+ "n.proto\032\033google/protobuf/empty.proto\032\037go" +
+ "ogle/protobuf/timestamp.proto\032\027google/rp" +
+ "c/status.proto\"\224\001\n\020RecognizeRequest\022@\n\006c" +
+ "onfig\030\001 \001(\01320.google.cloud.speech.v1p1be" +
+ "ta1.RecognitionConfig\022>\n\005audio\030\002 \001(\0132/.g" +
+ "oogle.cloud.speech.v1p1beta1.Recognition" +
+ "Audio\"\237\001\n\033LongRunningRecognizeRequest\022@\n" +
+ "\006config\030\001 \001(\01320.google.cloud.speech.v1p1" +
+ "beta1.RecognitionConfig\022>\n\005audio\030\002 \001(\0132/" +
+ ".google.cloud.speech.v1p1beta1.Recogniti" +
+ "onAudio\"\240\001\n\031StreamingRecognizeRequest\022U\n" +
+ "\020streaming_config\030\001 \001(\01329.google.cloud.s" +
+ "peech.v1p1beta1.StreamingRecognitionConf" +
+ "igH\000\022\027\n\raudio_content\030\002 \001(\014H\000B\023\n\021streami" +
+ "ng_request\"\221\001\n\032StreamingRecognitionConfi" +
+ "g\022@\n\006config\030\001 \001(\01320.google.cloud.speech." +
+ "v1p1beta1.RecognitionConfig\022\030\n\020single_ut" +
+ "terance\030\002 \001(\010\022\027\n\017interim_results\030\003 \001(\010\"\254" +
+ "\006\n\021RecognitionConfig\022P\n\010encoding\030\001 \001(\0162>" +
+ ".google.cloud.speech.v1p1beta1.Recogniti" +
+ "onConfig.AudioEncoding\022\031\n\021sample_rate_he" +
+ "rtz\030\002 \001(\005\022\033\n\023audio_channel_count\030\007 \001(\005\022/" +
+ "\n\'enable_separate_recognition_per_channe" +
+ "l\030\014 \001(\010\022\025\n\rlanguage_code\030\003 \001(\t\022\"\n\032altern" +
+ "ative_language_codes\030\022 \003(\t\022\030\n\020max_altern" +
+ "atives\030\004 \001(\005\022\030\n\020profanity_filter\030\005 \001(\010\022E" +
+ "\n\017speech_contexts\030\006 \003(\0132,.google.cloud.s" +
+ "peech.v1p1beta1.SpeechContext\022 \n\030enable_" +
+ "word_time_offsets\030\010 \001(\010\022\036\n\026enable_word_c" +
+ "onfidence\030\017 \001(\010\022$\n\034enable_automatic_punc" +
+ "tuation\030\013 \001(\010\022\"\n\032enable_speaker_diarizat" +
+ "ion\030\020 \001(\010\022!\n\031diarization_speaker_count\030\021" +
+ " \001(\005\022D\n\010metadata\030\t \001(\01322.google.cloud.sp" +
+ "eech.v1p1beta1.RecognitionMetadata\022\r\n\005mo" +
+ "del\030\r \001(\t\022\024\n\014use_enhanced\030\016 \001(\010\"\213\001\n\rAudi" +
+ "oEncoding\022\030\n\024ENCODING_UNSPECIFIED\020\000\022\014\n\010L" +
+ "INEAR16\020\001\022\010\n\004FLAC\020\002\022\t\n\005MULAW\020\003\022\007\n\003AMR\020\004\022" +
+ "\n\n\006AMR_WB\020\005\022\014\n\010OGG_OPUS\020\006\022\032\n\026SPEEX_WITH_" +
+ "HEADER_BYTE\020\007\"\323\010\n\023RecognitionMetadata\022\\\n" +
+ "\020interaction_type\030\001 \001(\0162B.google.cloud.s" +
+ "peech.v1p1beta1.RecognitionMetadata.Inte" +
+ "ractionType\022$\n\034industry_naics_code_of_au" +
+ "dio\030\003 \001(\r\022b\n\023microphone_distance\030\004 \001(\0162E" +
+ ".google.cloud.speech.v1p1beta1.Recogniti" +
+ "onMetadata.MicrophoneDistance\022a\n\023origina" +
+ "l_media_type\030\005 \001(\0162D.google.cloud.speech" +
+ ".v1p1beta1.RecognitionMetadata.OriginalM" +
+ "ediaType\022e\n\025recording_device_type\030\006 \001(\0162" +
+ "F.google.cloud.speech.v1p1beta1.Recognit" +
+ "ionMetadata.RecordingDeviceType\022\035\n\025recor" +
+ "ding_device_name\030\007 \001(\t\022\032\n\022original_mime_" +
+ "type\030\010 \001(\t\022\025\n\robfuscated_id\030\t \001(\003\022\023\n\013aud" +
+ "io_topic\030\n \001(\t\"\305\001\n\017InteractionType\022 \n\034IN" +
+ "TERACTION_TYPE_UNSPECIFIED\020\000\022\016\n\nDISCUSSI" +
+ "ON\020\001\022\020\n\014PRESENTATION\020\002\022\016\n\nPHONE_CALL\020\003\022\r" +
+ "\n\tVOICEMAIL\020\004\022\033\n\027PROFESSIONALLY_PRODUCED" +
+ "\020\005\022\020\n\014VOICE_SEARCH\020\006\022\021\n\rVOICE_COMMAND\020\007\022" +
+ "\r\n\tDICTATION\020\010\"d\n\022MicrophoneDistance\022#\n\037" +
+ "MICROPHONE_DISTANCE_UNSPECIFIED\020\000\022\r\n\tNEA" +
+ "RFIELD\020\001\022\014\n\010MIDFIELD\020\002\022\014\n\010FARFIELD\020\003\"N\n\021" +
+ "OriginalMediaType\022#\n\037ORIGINAL_MEDIA_TYPE" +
+ "_UNSPECIFIED\020\000\022\t\n\005AUDIO\020\001\022\t\n\005VIDEO\020\002\"\244\001\n" +
+ "\023RecordingDeviceType\022%\n!RECORDING_DEVICE" +
+ "_TYPE_UNSPECIFIED\020\000\022\016\n\nSMARTPHONE\020\001\022\006\n\002P" +
+ "C\020\002\022\016\n\nPHONE_LINE\020\003\022\013\n\007VEHICLE\020\004\022\030\n\024OTHE" +
+ "R_OUTDOOR_DEVICE\020\005\022\027\n\023OTHER_INDOOR_DEVIC" +
+ "E\020\006\" \n\rSpeechContext\022\017\n\007phrases\030\001 \003(\t\"D\n" +
+ "\020RecognitionAudio\022\021\n\007content\030\001 \001(\014H\000\022\r\n\003" +
+ "uri\030\002 \001(\tH\000B\016\n\014audio_source\"\\\n\021Recognize" +
+ "Response\022G\n\007results\030\002 \003(\01326.google.cloud" +
+ ".speech.v1p1beta1.SpeechRecognitionResul" +
+ "t\"g\n\034LongRunningRecognizeResponse\022G\n\007res" +
+ "ults\030\002 \003(\01326.google.cloud.speech.v1p1bet" +
+ "a1.SpeechRecognitionResult\"\236\001\n\034LongRunni" +
+ "ngRecognizeMetadata\022\030\n\020progress_percent\030" +
+ "\001 \001(\005\022.\n\nstart_time\030\002 \001(\0132\032.google.proto" +
+ "buf.Timestamp\0224\n\020last_update_time\030\003 \001(\0132" +
+ "\032.google.protobuf.Timestamp\"\277\002\n\032Streamin" +
+ "gRecognizeResponse\022!\n\005error\030\001 \001(\0132\022.goog" +
+ "le.rpc.Status\022J\n\007results\030\002 \003(\01329.google." +
+ "cloud.speech.v1p1beta1.StreamingRecognit" +
+ "ionResult\022d\n\021speech_event_type\030\004 \001(\0162I.g" +
+ "oogle.cloud.speech.v1p1beta1.StreamingRe" +
+ "cognizeResponse.SpeechEventType\"L\n\017Speec" +
+ "hEventType\022\034\n\030SPEECH_EVENT_UNSPECIFIED\020\000" +
+ "\022\033\n\027END_OF_SINGLE_UTTERANCE\020\001\"\364\001\n\032Stream" +
+ "ingRecognitionResult\022Q\n\014alternatives\030\001 \003" +
+ "(\0132;.google.cloud.speech.v1p1beta1.Speec" +
+ "hRecognitionAlternative\022\020\n\010is_final\030\002 \001(" +
+ "\010\022\021\n\tstability\030\003 \001(\002\0222\n\017result_end_time\030" +
+ "\004 \001(\0132\031.google.protobuf.Duration\022\023\n\013chan" +
+ "nel_tag\030\005 \001(\005\022\025\n\rlanguage_code\030\006 \001(\t\"\230\001\n" +
+ "\027SpeechRecognitionResult\022Q\n\014alternatives" +
+ "\030\001 \003(\0132;.google.cloud.speech.v1p1beta1.S" +
+ "peechRecognitionAlternative\022\023\n\013channel_t" +
+ "ag\030\002 \001(\005\022\025\n\rlanguage_code\030\005 \001(\t\"~\n\034Speec" +
+ "hRecognitionAlternative\022\022\n\ntranscript\030\001 " +
+ "\001(\t\022\022\n\nconfidence\030\002 \001(\002\0226\n\005words\030\003 \003(\0132\'" +
+ ".google.cloud.speech.v1p1beta1.WordInfo\"" +
+ "\235\001\n\010WordInfo\022-\n\nstart_time\030\001 \001(\0132\031.googl" +
+ "e.protobuf.Duration\022+\n\010end_time\030\002 \001(\0132\031." +
+ "google.protobuf.Duration\022\014\n\004word\030\003 \001(\t\022\022" +
+ "\n\nconfidence\030\004 \001(\002\022\023\n\013speaker_tag\030\005 \001(\0052" +
+ "\332\003\n\006Speech\022\226\001\n\tRecognize\022/.google.cloud." +
+ "speech.v1p1beta1.RecognizeRequest\0320.goog" +
+ "le.cloud.speech.v1p1beta1.RecognizeRespo" +
+ "nse\"&\202\323\344\223\002 \"\033/v1p1beta1/speech:recognize" +
+ ":\001*\022\244\001\n\024LongRunningRecognize\022:.google.cl" +
+ "oud.speech.v1p1beta1.LongRunningRecogniz" +
+ "eRequest\032\035.google.longrunning.Operation\"" +
+ "1\202\323\344\223\002+\"&/v1p1beta1/speech:longrunningre" +
+ "cognize:\001*\022\217\001\n\022StreamingRecognize\0228.goog" +
+ "le.cloud.speech.v1p1beta1.StreamingRecog" +
+ "nizeRequest\0329.google.cloud.speech.v1p1be" +
+ "ta1.StreamingRecognizeResponse\"\000(\0010\001Bz\n!" +
+ "com.google.cloud.speech.v1p1beta1B\013Speec" +
+ "hProtoP\001ZCgoogle.golang.org/genproto/goo" +
+ "gleapis/cloud/speech/v1p1beta1;speech\370\001\001" +
+ "b\006proto3"
};
com.google.protobuf.Descriptors.FileDescriptor.InternalDescriptorAssigner assigner =
new com.google.protobuf.Descriptors.FileDescriptor. InternalDescriptorAssigner() {
@@ -241,6 +243,7 @@ public com.google.protobuf.ExtensionRegistry assignDescriptors(
com.google.longrunning.OperationsProto.getDescriptor(),
com.google.protobuf.AnyProto.getDescriptor(),
com.google.protobuf.DurationProto.getDescriptor(),
+ com.google.protobuf.EmptyProto.getDescriptor(),
com.google.protobuf.TimestampProto.getDescriptor(),
com.google.rpc.StatusProto.getDescriptor(),
}, assigner);
@@ -321,7 +324,7 @@ public com.google.protobuf.ExtensionRegistry assignDescriptors(
internal_static_google_cloud_speech_v1p1beta1_StreamingRecognitionResult_fieldAccessorTable = new
com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
internal_static_google_cloud_speech_v1p1beta1_StreamingRecognitionResult_descriptor,
- new java.lang.String[] { "Alternatives", "IsFinal", "Stability", "ChannelTag", "LanguageCode", });
+ new java.lang.String[] { "Alternatives", "IsFinal", "Stability", "ResultEndTime", "ChannelTag", "LanguageCode", });
internal_static_google_cloud_speech_v1p1beta1_SpeechRecognitionResult_descriptor =
getDescriptor().getMessageTypes().get(13);
internal_static_google_cloud_speech_v1p1beta1_SpeechRecognitionResult_fieldAccessorTable = new
@@ -349,6 +352,7 @@ public com.google.protobuf.ExtensionRegistry assignDescriptors(
com.google.longrunning.OperationsProto.getDescriptor();
com.google.protobuf.AnyProto.getDescriptor();
com.google.protobuf.DurationProto.getDescriptor();
+ com.google.protobuf.EmptyProto.getDescriptor();
com.google.protobuf.TimestampProto.getDescriptor();
com.google.rpc.StatusProto.getDescriptor();
}
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternative.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternative.java
index 2e53e4a1e11b..35690d14eb80 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternative.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternative.java
@@ -171,7 +171,7 @@ public float getConfidence() {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -183,7 +183,7 @@ public java.util.List getWordsList()
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -196,7 +196,7 @@ public java.util.List getWordsList()
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -208,7 +208,7 @@ public int getWordsCount() {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -220,7 +220,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfo getWords(int index) {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -777,7 +777,7 @@ private void ensureWordsIsMutable() {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -793,7 +793,7 @@ public java.util.List getWordsList()
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -809,7 +809,7 @@ public int getWordsCount() {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -825,7 +825,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfo getWords(int index) {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -848,7 +848,7 @@ public Builder setWords(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -868,7 +868,7 @@ public Builder setWords(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -890,7 +890,7 @@ public Builder addWords(com.google.cloud.speech.v1p1beta1.WordInfo value) {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -913,7 +913,7 @@ public Builder addWords(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -933,7 +933,7 @@ public Builder addWords(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -953,7 +953,7 @@ public Builder addWords(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -974,7 +974,7 @@ public Builder addAllWords(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -993,7 +993,7 @@ public Builder clearWords() {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -1012,7 +1012,7 @@ public Builder removeWords(int index) {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -1025,7 +1025,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfo.Builder getWordsBuilder(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -1041,7 +1041,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfoOrBuilder getWordsOrBuilder(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -1058,7 +1058,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfoOrBuilder getWordsOrBuilder(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -1071,7 +1071,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfo.Builder addWordsBuilder() {
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -1085,7 +1085,7 @@ public com.google.cloud.speech.v1p1beta1.WordInfo.Builder addWordsBuilder(
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternativeOrBuilder.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternativeOrBuilder.java
index 97516e4ee893..0fad54139b00 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternativeOrBuilder.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/SpeechRecognitionAlternativeOrBuilder.java
@@ -43,7 +43,7 @@ public interface SpeechRecognitionAlternativeOrBuilder extends
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -54,7 +54,7 @@ public interface SpeechRecognitionAlternativeOrBuilder extends
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -64,7 +64,7 @@ public interface SpeechRecognitionAlternativeOrBuilder extends
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -74,7 +74,7 @@ public interface SpeechRecognitionAlternativeOrBuilder extends
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
@@ -85,7 +85,7 @@ public interface SpeechRecognitionAlternativeOrBuilder extends
/**
*
* Output only. A list of word-specific information for each recognized word.
- * Note: When enable_speaker_diarization is true, you will see all the words
+ * Note: When `enable_speaker_diarization` is true, you will see all the words
* from the beginning of the audio.
*
*
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResult.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResult.java
index e4e45bd2b3b6..b04b6a62bf1f 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResult.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResult.java
@@ -71,6 +71,19 @@ private StreamingRecognitionResult(
stability_ = input.readFloat();
break;
}
+ case 34: {
+ com.google.protobuf.Duration.Builder subBuilder = null;
+ if (resultEndTime_ != null) {
+ subBuilder = resultEndTime_.toBuilder();
+ }
+ resultEndTime_ = input.readMessage(com.google.protobuf.Duration.parser(), extensionRegistry);
+ if (subBuilder != null) {
+ subBuilder.mergeFrom(resultEndTime_);
+ resultEndTime_ = subBuilder.buildPartial();
+ }
+
+ break;
+ }
case 40: {
channelTag_ = input.readInt32();
@@ -222,6 +235,42 @@ public float getStability() {
return stability_;
}
+ public static final int RESULT_END_TIME_FIELD_NUMBER = 4;
+ private com.google.protobuf.Duration resultEndTime_;
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public boolean hasResultEndTime() {
+ return resultEndTime_ != null;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public com.google.protobuf.Duration getResultEndTime() {
+ return resultEndTime_ == null ? com.google.protobuf.Duration.getDefaultInstance() : resultEndTime_;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public com.google.protobuf.DurationOrBuilder getResultEndTimeOrBuilder() {
+ return getResultEndTime();
+ }
+
public static final int CHANNEL_TAG_FIELD_NUMBER = 5;
private int channelTag_;
/**
@@ -308,6 +357,9 @@ public void writeTo(com.google.protobuf.CodedOutputStream output)
if (stability_ != 0F) {
output.writeFloat(3, stability_);
}
+ if (resultEndTime_ != null) {
+ output.writeMessage(4, getResultEndTime());
+ }
if (channelTag_ != 0) {
output.writeInt32(5, channelTag_);
}
@@ -335,6 +387,10 @@ public int getSerializedSize() {
size += com.google.protobuf.CodedOutputStream
.computeFloatSize(3, stability_);
}
+ if (resultEndTime_ != null) {
+ size += com.google.protobuf.CodedOutputStream
+ .computeMessageSize(4, getResultEndTime());
+ }
if (channelTag_ != 0) {
size += com.google.protobuf.CodedOutputStream
.computeInt32Size(5, channelTag_);
@@ -366,6 +422,11 @@ public boolean equals(final java.lang.Object obj) {
java.lang.Float.floatToIntBits(getStability())
== java.lang.Float.floatToIntBits(
other.getStability()));
+ result = result && (hasResultEndTime() == other.hasResultEndTime());
+ if (hasResultEndTime()) {
+ result = result && getResultEndTime()
+ .equals(other.getResultEndTime());
+ }
result = result && (getChannelTag()
== other.getChannelTag());
result = result && getLanguageCode()
@@ -391,6 +452,10 @@ public int hashCode() {
hash = (37 * hash) + STABILITY_FIELD_NUMBER;
hash = (53 * hash) + java.lang.Float.floatToIntBits(
getStability());
+ if (hasResultEndTime()) {
+ hash = (37 * hash) + RESULT_END_TIME_FIELD_NUMBER;
+ hash = (53 * hash) + getResultEndTime().hashCode();
+ }
hash = (37 * hash) + CHANNEL_TAG_FIELD_NUMBER;
hash = (53 * hash) + getChannelTag();
hash = (37 * hash) + LANGUAGE_CODE_FIELD_NUMBER;
@@ -544,6 +609,12 @@ public Builder clear() {
stability_ = 0F;
+ if (resultEndTimeBuilder_ == null) {
+ resultEndTime_ = null;
+ } else {
+ resultEndTime_ = null;
+ resultEndTimeBuilder_ = null;
+ }
channelTag_ = 0;
languageCode_ = "";
@@ -587,6 +658,11 @@ public com.google.cloud.speech.v1p1beta1.StreamingRecognitionResult buildPartial
}
result.isFinal_ = isFinal_;
result.stability_ = stability_;
+ if (resultEndTimeBuilder_ == null) {
+ result.resultEndTime_ = resultEndTime_;
+ } else {
+ result.resultEndTime_ = resultEndTimeBuilder_.build();
+ }
result.channelTag_ = channelTag_;
result.languageCode_ = languageCode_;
result.bitField0_ = to_bitField0_;
@@ -670,6 +746,9 @@ public Builder mergeFrom(com.google.cloud.speech.v1p1beta1.StreamingRecognitionR
if (other.getStability() != 0F) {
setStability(other.getStability());
}
+ if (other.hasResultEndTime()) {
+ mergeResultEndTime(other.getResultEndTime());
+ }
if (other.getChannelTag() != 0) {
setChannelTag(other.getChannelTag());
}
@@ -1173,6 +1252,168 @@ public Builder clearStability() {
return this;
}
+ private com.google.protobuf.Duration resultEndTime_ = null;
+ private com.google.protobuf.SingleFieldBuilderV3<
+ com.google.protobuf.Duration, com.google.protobuf.Duration.Builder, com.google.protobuf.DurationOrBuilder> resultEndTimeBuilder_;
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public boolean hasResultEndTime() {
+ return resultEndTimeBuilder_ != null || resultEndTime_ != null;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public com.google.protobuf.Duration getResultEndTime() {
+ if (resultEndTimeBuilder_ == null) {
+ return resultEndTime_ == null ? com.google.protobuf.Duration.getDefaultInstance() : resultEndTime_;
+ } else {
+ return resultEndTimeBuilder_.getMessage();
+ }
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public Builder setResultEndTime(com.google.protobuf.Duration value) {
+ if (resultEndTimeBuilder_ == null) {
+ if (value == null) {
+ throw new NullPointerException();
+ }
+ resultEndTime_ = value;
+ onChanged();
+ } else {
+ resultEndTimeBuilder_.setMessage(value);
+ }
+
+ return this;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public Builder setResultEndTime(
+ com.google.protobuf.Duration.Builder builderForValue) {
+ if (resultEndTimeBuilder_ == null) {
+ resultEndTime_ = builderForValue.build();
+ onChanged();
+ } else {
+ resultEndTimeBuilder_.setMessage(builderForValue.build());
+ }
+
+ return this;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public Builder mergeResultEndTime(com.google.protobuf.Duration value) {
+ if (resultEndTimeBuilder_ == null) {
+ if (resultEndTime_ != null) {
+ resultEndTime_ =
+ com.google.protobuf.Duration.newBuilder(resultEndTime_).mergeFrom(value).buildPartial();
+ } else {
+ resultEndTime_ = value;
+ }
+ onChanged();
+ } else {
+ resultEndTimeBuilder_.mergeFrom(value);
+ }
+
+ return this;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public Builder clearResultEndTime() {
+ if (resultEndTimeBuilder_ == null) {
+ resultEndTime_ = null;
+ onChanged();
+ } else {
+ resultEndTime_ = null;
+ resultEndTimeBuilder_ = null;
+ }
+
+ return this;
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public com.google.protobuf.Duration.Builder getResultEndTimeBuilder() {
+
+ onChanged();
+ return getResultEndTimeFieldBuilder().getBuilder();
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ public com.google.protobuf.DurationOrBuilder getResultEndTimeOrBuilder() {
+ if (resultEndTimeBuilder_ != null) {
+ return resultEndTimeBuilder_.getMessageOrBuilder();
+ } else {
+ return resultEndTime_ == null ?
+ com.google.protobuf.Duration.getDefaultInstance() : resultEndTime_;
+ }
+ }
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ private com.google.protobuf.SingleFieldBuilderV3<
+ com.google.protobuf.Duration, com.google.protobuf.Duration.Builder, com.google.protobuf.DurationOrBuilder>
+ getResultEndTimeFieldBuilder() {
+ if (resultEndTimeBuilder_ == null) {
+ resultEndTimeBuilder_ = new com.google.protobuf.SingleFieldBuilderV3<
+ com.google.protobuf.Duration, com.google.protobuf.Duration.Builder, com.google.protobuf.DurationOrBuilder>(
+ getResultEndTime(),
+ getParentForChildren(),
+ isClean());
+ resultEndTime_ = null;
+ }
+ return resultEndTimeBuilder_;
+ }
+
private int channelTag_ ;
/**
*
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResultOrBuilder.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResultOrBuilder.java
index 445015b286b7..2f39dd41f60c 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResultOrBuilder.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognitionResultOrBuilder.java
@@ -92,6 +92,34 @@ com.google.cloud.speech.v1p1beta1.SpeechRecognitionAlternativeOrBuilder getAlter
*/
float getStability();
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ boolean hasResultEndTime();
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ com.google.protobuf.Duration getResultEndTime();
+ /**
+ *
+ * Output only. Time offset of the end of this result relative to the
+ * beginning of the audio.
+ *
+ *
+ * .google.protobuf.Duration result_end_time = 4;
+ */
+ com.google.protobuf.DurationOrBuilder getResultEndTimeOrBuilder();
+
/**
*
* For multi-channel audio, this is the channel number corresponding to the
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequest.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequest.java
index 5fa3c577f017..6ad9f098c637 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequest.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequest.java
@@ -193,7 +193,7 @@ public com.google.cloud.speech.v1p1beta1.StreamingRecognitionConfigOrBuilder get
* `audio_content` data. The audio bytes must be encoded as specified in
* `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
* pure binary representation (not base64). See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* bytes audio_content = 2;
@@ -782,7 +782,7 @@ public com.google.cloud.speech.v1p1beta1.StreamingRecognitionConfigOrBuilder get
* `audio_content` data. The audio bytes must be encoded as specified in
* `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
* pure binary representation (not base64). See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* bytes audio_content = 2;
@@ -802,7 +802,7 @@ public com.google.protobuf.ByteString getAudioContent() {
* `audio_content` data. The audio bytes must be encoded as specified in
* `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
* pure binary representation (not base64). See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* bytes audio_content = 2;
@@ -825,7 +825,7 @@ public Builder setAudioContent(com.google.protobuf.ByteString value) {
* `audio_content` data. The audio bytes must be encoded as specified in
* `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
* pure binary representation (not base64). See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* bytes audio_content = 2;
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequestOrBuilder.java b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequestOrBuilder.java
index 5dee786892ce..f669b09d7397 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequestOrBuilder.java
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/java/com/google/cloud/speech/v1p1beta1/StreamingRecognizeRequestOrBuilder.java
@@ -47,7 +47,7 @@ public interface StreamingRecognizeRequestOrBuilder extends
* `audio_content` data. The audio bytes must be encoded as specified in
* `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
* pure binary representation (not base64). See
- * [audio limits](https://cloud.google.com/speech/limits#content).
+ * [content limits](/speech-to-text/quotas#content).
*
*
* bytes audio_content = 2;
diff --git a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto
index 208f53633e02..53283d3b7d33 100644
--- a/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto
+++ b/google-api-grpc/proto-google-cloud-speech-v1p1beta1/src/main/proto/google/cloud/speech/v1p1beta1/cloud_speech.proto
@@ -1,4 +1,4 @@
-// Copyright 2018 Google Inc.
+// Copyright 2018 Google LLC.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
@@ -11,6 +11,7 @@
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
+//
syntax = "proto3";
@@ -20,6 +21,7 @@ import "google/api/annotations.proto";
import "google/longrunning/operations.proto";
import "google/protobuf/any.proto";
import "google/protobuf/duration.proto";
+import "google/protobuf/empty.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";
@@ -54,7 +56,8 @@ service Speech {
// Performs bidirectional streaming speech recognition: receive results while
// sending audio. This method is only available via the gRPC API (not REST).
- rpc StreamingRecognize(stream StreamingRecognizeRequest) returns (stream StreamingRecognizeResponse);
+ rpc StreamingRecognize(stream StreamingRecognizeRequest) returns (stream StreamingRecognizeResponse) {
+ }
}
// The top-level message sent by the client for the `Recognize` method.
@@ -98,7 +101,7 @@ message StreamingRecognizeRequest {
// `audio_content` data. The audio bytes must be encoded as specified in
// `RecognitionConfig`. Note: as with all bytes fields, protobuffers use a
// pure binary representation (not base64). See
- // [audio limits](https://cloud.google.com/speech/limits#content).
+ // [content limits](/speech-to-text/quotas#content).
bytes audio_content = 2;
}
}
@@ -218,36 +221,36 @@ message RecognitionConfig {
// Valid values for OGG_OPUS are '1'-'254'.
// Valid value for MULAW, AMR, AMR_WB and SPEEX_WITH_HEADER_BYTE is only `1`.
// If `0` or omitted, defaults to one channel (mono).
- // NOTE: We only recognize the first channel by default.
+ // Note: We only recognize the first channel by default.
// To perform independent recognition on each channel set
- // enable_separate_recognition_per_channel to 'true'.
+ // `enable_separate_recognition_per_channel` to 'true'.
int32 audio_channel_count = 7;
- // This needs to be set to ‘true’ explicitly and audio_channel_count > 1
+ // This needs to be set to ‘true’ explicitly and `audio_channel_count` > 1
// to get each channel recognized separately. The recognition result will
- // contain a channel_tag field to state which channel that result belongs to.
- // If this is not ‘true’, we will only recognize the first channel.
- // NOTE: The request is also billed cumulatively for all channels recognized:
- // (audio_channel_count times the audio length)
+ // contain a `channel_tag` field to state which channel that result belongs
+ // to. If this is not true, we will only recognize the first channel. The
+ // request is billed cumulatively for all channels recognized:
+ // `audio_channel_count` multiplied by the length of the audio.
bool enable_separate_recognition_per_channel = 12;
// *Required* The language of the supplied audio as a
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag.
// Example: "en-US".
- // See [Language Support](https://cloud.google.com/speech/docs/languages)
+ // See [Language Support](/speech-to-text/docs/languages)
// for a list of the currently supported language codes.
string language_code = 3;
// *Optional* A list of up to 3 additional
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tags,
// listing possible alternative languages of the supplied audio.
- // See [Language Support](https://cloud.google.com/speech/docs/languages)
+ // See [Language Support](/speech-to-text/docs/languages)
// for a list of the currently supported language codes.
// If alternative languages are listed, recognition result will contain
// recognition in the most likely language detected including the main
// language_code. The recognition result will include the language tag
// of the language detected in the audio.
- // NOTE: This feature is only supported for Voice Command and Voice Search
+ // Note: This feature is only supported for Voice Command and Voice Search
// use cases and performance may vary for other use cases (e.g., phone call
// transcription).
repeated string alternative_language_codes = 18;
@@ -266,7 +269,9 @@ message RecognitionConfig {
// won't be filtered out.
bool profanity_filter = 5;
- // *Optional* A means to provide context to assist the speech recognition.
+ // *Optional* array of [SpeechContext][google.cloud.speech.v1p1beta1.SpeechContext].
+ // A means to provide context to assist the speech recognition. For more
+ // information, see [Phrase Hints](/speech-to-text/docs/basics#phrase-hints).
repeated SpeechContext speech_contexts = 6;
// *Optional* If `true`, the top result includes a list of words and
@@ -284,18 +289,20 @@ message RecognitionConfig {
// This feature is only available in select languages. Setting this for
// requests in other languages has no effect at all.
// The default 'false' value does not add punctuation to result hypotheses.
- // NOTE: "This is currently offered as an experimental service, complimentary
+ // Note: This is currently offered as an experimental service, complimentary
// to all users. In the future this may be exclusively available as a
- // premium feature."
+ // premium feature.
bool enable_automatic_punctuation = 11;
// *Optional* If 'true', enables speaker detection for each recognized word in
// the top alternative of the recognition result using a speaker_tag provided
// in the WordInfo.
// Note: When this is true, we send all the words from the beginning of the
- // audio for the top alternative in every consecutive responses.
+ // audio for the top alternative in every consecutive STREAMING responses.
// This is done in order to improve our speaker tags as our models learn to
// identify the speakers in the conversation over time.
+ // For non-streaming requests, the diarization results will be provided only
+ // in the top alternative of the FINAL SpeechRecognitionResult.
bool enable_speaker_diarization = 16;
// *Optional*
@@ -342,14 +349,18 @@ message RecognitionConfig {
string model = 13;
// *Optional* Set to true to use an enhanced model for speech recognition.
- // You must also set the `model` field to a valid, enhanced model. If
- // `use_enhanced` is set to true and the `model` field is not set, then
- // `use_enhanced` is ignored. If `use_enhanced` is true and an enhanced
- // version of the specified model does not exist, then the speech is
- // recognized using the standard version of the specified model.
+ // If `use_enhanced` is set to true and the `model` field is not set, then
+ // an appropriate enhanced model is chosen if:
+ // 1. project is eligible for requesting enhanced models
+ // 2. an enhanced model exists for the audio
+ //
+ // If `use_enhanced` is true and an enhanced version of the specified model
+ // does not exist, then the speech is recognized using the standard version
+ // of the specified model.
//
- // Enhanced speech models require that you opt-in to the audio logging using
- // instructions in the [alpha documentation](/speech/data-sharing). If you set
+ // Enhanced speech models require that you opt-in to data logging using
+ // instructions in the
+ // [documentation](/speech-to-text/docs/enable-data-logging). If you set
// `use_enhanced` to true and you have not enabled audio logging, then you
// will receive an error.
bool use_enhanced = 14;
@@ -494,14 +505,14 @@ message SpeechContext {
// to improve the accuracy for specific words and phrases, for example, if
// specific commands are typically spoken by the user. This can also be used
// to add additional words to the vocabulary of the recognizer. See
- // [usage limits](https://cloud.google.com/speech/limits#content).
+ // [usage limits](/speech-to-text/quotas#content).
repeated string phrases = 1;
}
// Contains audio data in the encoding specified in the `RecognitionConfig`.
// Either `content` or `uri` must be supplied. Supplying both or neither
// returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]. See
-// [audio limits](https://cloud.google.com/speech/limits#content).
+// [content limits](/speech-to-text/quotas#content).
message RecognitionAudio {
// The audio source, which is either inline content or a Google Cloud
// Storage uri.
@@ -512,7 +523,8 @@ message RecognitionAudio {
bytes content = 1;
// URI that points to a file that contains audio data bytes as specified in
- // `RecognitionConfig`. Currently, only Google Cloud Storage URIs are
+ // `RecognitionConfig`. The file must not be compressed (for example, gzip).
+ // Currently, only Google Cloud Storage URIs are
// supported, which must be specified in the following format:
// `gs://bucket_name/object_name` (other URI formats return
// [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]). For more information, see
@@ -658,6 +670,10 @@ message StreamingRecognitionResult {
// The default of 0.0 is a sentinel value indicating `stability` was not set.
float stability = 3;
+ // Output only. Time offset of the end of this result relative to the
+ // beginning of the audio.
+ google.protobuf.Duration result_end_time = 4;
+
// For multi-channel audio, this is the channel number corresponding to the
// recognized result for the audio from that channel.
// For audio_channel_count = N, its output values can range from '1' to 'N'.
@@ -705,7 +721,7 @@ message SpeechRecognitionAlternative {
float confidence = 2;
// Output only. A list of word-specific information for each recognized word.
- // Note: When enable_speaker_diarization is true, you will see all the words
+ // Note: When `enable_speaker_diarization` is true, you will see all the words
// from the beginning of the audio.
repeated WordInfo words = 3;
}
@@ -746,5 +762,4 @@ message WordInfo {
// speaker_tag is set if enable_speaker_diarization = 'true' and only in the
// top alternative.
int32 speaker_tag = 5;
-
}