google-cloud-speech-v1p1beta1 0.16.0 → 0.17.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: a5f8a422d44657d200973215f7be62dc602e85670f696b63a5f746098bf95363
-  data.tar.gz: 66ffa2a37d29b3a6397e7eacbd45313c540b9c897bd1f28e1416bb2db44e8a9a
+  metadata.gz: 3fb51328890358e72c887d4c047bbe5380b02f67a57e19a315a824f35fedf151
+  data.tar.gz: 76ad18cf2a0031d1d491e791fd84f45cc67f84abb59361a3366a116dc640b4c3
 SHA512:
-  metadata.gz: 8c653961c30391c40cb6cc1e3c84a503d9de996a3b78a8cb5fe09e4736493d26cf8c6fef6bb9c31f32ce84fd20954bf31fddd295923350f7f553c7df0542b7af
-  data.tar.gz: f0272fb389329bcfcd9b83c2db707057dd7d5adcfd018e9889b3e391e7297c5f5beb51030c1170eec261f3746e64d7f18b5c27b673e762e2c6e7bde606f68754
+  metadata.gz: b59f26dd15aa099a0e4b048a90e44d2a7bd4d745a10c047939508923c0ef515172378efbc0b75fff35c9f74603ed8ee585a6b7e659e5a2c898260a622ee32385
+  data.tar.gz: 0420ff684d70303bf3f1fdfe38bb31ae944807c0441215d507b6e6a4fa027032a2d5b2c5a582cc51db7f659e9d87167ad53668b012d7ec55b3720a20767a8402

data/README.md

@@ -1,6 +1,6 @@
 # Ruby Client for the Cloud Speech-to-Text V1p1beta1 API
 
-API Client library for the Cloud Speech-to-Text V1p1beta1 API
+Converts audio to text by applying powerful neural network models.
 
 Google Speech-to-Text enables developers to convert audio to text by applying powerful neural network models in an easy-to-use API. The API recognizes more than 120 languages and variants to support your global user base. You can enable voice command-and-control, transcribe audio from call centers, and more. It can process real-time streaming or prerecorded audio, using Google's machine learning technology.
 

data/lib/google/cloud/speech/v1p1beta1/cloud_speech_pb.rb

@@ -39,6 +39,12 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
       optional :config, :message, 1, "google.cloud.speech.v1p1beta1.RecognitionConfig"
       optional :single_utterance, :bool, 2
       optional :interim_results, :bool, 3
+      optional :enable_voice_activity_events, :bool, 5
+      optional :voice_activity_timeout, :message, 6, "google.cloud.speech.v1p1beta1.StreamingRecognitionConfig.VoiceActivityTimeout"
+    end
+    add_message "google.cloud.speech.v1p1beta1.StreamingRecognitionConfig.VoiceActivityTimeout" do
+      optional :speech_start_timeout, :message, 1, "google.protobuf.Duration"
+      optional :speech_end_timeout, :message, 2, "google.protobuf.Duration"
     end
     add_message "google.cloud.speech.v1p1beta1.RecognitionConfig" do
       optional :encoding, :enum, 1, "google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding"
@@ -159,6 +165,7 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
       optional :error, :message, 1, "google.rpc.Status"
       repeated :results, :message, 2, "google.cloud.speech.v1p1beta1.StreamingRecognitionResult"
       optional :speech_event_type, :enum, 4, "google.cloud.speech.v1p1beta1.StreamingRecognizeResponse.SpeechEventType"
+      optional :speech_event_time, :message, 8, "google.protobuf.Duration"
       optional :total_billed_time, :message, 5, "google.protobuf.Duration"
       optional :speech_adaptation_info, :message, 9, "google.cloud.speech.v1p1beta1.SpeechAdaptationInfo"
       optional :request_id, :int64, 10
@@ -166,6 +173,9 @@ Google::Protobuf::DescriptorPool.generated_pool.build do
     add_enum "google.cloud.speech.v1p1beta1.StreamingRecognizeResponse.SpeechEventType" do
       value :SPEECH_EVENT_UNSPECIFIED, 0
       value :END_OF_SINGLE_UTTERANCE, 1
+      value :SPEECH_ACTIVITY_BEGIN, 2
+      value :SPEECH_ACTIVITY_END, 3
+      value :SPEECH_ACTIVITY_TIMEOUT, 4
     end
     add_message "google.cloud.speech.v1p1beta1.StreamingRecognitionResult" do
       repeated :alternatives, :message, 1, "google.cloud.speech.v1p1beta1.SpeechRecognitionAlternative"
@@ -209,6 +219,7 @@ module Google
         TranscriptOutputConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.TranscriptOutputConfig").msgclass
         StreamingRecognizeRequest = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.StreamingRecognizeRequest").msgclass
         StreamingRecognitionConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.StreamingRecognitionConfig").msgclass
+        StreamingRecognitionConfig::VoiceActivityTimeout = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.StreamingRecognitionConfig.VoiceActivityTimeout").msgclass
         RecognitionConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.RecognitionConfig").msgclass
         RecognitionConfig::AudioEncoding = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.RecognitionConfig.AudioEncoding").enummodule
         SpeakerDiarizationConfig = ::Google::Protobuf::DescriptorPool.generated_pool.lookup("google.cloud.speech.v1p1beta1.SpeakerDiarizationConfig").msgclass

data/lib/google/cloud/speech/v1p1beta1/version.rb

@@ -21,7 +21,7 @@ module Google
   module Cloud
     module Speech
       module V1p1beta1
-        VERSION = "0.16.0"
+        VERSION = "0.17.0"
       end
     end
   end

data/proto_docs/google/cloud/speech/v1p1beta1/cloud_speech.rb

@@ -122,9 +122,30 @@ module Google
         #     returned as they become available (these interim results are indicated with
         #     the `is_final=false` flag).
         #     If `false` or omitted, only `is_final=true` result(s) are returned.
+        # @!attribute [rw] enable_voice_activity_events
+        #   @return [::Boolean]
+        #     If `true`, responses with voice activity speech events will be returned as
+        #     they are detected.
+        # @!attribute [rw] voice_activity_timeout
+        #   @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognitionConfig::VoiceActivityTimeout]
+        #     If set, the server will automatically close the stream after the specified
+        #     duration has elapsed after the last VOICE_ACTIVITY speech event has been
+        #     sent. The field `voice_activity_events` must also be set to true.
         class StreamingRecognitionConfig
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
+
+          # Events that a timeout can be set on for voice activity.
+          # @!attribute [rw] speech_start_timeout
+          #   @return [::Google::Protobuf::Duration]
+          #     Duration to timeout the stream if no speech begins.
+          # @!attribute [rw] speech_end_timeout
+          #   @return [::Google::Protobuf::Duration]
+          #     Duration to timeout the stream after speech ends.
+          class VoiceActivityTimeout
+            include ::Google::Protobuf::MessageExts
+            extend ::Google::Protobuf::MessageExts::ClassMethods
+          end
         end
 
         # Provides information to the recognizer that specifies how to process the
@@ -133,7 +154,8 @@ module Google
         #   @return [::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding]
         #     Encoding of audio data sent in all `RecognitionAudio` messages.
         #     This field is optional for `FLAC` and `WAV` audio files and required
-        #     for all other audio formats. For details, see {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
+        #     for all other audio formats. For details, see
+        #     {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
         # @!attribute [rw] sample_rate_hertz
         #   @return [::Integer]
         #     Sample rate in Hertz of the audio data sent in all
@@ -142,7 +164,8 @@ module Google
         #     source to 16000 Hz. If that's not possible, use the native sample rate of
         #     the audio source (instead of re-sampling).
         #     This field is optional for FLAC and WAV audio files, but is
-        #     required for all other audio formats. For details, see {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
+        #     required for all other audio formats. For details, see
+        #     {::Google::Cloud::Speech::V1p1beta1::RecognitionConfig::AudioEncoding AudioEncoding}.
         # @!attribute [rw] audio_channel_count
         #   @return [::Integer]
         #     The number of channels in the input audio data.
@@ -363,7 +386,8 @@ module Google
           # an `AudioEncoding` when you send  send `FLAC` or `WAV` audio, the
           # encoding configuration must match the encoding described in the audio
           # header; otherwise the request returns an
-          # [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error code.
+          # [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT] error
+          # code.
           module AudioEncoding
             # Not specified.
             ENCODING_UNSPECIFIED = 0
@@ -612,8 +636,8 @@ module Google
 
         # 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
-        # [content limits](https://cloud.google.com/speech-to-text/quotas#content).
+        # returns [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT].
+        # See [content limits](https://cloud.google.com/speech-to-text/quotas#content).
         # @!attribute [rw] content
         #   @return [::String]
         #     The audio data bytes encoded as specified in
@@ -626,8 +650,9 @@ module Google
         #     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
-        #     [Request URIs](https://cloud.google.com/storage/docs/reference-uris).
+        #     [google.rpc.Code.INVALID_ARGUMENT][google.rpc.Code.INVALID_ARGUMENT]).
+        #     For more information, see [Request
+        #     URIs](https://cloud.google.com/storage/docs/reference-uris).
         class RecognitionAudio
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -700,11 +725,12 @@ module Google
         #     Time of the most recent processing update.
         # @!attribute [r] uri
         #   @return [::String]
-        #     Output only. The URI of the audio file being transcribed. Empty if the audio was sent
-        #     as byte content.
+        #     Output only. The URI of the audio file being transcribed. Empty if the
+        #     audio was sent as byte content.
         # @!attribute [r] output_config
         #   @return [::Google::Cloud::Speech::V1p1beta1::TranscriptOutputConfig]
-        #     Output only. A copy of the TranscriptOutputConfig if it was set in the request.
+        #     Output only. A copy of the TranscriptOutputConfig if it was set in the
+        #     request.
         class LongRunningRecognizeMetadata
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -772,6 +798,9 @@ module Google
         # @!attribute [rw] speech_event_type
         #   @return [::Google::Cloud::Speech::V1p1beta1::StreamingRecognizeResponse::SpeechEventType]
         #     Indicates the type of speech event.
+        # @!attribute [rw] speech_event_time
+        #   @return [::Google::Protobuf::Duration]
+        #     Time offset between the beginning of the audio and event emission.
         # @!attribute [rw] total_billed_time
         #   @return [::Google::Protobuf::Duration]
         #     When available, billed audio seconds for the stream.
@@ -800,6 +829,23 @@ module Google
             # until the server closes the gRPC connection. This event is only sent if
             # `single_utterance` was set to `true`, and is not used otherwise.
             END_OF_SINGLE_UTTERANCE = 1
+
+            # This event indicates that the server has detected the beginning of human
+            # voice activity in the stream. This event can be returned multiple times
+            # if speech starts and stops repeatedly throughout the stream. This event
+            # is only sent if `voice_activity_events` is set to true.
+            SPEECH_ACTIVITY_BEGIN = 2
+
+            # This event indicates that the server has detected the end of human voice
+            # activity in the stream. This event can be returned multiple times if
+            # speech starts and stops repeatedly throughout the stream. This event is
+            # only sent if `voice_activity_events` is set to true.
+            SPEECH_ACTIVITY_END = 3
+
+            # This event indicates that the user-set timeout for speech activity begin
+            # or end has exceeded. Upon receiving this event, the client is expected to
+            # send a half close. Further audio will not be processed.
+            SPEECH_ACTIVITY_TIMEOUT = 4
           end
         end
 
@@ -836,9 +882,9 @@ module Google
         #     For audio_channel_count = N, its output values can range from '1' to 'N'.
         # @!attribute [r] language_code
         #   @return [::String]
-        #     Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag
-        #     of the language in this result. This language code was detected to have
-        #     the most likelihood of being spoken in the audio.
+        #     Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
+        #     language tag of the language in this result. This language code was
+        #     detected to have the most likelihood of being spoken in the audio.
         class StreamingRecognitionResult
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods
@@ -862,9 +908,9 @@ module Google
         #     beginning of the audio.
         # @!attribute [r] language_code
         #   @return [::String]
-        #     Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt) language tag
-        #     of the language in this result. This language code was detected to have
-        #     the most likelihood of being spoken in the audio.
+        #     Output only. The [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt)
+        #     language tag of the language in this result. This language code was
+        #     detected to have the most likelihood of being spoken in the audio.
         class SpeechRecognitionResult
           include ::Google::Protobuf::MessageExts
           extend ::Google::Protobuf::MessageExts::ClassMethods

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: google-cloud-speech-v1p1beta1
 version: !ruby/object:Gem::Version
-  version: 0.16.0
+  version: 0.17.0
 platform: ruby
 authors:
 - Google LLC
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-02-23 00:00:00.000000000 Z
+date: 2023-02-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: gapic-common
@@ -16,7 +16,7 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.17.1
+        version: 0.18.0
     - - "<"
       - !ruby/object:Gem::Version
         version: 2.a
@@ -26,7 +26,7 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 0.17.1
+        version: 0.18.0
     - - "<"
       - !ruby/object:Gem::Version
         version: 2.a
@@ -236,5 +236,5 @@ requirements: []
 rubygems_version: 3.4.2
 signing_key: 
 specification_version: 4
-summary: API Client library for the Cloud Speech-to-Text V1p1beta1 API
+summary: Converts audio to text by applying powerful neural network models.
 test_files: []