feat(speech): update the api

#### speech:v1

The following keys were added:
- schemas.RecognitionConfig.properties.enableSpokenEmojis.type (Total Keys: 1)
- schemas.RecognitionConfig.properties.enableSpokenPunctuation.type (Total Keys: 1)

Author: yoshi-automation

docs/dyn/speech_v1.speech.html

@@ -115,6 +115,8 @@ <h3>Method Details</h3>
     },
     &quot;enableAutomaticPunctuation&quot;: True or False, # If &#x27;true&#x27;, adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default &#x27;false&#x27; value does not add punctuation to result hypotheses.
     &quot;enableSeparateRecognitionPerChannel&quot;: True or False, # This needs to be set to `true` explicitly and `audio_channel_count` &gt; 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. The request is billed cumulatively for all channels recognized: `audio_channel_count` multiplied by the length of the audio.
+    &quot;enableSpokenEmojis&quot;: True or False, # The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If &#x27;true&#x27;, adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If &#x27;false&#x27;, spoken emojis are not replaced.
+    &quot;enableSpokenPunctuation&quot;: True or False, # The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If &#x27;true&#x27;, replaces spoken punctuation with the corresponding symbols in the request. For example, &quot;how are you question mark&quot; becomes &quot;how are you?&quot;. See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If &#x27;false&#x27;, spoken punctuation is not replaced.
     &quot;enableWordConfidence&quot;: True or False, # If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.
     &quot;enableWordTimeOffsets&quot;: True or False, # If `true`, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If `false`, no word-level time offset information is returned. The default is `false`.
     &quot;encoding&quot;: &quot;A String&quot;, # 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 AudioEncoding.
@@ -202,6 +204,8 @@ <h3>Method Details</h3>
     },
     &quot;enableAutomaticPunctuation&quot;: True or False, # If &#x27;true&#x27;, adds punctuation to recognition result hypotheses. This feature is only available in select languages. Setting this for requests in other languages has no effect at all. The default &#x27;false&#x27; value does not add punctuation to result hypotheses.
     &quot;enableSeparateRecognitionPerChannel&quot;: True or False, # This needs to be set to `true` explicitly and `audio_channel_count` &gt; 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. The request is billed cumulatively for all channels recognized: `audio_channel_count` multiplied by the length of the audio.
+    &quot;enableSpokenEmojis&quot;: True or False, # The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If &#x27;true&#x27;, adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If &#x27;false&#x27;, spoken emojis are not replaced.
+    &quot;enableSpokenPunctuation&quot;: True or False, # The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If &#x27;true&#x27;, replaces spoken punctuation with the corresponding symbols in the request. For example, &quot;how are you question mark&quot; becomes &quot;how are you?&quot;. See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If &#x27;false&#x27;, spoken punctuation is not replaced.
     &quot;enableWordConfidence&quot;: True or False, # If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.
     &quot;enableWordTimeOffsets&quot;: True or False, # If `true`, the top result includes a list of words and the start and end time offsets (timestamps) for those words. If `false`, no word-level time offset information is returned. The default is `false`.
     &quot;encoding&quot;: &quot;A String&quot;, # 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 AudioEncoding.

googleapiclient/discovery_cache/documents/speech.v1.json

@@ -212,7 +212,7 @@
       }
     }
   },
-  "revision": "20211008",
+  "revision": "20211021",
   "rootUrl": "https://speech.googleapis.com/",
   "schemas": {
     "ListOperationsResponse": {
@@ -385,6 +385,14 @@
           "description": "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. The request is billed cumulatively for all channels recognized: `audio_channel_count` multiplied by the length of the audio.",
           "type": "boolean"
         },
+        "enableSpokenEmojis": {
+          "description": "The spoken emoji behavior for the call If not set, uses default behavior based on model of choice If 'true', adds spoken emoji formatting for the request. This will replace spoken emojis with the corresponding Unicode symbols in the final transcript. If 'false', spoken emojis are not replaced.",
+          "type": "boolean"
+        },
+        "enableSpokenPunctuation": {
+          "description": "The spoken punctuation behavior for the call If not set, uses default behavior based on model of choice e.g. command_and_search will enable spoken punctuation by default If 'true', replaces spoken punctuation with the corresponding symbols in the request. For example, \"how are you question mark\" becomes \"how are you?\". See https://cloud.google.com/speech-to-text/docs/spoken-punctuation for support. If 'false', spoken punctuation is not replaced.",
+          "type": "boolean"
+        },
         "enableWordConfidence": {
           "description": "If `true`, the top result includes a list of words and the confidence for those words. If `false`, no word-level confidence information is returned. The default is `false`.",
           "type": "boolean"

googleapiclient/discovery_cache/documents/speech.v1p1beta1.json

@@ -524,7 +524,7 @@
       }
     }
   },
-  "revision": "20211008",
+  "revision": "20211021",
   "rootUrl": "https://speech.googleapis.com/",
   "schemas": {
     "ClassItem": {

googleapiclient/discovery_cache/documents/speech.v2beta1.json

@@ -184,7 +184,7 @@
       }
     }
   },
-  "revision": "20211008",
+  "revision": "20211021",
   "rootUrl": "https://speech.googleapis.com/",
   "schemas": {
     "ListOperationsResponse": {