feat(speech): update the API

#### speech:v1

The following keys were added:
- schemas.LongRunningRecognizeResponse.properties.outputConfig.$ref
- schemas.LongRunningRecognizeResponse.properties.outputConfig.description
- schemas.LongRunningRecognizeResponse.properties.outputError.$ref
- schemas.LongRunningRecognizeResponse.properties.outputError.description

The following keys were changed:
- schemas.RecognitionConfig.properties.encoding.enum
- schemas.RecognitionConfig.properties.encoding.enumDescriptions

discovery/speech-v1.json

@@ -212,7 +212,7 @@
       }
     }
   },
-  "revision": "20210825",
+  "revision": "20210929",
   "rootUrl": "https://speech.googleapis.com/",
   "schemas": {
     "ListOperationsResponse": {
@@ -283,6 +283,14 @@
       "description": "The only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.",
       "id": "LongRunningRecognizeResponse",
       "properties": {
+        "outputConfig": {
+          "$ref": "TranscriptOutputConfig",
+          "description": "Original output config if present in the request."
+        },
+        "outputError": {
+          "$ref": "Status",
+          "description": "If the transcript output fails this field contains the relevant error."
+        },
         "results": {
           "description": "Sequential list of transcription results corresponding to sequential portions of audio.",
           "items": {
@@ -384,7 +392,8 @@
             "AMR",
             "AMR_WB",
             "OGG_OPUS",
-            "SPEEX_WITH_HEADER_BYTE"
+            "SPEEX_WITH_HEADER_BYTE",
+            "WEBM_OPUS"
           ],
           "enumDescriptions": [
             "Not specified.",
@@ -394,7 +403,8 @@
             "Adaptive Multi-Rate Narrowband codec. `sample_rate_hertz` must be 8000.",
             "Adaptive Multi-Rate Wideband codec. `sample_rate_hertz` must be 16000.",
             "Opus encoded audio frames in Ogg container ([OggOpus](https://wiki.xiph.org/OggOpus)). `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000.",
-            "Although the use of lossy encodings is not recommended, if a very low bitrate encoding is required, `OGG_OPUS` is highly preferred over Speex encoding. The [Speex](https://speex.org/) encoding supported by Cloud Speech API has a header byte in each block, as in MIME type `audio/x-speex-with-header-byte`. It is a variant of the RTP Speex encoding defined in [RFC 5574](https://tools.ietf.org/html/rfc5574). The stream is a sequence of blocks, one block per RTP packet. Each block starts with a byte containing the length of the block, in bytes, followed by one or more frames of Speex data, padded to an integral number of bytes (octets) as specified in RFC 5574. In other words, each RTP header is replaced with a single byte containing the block length. Only Speex wideband is supported. `sample_rate_hertz` must be 16000."
+            "Although the use of lossy encodings is not recommended, if a very low bitrate encoding is required, `OGG_OPUS` is highly preferred over Speex encoding. The [Speex](https://speex.org/) encoding supported by Cloud Speech API has a header byte in each block, as in MIME type `audio/x-speex-with-header-byte`. It is a variant of the RTP Speex encoding defined in [RFC 5574](https://tools.ietf.org/html/rfc5574). The stream is a sequence of blocks, one block per RTP packet. Each block starts with a byte containing the length of the block, in bytes, followed by one or more frames of Speex data, padded to an integral number of bytes (octets) as specified in RFC 5574. In other words, each RTP header is replaced with a single byte containing the block length. Only Speex wideband is supported. `sample_rate_hertz` must be 16000.",
+            "Opus encoded audio frames in WebM container ([OggOpus](https://wiki.xiph.org/OggOpus)). This is a Beta features and only available in v1p1beta1. `sample_rate_hertz` must be one of 8000, 12000, 16000, 24000, or 48000."
           ],
           "type": "string"
         },

src/apis/speech/v1.ts

@@ -182,6 +182,14 @@ export namespace speech_v1 {
    * The only message returned to the client by the `LongRunningRecognize` method. It contains the result as zero or more sequential `SpeechRecognitionResult` messages. It is included in the `result.response` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
    */
   export interface Schema$LongRunningRecognizeResponse {
+    /**
+     * Original output config if present in the request.
+     */
+    outputConfig?: Schema$TranscriptOutputConfig;
+    /**
+     * If the transcript output fails this field contains the relevant error.
+     */
+    outputError?: Schema$Status;
     /**
      * Sequential list of transcription results corresponding to sequential portions of audio.
      */