[Call Automation] Adding custom models for Play/Recognize (Azure#26406)

### Packages impacted by this PR


### Issues associated with this PR


### Describe the problem that is addressed by this PR


### What are the possible designs available to address the problem? If
there are more than one possible design, why was the one in this PR
chosen?


### Are there test cases added in this PR? _(If not, why?)_


### Provide a list of related PRs _(if any)_


### Command used to generate this PR:**_(Applicable only to SDK release
request PRs)_

### Checklists
- [ ] Added impacted package name to the issue description
- [ ] Does this PR needs any fixes in the SDK Generator?** _(If so,
create an Issue in the
[Autorest/typescript](https://github.com/Azure/autorest.typescript)
repository and link it here)_
- [ ] Added a changelog (if necessary)

sdk/communication/communication-call-automation/package.json

@@ -79,6 +79,7 @@
     "@azure/core-rest-pipeline": "^1.3.0",
     "@azure/core-tracing": "^1.0.0",
     "@azure/logger": "^1.0.0",
+    "esm": "^3.2.25",
     "events": "^3.0.0",
     "tslib": "^2.2.0",
     "uuid": "^8.3.0"

sdk/communication/communication-call-automation/review/communication-call-automation.api.md

@@ -196,6 +196,8 @@ export interface CallMediaRecognizeOptions extends OperationOptions {
     // (undocumented)
     playPrompt?: FileSource | TextSource | SsmlSource;
     // (undocumented)
+    speechModelEndpointId?: string;
+    // (undocumented)
     stopCurrentOperations?: boolean;
 }
 
@@ -856,6 +858,8 @@ export interface SendDtmfOptions extends OperationOptions {
 
 // @public
 export interface SsmlSource extends PlaySource {
+    // (undocumented)
+    customVoiceEndpointId?: string;
     // (undocumented)
     readonly kind: "ssmlSource";
     // (undocumented)
@@ -878,6 +882,8 @@ export type StopRecordingOptions = OperationOptions;
 
 // @public
 export interface TextSource extends PlaySource {
+    // (undocumented)
+    customVoiceEndpointId?: string;
     // (undocumented)
     readonly kind: "textSource";
     // (undocumented)

sdk/communication/communication-call-automation/src/callMedia.ts

@@ -79,6 +79,7 @@ export class CallMedia {
         sourceLocale: playSource.sourceLocale,
         voiceGender: playSource.voiceGender,
         voiceName: playSource.voiceName,
+        customVoiceEndpointId: playSource.customVoiceEndpointId,
       };
       return {
         sourceType: KnownPlaySourceType.Text,
@@ -88,6 +89,7 @@ export class CallMedia {
     } else if (playSource.kind === "ssmlSource") {
       const ssmlSource: SsmlSourceInternal = {
         ssmlText: playSource.ssmlText,
+        customVoiceEndpointId: playSource.customVoiceEndpointId,
       };
       return {
         sourceType: KnownPlaySourceType.Ssml,
@@ -215,6 +217,7 @@ export class CallMedia {
           : 5,
         targetParticipant: serializeCommunicationIdentifier(targetParticipant),
         speechOptions: speechOptions,
+        speechRecognitionModelEndpointId: recognizeOptions.speechModelEndpointId,
       };
       return {
         recognizeInputType: KnownRecognizeInputType.Speech,
@@ -246,6 +249,7 @@ export class CallMedia {
         targetParticipant: serializeCommunicationIdentifier(targetParticipant),
         speechOptions: speechOptions,
         dtmfOptions: dtmfOptionsInternal,
+        speechRecognitionModelEndpointId: recognizeOptions.speechModelEndpointId,
       };
       return {
         recognizeInputType: KnownRecognizeInputType.SpeechOrDtmf,

sdk/communication/communication-call-automation/src/models/models.ts

@@ -89,12 +89,14 @@ export interface TextSource extends PlaySource {
   sourceLocale?: string;
   voiceGender?: Gender;
   voiceName?: string;
+  customVoiceEndpointId?: string;
   readonly kind: "textSource";
 }
 
 /** The SsmlSource model. */
 export interface SsmlSource extends PlaySource {
   ssmlText: string;
+  customVoiceEndpointId?: string;
   readonly kind: "ssmlSource";
 }
 

sdk/communication/communication-call-automation/src/models/options.ts

@@ -26,6 +26,7 @@ export interface CallMediaRecognizeOptions extends OperationOptions {
   operationContext?: string;
   interruptPrompt?: boolean;
   initialSilenceTimeoutInSeconds?: number;
+  speechModelEndpointId?: string;
 }
 
 /** The recognize configuration specific to Dtmf. */

sdk/communication/communication-call-automation/test/callMediaClient.spec.ts

@@ -97,6 +97,7 @@ describe("CallMedia Unit Tests", async function () {
 
     const playSource: TextSource = {
       text: "test test test",
+      customVoiceEndpointId: "customVoiceEndpointId",
       kind: "textSource",
     };
 
@@ -121,6 +122,7 @@ describe("CallMedia Unit Tests", async function () {
     const playSource: SsmlSource = {
       ssmlText:
         '<speak version="1.0" xmlns="http://www.w3.org/2001/10/synthesis" xml:lang="en-US"><voice name="en-US-JennyNeural">Recognize Choice Completed, played through SSML source.</voice></speak>',
+      customVoiceEndpointId: "customVoiceEndpointId",
       kind: "ssmlSource",
     };
 
@@ -211,6 +213,7 @@ describe("CallMedia Unit Tests", async function () {
     const targetParticipant: CommunicationIdentifier = { communicationUserId: CALL_TARGET_ID };
     const recognizeOptions: CallMediaRecognizeSpeechOptions = {
       kind: "callMediaRecognizeSpeechOptions",
+      speechModelEndpointId: "customModelEndpointId",
     };
     const maxTonesToCollect = 5;