add audio response modality and fix voiceName

Author: dlarocque

common/api-review/ai.api.md

@@ -866,7 +866,7 @@ export const POSSIBLE_ROLES: readonly ["user", "model", "function", "system"];
 
 // @beta
 export interface PrebuiltVoiceConfig {
-    voiceConfig?: string;
+    voiceName?: string;
 }
 
 // @public
@@ -888,6 +888,7 @@ export interface RequestOptions {
 export const ResponseModality: {
     readonly TEXT: "TEXT";
     readonly IMAGE: "IMAGE";
+    readonly AUDIO: "AUDIO";
 };
 
 // @beta

docs-devsite/ai.md

@@ -663,6 +663,7 @@ Generation modalities to be returned in generation responses.
 ResponseModality: {
     readonly TEXT: "TEXT";
     readonly IMAGE: "IMAGE";
+    readonly AUDIO: "AUDIO";
 }
 ```
 

docs-devsite/ai.prebuiltvoiceconfig.md

@@ -25,9 +25,9 @@ export interface PrebuiltVoiceConfig
 
 |  Property | Type | Description |
 |  --- | --- | --- |
-|  [voiceConfig](./ai.prebuiltvoiceconfig.md#prebuiltvoiceconfigvoiceconfig) | string | <b><i>(Public Preview)</i></b> The voice name to use for speech synthesis.<!-- -->For a full list of names and demos of what each voice sounds like, see [Chirp 3: HD Voices](https://cloud.google.com/text-to-speech/docs/chirp3-hd)<!-- -->. |
+|  [voiceName](./ai.prebuiltvoiceconfig.md#prebuiltvoiceconfigvoicename) | string | <b><i>(Public Preview)</i></b> The voice name to use for speech synthesis.<!-- -->For a full list of names and demos of what each voice sounds like, see [Chirp 3: HD Voices](https://cloud.google.com/text-to-speech/docs/chirp3-hd)<!-- -->. |
 
-## PrebuiltVoiceConfig.voiceConfig
+## PrebuiltVoiceConfig.voiceName
 
 > This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
 > 
@@ -39,5 +39,5 @@ For a full list of names and demos of what each voice sounds like, see [Chirp 3:
 <b>Signature:</b>
 
 ```typescript
-voiceConfig?: string;
+voiceName?: string;
 ```

packages/ai/src/types/enums.ts

@@ -325,7 +325,12 @@ export const ResponseModality = {
    * Image.
    * @beta
    */
-  IMAGE: 'IMAGE'
+  IMAGE: 'IMAGE',
+  /**
+   * Audio.
+   * @beta
+   */
+  AUDIO: 'AUDIO'
 } as const;
 
 /**

packages/ai/src/types/requests.ts

@@ -369,7 +369,7 @@ export interface PrebuiltVoiceConfig {
    *
    * For a full list of names and demos of what each voice sounds like, see {@link https://cloud.google.com/text-to-speech/docs/chirp3-hd | Chirp 3: HD Voices}.
    */
-  voiceConfig?: string;
+  voiceName?: string;
 }
 
 /**