@mastra/voice-google 0.12.0-beta.0 → 0.12.0-beta.2

package/dist/docs/voice/02-reference.md

@@ -0,0 +1,184 @@
+# Voice API Reference
+
+> API reference for voice - 1 entries
+
+
+---
+
+## Reference: Google
+
+> Documentation for the Google Voice implementation, providing text-to-speech and speech-to-text capabilities with support for both API key and Vertex AI authentication.
+
+The Google Voice implementation in Mastra provides both text-to-speech (TTS) and speech-to-text (STT) capabilities using Google Cloud services. It supports multiple voices, languages, advanced audio configuration options, and both standard API key authentication and Vertex AI mode for enterprise deployments.
+
+## Usage Example
+
+```typescript
+import { GoogleVoice } from "@mastra/voice-google";
+
+// Initialize with default configuration (uses GOOGLE_API_KEY environment variable)
+const voice = new GoogleVoice();
+
+// Text-to-Speech
+const audioStream = await voice.speak("Hello, world!", {
+  languageCode: "en-US",
+  audioConfig: {
+    audioEncoding: "LINEAR16",
+  },
+});
+
+// Speech-to-Text
+const transcript = await voice.listen(audioStream, {
+  config: {
+    encoding: "LINEAR16",
+    languageCode: "en-US",
+  },
+});
+
+// Get available voices for a specific language
+const voices = await voice.getSpeakers({ languageCode: "en-US" });
+```
+
+## Constructor Parameters
+
+### GoogleModelConfig
+
+## Methods
+
+### speak()
+
+Converts text to speech using Google Cloud Text-to-Speech service.
+
+Returns: `Promise<NodeJS.ReadableStream>`
+
+### listen()
+
+Converts speech to text using Google Cloud Speech-to-Text service.
+
+Returns: `Promise<string>`
+
+### getSpeakers()
+
+Returns an array of available voice options, where each node contains:
+
+### isUsingVertexAI()
+
+Checks if Vertex AI mode is enabled.
+
+Returns: `boolean` - `true` if using Vertex AI, `false` otherwise
+
+### getProject()
+
+Gets the configured Google Cloud project ID.
+
+Returns: `string | undefined` - The project ID or `undefined` if not set
+
+### getLocation()
+
+Gets the configured Google Cloud location/region.
+
+Returns: `string` - The location (default: `'us-central1'`)
+
+## Authentication
+
+The Google Voice provider supports two authentication methods:
+
+### Standard Mode (API Key)
+
+Uses a Google Cloud API key for authentication. Suitable for development and simple use cases.
+
+```typescript
+// Using environment variable (GOOGLE_API_KEY)
+const voice = new GoogleVoice();
+
+// Using explicit API key
+const voice = new GoogleVoice({
+  speechModel: { apiKey: "your-api-key" },
+  listeningModel: { apiKey: "your-api-key" },
+  speaker: "en-US-Casual-K",
+});
+```
+
+### Vertex AI Mode (Service Account)
+
+Uses Google Cloud project-based authentication with service accounts. Recommended for production and enterprise deployments.
+
+**Benefits:**
+- Better security (no API keys in code)
+- IAM-based access control
+- Project-level billing and quotas
+- Audit logging
+- Enterprise features
+
+**Configuration Options:**
+
+```typescript
+// Using Application Default Credentials (ADC)
+// Set GOOGLE_APPLICATION_CREDENTIALS and GOOGLE_CLOUD_PROJECT env vars
+const voice = new GoogleVoice({
+  vertexAI: true,
+  project: "your-gcp-project",
+  location: "us-central1", // Optional, defaults to 'us-central1'
+});
+
+// Using service account key file
+const voice = new GoogleVoice({
+  vertexAI: true,
+  project: "your-gcp-project",
+  speechModel: {
+    keyFilename: "/path/to/service-account.json",
+  },
+  listeningModel: {
+    keyFilename: "/path/to/service-account.json",
+  },
+});
+
+// Using in-memory credentials
+const voice = new GoogleVoice({
+  vertexAI: true,
+  project: "your-gcp-project",
+  speechModel: {
+    credentials: {
+      client_email: "service-account@project.iam.gserviceaccount.com",
+      private_key: "-----BEGIN PRIVATE KEY-----\n...\n-----END PRIVATE KEY-----",
+    },
+  },
+});
+```
+
+**Required Permissions:**
+
+**IAM Roles:**
+
+For Text-to-Speech:
+- `roles/texttospeech.admin` - Text-to-Speech Admin (full access)
+- `roles/texttospeech.editor` - Text-to-Speech Editor (create and manage)
+- `roles/texttospeech.viewer` - Text-to-Speech Viewer (read-only)
+
+For Speech-to-Text:
+- `roles/speech.client` - Speech-to-Text Client
+
+**OAuth Scopes:**
+
+For synchronous Text-to-Speech synthesis:
+- `https://www.googleapis.com/auth/cloud-platform` - Full access to Google Cloud Platform services
+
+For long-audio Text-to-Speech operations:
+- `locations.longAudioSynthesize` - Create long-audio synthesis operations
+- `operations.get` - Get operation status
+- `operations.list` - List operations
+
+## Important Notes
+
+1. **Authentication**: Either a Google Cloud API key (standard mode) or service account credentials (Vertex AI mode) is required.
+2. **Environment Variables**:
+   - `GOOGLE_API_KEY` - API key for standard mode
+   - `GOOGLE_CLOUD_PROJECT` - Project ID for Vertex AI mode
+   - `GOOGLE_CLOUD_LOCATION` - Location for Vertex AI mode (defaults to 'us-central1')
+   - `GOOGLE_APPLICATION_CREDENTIALS` - Path to service account key file
+3. The default voice is set to `'en-US-Casual-K'`.
+4. Both text-to-speech and speech-to-text services use LINEAR16 as the default audio encoding.
+5. The `speak()` method supports advanced audio configuration through the Google Cloud Text-to-Speech API.
+6. The `listen()` method supports various recognition configurations through the Google Cloud Speech-to-Text API.
+7. Available voices can be filtered by language code using the `getSpeakers()` method.
+8. Vertex AI mode provides enterprise features including IAM control, audit logs, and project-level billing.

package/dist/index.cjs

@@ -6,10 +6,16 @@ var textToSpeech = require('@google-cloud/text-to-speech');
 var voice = require('@mastra/core/voice');
 
 // src/index.ts
-var resolveAuthConfig = (modelConfig, fallback) => {
+var resolveAuthConfig = (modelConfig, fallback, vertexConfig) => {
   const resolved = {};
+  if (vertexConfig?.vertexAI) {
+    const projectId = vertexConfig.project || process.env.GOOGLE_CLOUD_PROJECT;
+    if (projectId) {
+      resolved.projectId = projectId;
+    }
+  }
   const apiKey = modelConfig?.apiKey ?? fallback.apiKey;
-  if (apiKey) {
+  if (apiKey && !vertexConfig?.vertexAI) {
     resolved.apiKey = apiKey;
   }
   const keyFilename = modelConfig?.keyFilename ?? fallback.keyFilename;
@@ -22,44 +28,57 @@ var resolveAuthConfig = (modelConfig, fallback) => {
   }
   return resolved;
 };
-var buildAuthOptions = (config) => {
+var buildAuthOptions = (config, vertexConfig) => {
+  const options = {};
   if (config.credentials) {
-    return { credentials: config.credentials };
+    options.credentials = config.credentials;
   }
   if (config.keyFilename) {
-    return { keyFilename: config.keyFilename };
+    options.keyFilename = config.keyFilename;
   }
-  if (config.apiKey) {
-    return { apiKey: config.apiKey };
+  if (config.apiKey && !vertexConfig?.vertexAI) {
+    options.apiKey = config.apiKey;
   }
-  return {};
+  if (config.projectId) {
+    options.projectId = config.projectId;
+  }
+  return options;
 };
 var DEFAULT_VOICE = "en-US-Casual-K";
 var GoogleVoice = class extends voice.MastraVoice {
   ttsClient;
   speechClient;
+  vertexAI;
+  project;
+  location;
   /**
    * Creates an instance of GoogleVoice
-   * @param {Object} config - Configuration options
+   * @param {GoogleVoiceConfig} config - Configuration options
    * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
    * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
    * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
+   * @param {boolean} [config.vertexAI] - Enable Vertex AI mode
+   * @param {string} [config.project] - Google Cloud project ID (required for Vertex AI)
+   * @param {string} [config.location] - Google Cloud region (default: 'us-central1')
    */
-  constructor({
-    listeningModel,
-    speechModel,
-    speaker
-  } = {}) {
+  constructor({ listeningModel, speechModel, speaker, vertexAI = false, project, location } = {}) {
     const defaultApiKey = process.env.GOOGLE_API_KEY;
     const defaultKeyFilename = process.env.GOOGLE_APPLICATION_CREDENTIALS;
     const defaultSpeaker = DEFAULT_VOICE;
+    const resolvedProject = project || process.env.GOOGLE_CLOUD_PROJECT;
+    const resolvedLocation = location || process.env.GOOGLE_CLOUD_LOCATION || "us-central1";
+    if (vertexAI && !resolvedProject) {
+      throw new Error(
+        "Google Cloud project ID is required when using Vertex AI. Set GOOGLE_CLOUD_PROJECT environment variable or pass project to constructor."
+      );
+    }
+    const vertexConfig = { vertexAI, project: resolvedProject };
     const sharedFallback = {
       apiKey: defaultApiKey ?? speechModel?.apiKey ?? listeningModel?.apiKey,
       keyFilename: defaultKeyFilename ?? speechModel?.keyFilename ?? listeningModel?.keyFilename,
-      credentials: speechModel?.credentials ?? listeningModel?.credentials
-    };
-    const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback);
-    const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback);
+      credentials: speechModel?.credentials ?? listeningModel?.credentials};
+    const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback, vertexConfig);
+    const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback, vertexConfig);
     super({
       speechModel: {
         name: "",
@@ -71,11 +90,35 @@ var GoogleVoice = class extends voice.MastraVoice {
       },
       speaker: speaker ?? defaultSpeaker
     });
-    const ttsOptions = buildAuthOptions(speechAuthConfig);
-    const speechOptions = buildAuthOptions(listeningAuthConfig);
+    this.vertexAI = vertexAI;
+    this.project = resolvedProject;
+    this.location = resolvedLocation;
+    const ttsOptions = buildAuthOptions(speechAuthConfig, { vertexAI});
+    const speechOptions = buildAuthOptions(listeningAuthConfig, { vertexAI});
     this.ttsClient = new textToSpeech.TextToSpeechClient(ttsOptions);
     this.speechClient = new speech.SpeechClient(speechOptions);
   }
+  /**
+   * Check if Vertex AI mode is enabled
+   * @returns {boolean} True if using Vertex AI
+   */
+  isUsingVertexAI() {
+    return this.vertexAI;
+  }
+  /**
+   * Get the configured Google Cloud project ID
+   * @returns {string | undefined} The project ID or undefined if not set
+   */
+  getProject() {
+    return this.project;
+  }
+  /**
+   * Get the configured Google Cloud location/region
+   * @returns {string} The location (default: 'us-central1')
+   */
+  getLocation() {
+    return this.location;
+  }
   /**
    * Gets a list of available voices
    * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.

package/dist/index.cjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"names":["MastraVoice","TextToSpeechClient","SpeechClient","stream","PassThrough"],"mappings":";;;;;;;;AA6BA,IAAM,iBAAA,GAAoB,CAAC,WAAA,EAA4C,QAAA,KAAqC;AAC1G,EAAA,MAAM,WAAuB,EAAC;AAE9B,EAAA,MAAM,MAAA,GAAS,WAAA,EAAa,MAAA,IAAU,QAAA,CAAS,MAAA;AAC/C,EAAA,IAAI,MAAA,EAAQ;AACV,IAAA,QAAA,CAAS,MAAA,GAAS,MAAA;AAAA,EACpB;AAEA,EAAA,MAAM,WAAA,GAAc,WAAA,EAAa,WAAA,IAAe,QAAA,CAAS,WAAA;AACzD,EAAA,IAAI,WAAA,EAAa;AACf,IAAA,QAAA,CAAS,WAAA,GAAc,WAAA;AAAA,EACzB;AAEA,EAAA,MAAM,WAAA,GAAc,WAAA,EAAa,WAAA,IAAe,QAAA,CAAS,WAAA;AACzD,EAAA,IAAI,WAAA,EAAa;AACf,IAAA,QAAA,CAAS,WAAA,GAAc,WAAA;AAAA,EACzB;AAEA,EAAA,OAAO,QAAA;AACT,CAAA;AAEA,IAAM,gBAAA,GAAmB,CAAC,MAAA,KAA4C;AACpE,EAAA,IAAI,OAAO,WAAA,EAAa;AACtB,IAAA,OAAO,EAAE,WAAA,EAAa,MAAA,CAAO,WAAA,EAAY;AAAA,EAC3C;AAEA,EAAA,IAAI,OAAO,WAAA,EAAa;AACtB,IAAA,OAAO,EAAE,WAAA,EAAa,MAAA,CAAO,WAAA,EAAY;AAAA,EAC3C;AAEA,EAAA,IAAI,OAAO,MAAA,EAAQ;AACjB,IAAA,OAAO,EAAE,MAAA,EAAQ,MAAA,CAAO,MAAA,EAAO;AAAA,EACjC;AAEA,EAAA,OAAO,EAAC;AACV,CAAA;AAEA,IAAM,aAAA,GAAgB,gBAAA;AAOf,IAAM,WAAA,GAAN,cAA0BA,iBAAA,CAAY;AAAA,EACnC,SAAA;AAAA,EACA,YAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASR,WAAA,CAAY;AAAA,IACV,cAAA;AAAA,IACA,WAAA;AAAA,IACA;AAAA,GACF,GAII,EAAC,EAAG;AACN,IAAA,MAAM,aAAA,GAAgB,QAAQ,GAAA,CAAI,cAAA;AAClC,IAAA,MAAM,kBAAA,GAAqB,QAAQ,GAAA,CAAI,8BAAA;AACvC,IAAA,MAAM,cAAA,GAAiB,aAAA;AAEvB,IAAA,MAAM,cAAA,GAA6B;AAAA,MACjC,MAAA,EAAQ,aAAA,IAAiB,WAAA,EAAa,MAAA,IAAU,cAAA,EAAgB,MAAA;AAAA,MAChE,WAAA,EAAa,kBAAA,IAAsB,WAAA,EAAa,WAAA,IAAe,cAAA,EAAgB,WAAA;AAAA,MAC/E,WAAA,EAAa,WAAA,EAAa,WAAA,IAAe,cAAA,EAAgB;AAAA,KAC3D;AAEA,IAAA,MAAM,gBAAA,GAAmB,iBAAA,CAAkB,WAAA,EAAa,cAAc,CAAA;AACtE,IAAA,MAAM,mBAAA,GAAsB,iBAAA,CAAkB,cAAA,EAAgB,cAAc,CAAA;AAE5E,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,iBAAiB,MAAA,IAAU;AAAA,OACrC;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,oBAAoB,MAAA,IAAU;AAAA,OACxC;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,UAAA,GAAa,iBAAiB,gBAAgB,CAAA;AACpD,IAAA,MAAM,aAAA,GAAgB,iBAAiB,mBAAmB,CAAA;AAE1D,IAAA,IAAA,CAAK,SAAA,GAAY,IAAIC,+BAAA,CAAmB,UAAU,CAAA;AAElD,IAAA,IAAA,CAAK,YAAA,GAAe,IAAIC,mBAAA,CAAa,aAAa,CAAA;AAAA,EACpD;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAM,WAAA,CAAY,EAAE,eAAe,OAAA,EAAQ,GAA+B,EAAC,EAAG;AAC5E,IAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,KAAK,SAAA,CAAU,UAAA,CAAW,EAAE,YAAA,EAA4B,CAAA;AACjF,IAAA,OAAA,CAAQ,QAAA,EAAU,MAAA,IAAU,EAAC,EAC1B,MAAA,CAAO,CAAA,KAAA,KAAS,KAAA,CAAM,IAAA,IAAQ,KAAA,CAAM,aAAa,CAAA,CACjD,GAAA,CAAI,CAAA,KAAA,MAAU;AAAA,MACb,SAAS,KAAA,CAAM,IAAA;AAAA,MACf,eAAe,KAAA,CAAM;AAAA,KACvB,CAAE,CAAA;AAAA,EACN;AAAA,EAEA,MAAc,eAAe,MAAA,EAAgD;AAC3E,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,MAAA,EAAQ;AAChC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,OAAO,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA,CAAE,SAAS,OAAO,CAAA;AAAA,EAC/C;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAWA,MAAM,KAAA,CACJ,KAAA,EACA,OAAA,EAKgC;AAChC,IAAA,MAAM,IAAA,GAAO,OAAO,KAAA,KAAU,QAAA,GAAW,QAAQ,MAAM,IAAA,CAAK,eAAe,KAAK,CAAA;AAEhF,IAAA,MAAM,OAAA,GAA4E;AAAA,MAChF,KAAA,EAAO,EAAE,IAAA,EAAK;AAAA,MACd,KAAA,EAAO;AAAA,QACL,IAAA,EAAM,OAAA,EAAS,OAAA,IAAW,IAAA,CAAK,OAAA;AAAA,QAC/B,YAAA,EAAc,OAAA,EAAS,YAAA,IAAgB,OAAA,EAAS,SAAS,KAAA,CAAM,GAAG,CAAA,CAAE,KAAA,CAAM,CAAA,EAAG,CAAC,CAAA,CAAE,IAAA,CAAK,GAAG,CAAA,IAAK;AAAA,OAC/F;AAAA,MACA,WAAA,EAAa,OAAA,EAAS,WAAA,IAAe,EAAE,eAAe,UAAA;AAAW,KACnE;AAEA,IAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,SAAA,CAAU,iBAAiB,OAAO,CAAA;AAEhE,IAAA,IAAI,CAAC,SAAS,YAAA,EAAc;AAC1B,MAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,IAC9C;AAEA,IAAA,IAAI,OAAO,QAAA,CAAS,YAAA,KAAiB,QAAA,EAAU;AAC7C,MAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,IAC9C;AAEA,IAAA,MAAMC,QAAA,GAAS,IAAIC,kBAAA,EAAY;AAC/B,IAAAD,QAAA,CAAO,GAAA,CAAI,MAAA,CAAO,IAAA,CAAK,QAAA,CAAS,YAAY,CAAC,CAAA;AAC7C,IAAA,OAAOA,QAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,WAAA,GAAc;AAClB,IAAA,OAAO,EAAE,SAAS,IAAA,EAAK;AAAA,EACzB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,MAAA,CACJ,WAAA,EACA,OAAA,EACiB;AACjB,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,MAAM,MAAA,GAAS,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAEnC,IAAA,IAAI,OAAA,GAAU;AAAA,MACZ,MAAA,EAAQ;AAAA,QACN,QAAA,EAAU,UAAA;AAAA,QACV,YAAA,EAAc,OAAA;AAAA,QACd,GAAG,OAAA,EAAS;AAAA,OACd;AAAA,MACA,KAAA,EAAO;AAAA,QACL,OAAA,EAAS,MAAA,CAAO,QAAA,CAAS,QAAQ;AAAA;AACnC,KACF;AACA,IAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,YAAA,CAAa,UAAU,OAAwD,CAAA;AAE7G,IAAA,IAAI,CAAC,QAAA,CAAS,OAAA,IAAW,QAAA,CAAS,OAAA,CAAQ,WAAW,CAAA,EAAG;AACtD,MAAA,MAAM,IAAI,MAAM,mCAAmC,CAAA;AAAA,IACrD;AAEA,IAAA,MAAM,aAAA,GAAgB,QAAA,CAAS,OAAA,CAC5B,GAAA,CAAI,CAAC,MAAA,KAAgB;AACpB,MAAA,IAAI,CAAC,MAAA,CAAO,YAAA,IAAgB,MAAA,CAAO,YAAA,CAAa,WAAW,CAAA,EAAG;AAC5D,QAAA,OAAO,EAAA;AAAA,MACT;AACA,MAAA,OAAO,MAAA,CAAO,YAAA,CAAa,CAAC,CAAA,CAAE,UAAA,IAAc,EAAA;AAAA,IAC9C,CAAC,CAAA,CACA,MAAA,CAAO,CAAC,IAAA,KAAiB,KAAK,MAAA,GAAS,CAAC,CAAA,CACxC,IAAA,CAAK,GAAG,CAAA;AAEX,IAAA,IAAI,CAAC,aAAA,EAAe;AAClB,MAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,IAC3D;AAEA,IAAA,OAAO,aAAA;AAAA,EACT;AACF","file":"index.cjs","sourcesContent":["import { PassThrough } from 'stream';\n\nimport { SpeechClient } from '@google-cloud/speech';\nimport type { google as SpeechTypes } from '@google-cloud/speech/build/protos/protos';\nimport { TextToSpeechClient } from '@google-cloud/text-to-speech';\nimport type { google as TextToSpeechTypes } from '@google-cloud/text-to-speech/build/protos/protos';\nimport { MastraVoice } from '@mastra/core/voice';\n\n/**\n * Configuration for Google Cloud Voice models\n * @interface GoogleModelConfig\n * @property {string} [apiKey] - Optional Google Cloud API key. If not provided, will use GOOGLE_API_KEY environment variable\n * @property {string} [keyFilename] - Optional path to a service account key file. If not provided, will use GOOGLE_APPLICATION_CREDENTIALS environment variable\n * @property {{ client_email?: string; private_key?: string }} [credentials] - Optional in-memory service account credentials\n */\nexport interface GoogleModelConfig {\n  apiKey?: string;\n  keyFilename?: string;\n  credentials?: {\n    client_email?: string;\n    private_key?: string;\n    [key: string]: unknown;\n  };\n}\n\ntype AuthConfig = Pick<GoogleModelConfig, 'apiKey' | 'keyFilename' | 'credentials'>;\n\ntype GoogleClientOptions = AuthConfig;\n\nconst resolveAuthConfig = (modelConfig: GoogleModelConfig | undefined, fallback: AuthConfig): AuthConfig => {\n  const resolved: AuthConfig = {};\n\n  const apiKey = modelConfig?.apiKey ?? fallback.apiKey;\n  if (apiKey) {\n    resolved.apiKey = apiKey;\n  }\n\n  const keyFilename = modelConfig?.keyFilename ?? fallback.keyFilename;\n  if (keyFilename) {\n    resolved.keyFilename = keyFilename;\n  }\n\n  const credentials = modelConfig?.credentials ?? fallback.credentials;\n  if (credentials) {\n    resolved.credentials = credentials;\n  }\n\n  return resolved;\n};\n\nconst buildAuthOptions = (config: AuthConfig): GoogleClientOptions => {\n  if (config.credentials) {\n    return { credentials: config.credentials };\n  }\n\n  if (config.keyFilename) {\n    return { keyFilename: config.keyFilename };\n  }\n\n  if (config.apiKey) {\n    return { apiKey: config.apiKey };\n  }\n\n  return {};\n};\n\nconst DEFAULT_VOICE = 'en-US-Casual-K';\n\n/**\n * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services\n * @class GoogleVoice\n * @extends MastraVoice\n */\nexport class GoogleVoice extends MastraVoice {\n  private ttsClient: TextToSpeechClient;\n  private speechClient: SpeechClient;\n\n  /**\n   * Creates an instance of GoogleVoice\n   * @param {Object} config - Configuration options\n   * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis\n   * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition\n   * @param {string} [config.speaker] - Default voice ID to use for speech synthesis\n   */\n  constructor({\n    listeningModel,\n    speechModel,\n    speaker,\n  }: {\n    listeningModel?: GoogleModelConfig;\n    speechModel?: GoogleModelConfig;\n    speaker?: string;\n  } = {}) {\n    const defaultApiKey = process.env.GOOGLE_API_KEY;\n    const defaultKeyFilename = process.env.GOOGLE_APPLICATION_CREDENTIALS;\n    const defaultSpeaker = DEFAULT_VOICE;\n\n    const sharedFallback: AuthConfig = {\n      apiKey: defaultApiKey ?? speechModel?.apiKey ?? listeningModel?.apiKey,\n      keyFilename: defaultKeyFilename ?? speechModel?.keyFilename ?? listeningModel?.keyFilename,\n      credentials: speechModel?.credentials ?? listeningModel?.credentials,\n    };\n\n    const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback);\n    const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback);\n\n    super({\n      speechModel: {\n        name: '',\n        apiKey: speechAuthConfig.apiKey ?? defaultApiKey,\n      },\n      listeningModel: {\n        name: '',\n        apiKey: listeningAuthConfig.apiKey ?? defaultApiKey,\n      },\n      speaker: speaker ?? defaultSpeaker,\n    });\n\n    const ttsOptions = buildAuthOptions(speechAuthConfig);\n    const speechOptions = buildAuthOptions(listeningAuthConfig);\n\n    this.ttsClient = new TextToSpeechClient(ttsOptions);\n\n    this.speechClient = new SpeechClient(speechOptions);\n  }\n\n  /**\n   * Gets a list of available voices\n   * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.\n   */\n  async getSpeakers({ languageCode = 'en-US' }: { languageCode?: string } = {}) {\n    const [response] = await this.ttsClient.listVoices({ languageCode: languageCode });\n    return (response?.voices || [])\n      .filter(voice => voice.name && voice.languageCodes)\n      .map(voice => ({\n        voiceId: voice.name!,\n        languageCodes: voice.languageCodes!,\n      }));\n  }\n\n  private async streamToString(stream: NodeJS.ReadableStream): Promise<string> {\n    const chunks: Buffer[] = [];\n    for await (const chunk of stream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    return Buffer.concat(chunks).toString('utf-8');\n  }\n\n  /**\n   * Converts text to speech\n   * @param {string | NodeJS.ReadableStream} input - Text or stream to convert to speech\n   * @param {Object} [options] - Speech synthesis options\n   * @param {string} [options.speaker] - Voice ID to use\n   * @param {string} [options.languageCode] - Language code for the voice\n   * @param {TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig']} [options.audioConfig] - Audio configuration options\n   * @returns {Promise<NodeJS.ReadableStream>} Stream of synthesized audio. Default encoding is LINEAR16.\n   */\n  async speak(\n    input: string | NodeJS.ReadableStream,\n    options?: {\n      speaker?: string;\n      languageCode?: string;\n      audioConfig?: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig'];\n    },\n  ): Promise<NodeJS.ReadableStream> {\n    const text = typeof input === 'string' ? input : await this.streamToString(input);\n\n    const request: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest = {\n      input: { text },\n      voice: {\n        name: options?.speaker || this.speaker,\n        languageCode: options?.languageCode || options?.speaker?.split('-').slice(0, 2).join('-') || 'en-US',\n      },\n      audioConfig: options?.audioConfig || { audioEncoding: 'LINEAR16' },\n    };\n\n    const [response] = await this.ttsClient.synthesizeSpeech(request);\n\n    if (!response.audioContent) {\n      throw new Error('No audio content returned.');\n    }\n\n    if (typeof response.audioContent === 'string') {\n      throw new Error('Audio content is a string.');\n    }\n\n    const stream = new PassThrough();\n    stream.end(Buffer.from(response.audioContent));\n    return stream;\n  }\n\n  /**\n   * Checks if listening capabilities are enabled.\n   *\n   * @returns {Promise<{ enabled: boolean }>}\n   */\n  async getListener() {\n    return { enabled: true };\n  }\n\n  /**\n   * Converts speech to text\n   * @param {NodeJS.ReadableStream} audioStream - Audio stream to transcribe. Default encoding is LINEAR16.\n   * @param {Object} [options] - Recognition options\n   * @param {SpeechTypes.cloud.speech.v1.IRecognitionConfig} [options.config] - Recognition configuration\n   * @returns {Promise<string>} Transcribed text\n   */\n  async listen(\n    audioStream: NodeJS.ReadableStream,\n    options?: { stream?: boolean; config?: SpeechTypes.cloud.speech.v1.IRecognitionConfig },\n  ): Promise<string> {\n    const chunks: Buffer[] = [];\n    for await (const chunk of audioStream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    const buffer = Buffer.concat(chunks);\n\n    let request = {\n      config: {\n        encoding: 'LINEAR16',\n        languageCode: 'en-US',\n        ...options?.config,\n      },\n      audio: {\n        content: buffer.toString('base64'),\n      },\n    };\n    const [response] = await this.speechClient.recognize(request as SpeechTypes.cloud.speech.v1.IRecognizeRequest);\n\n    if (!response.results || response.results.length === 0) {\n      throw new Error('No transcription results returned');\n    }\n\n    const transcription = response.results\n      .map((result: any) => {\n        if (!result.alternatives || result.alternatives.length === 0) {\n          return '';\n        }\n        return result.alternatives[0].transcript || '';\n      })\n      .filter((text: string) => text.length > 0)\n      .join(' ');\n\n    if (!transcription) {\n      throw new Error('No valid transcription found in results');\n    }\n\n    return transcription;\n  }\n}\n"]}
+{"version":3,"sources":["../src/index.ts"],"names":["MastraVoice","TextToSpeechClient","SpeechClient","stream","PassThrough"],"mappings":";;;;;;;;AA6DA,IAAM,iBAAA,GAAoB,CACxB,WAAA,EACA,QAAA,EACA,YAAA,KACe;AACf,EAAA,MAAM,WAAuB,EAAC;AAG9B,EAAA,IAAI,cAAc,QAAA,EAAU;AAC1B,IAAA,MAAM,SAAA,GAAY,YAAA,CAAa,OAAA,IAAW,OAAA,CAAQ,GAAA,CAAI,oBAAA;AACtD,IAAA,IAAI,SAAA,EAAW;AACb,MAAA,QAAA,CAAS,SAAA,GAAY,SAAA;AAAA,IACvB;AAAA,EACF;AAEA,EAAA,MAAM,MAAA,GAAS,WAAA,EAAa,MAAA,IAAU,QAAA,CAAS,MAAA;AAE/C,EAAA,IAAI,MAAA,IAAU,CAAC,YAAA,EAAc,QAAA,EAAU;AACrC,IAAA,QAAA,CAAS,MAAA,GAAS,MAAA;AAAA,EACpB;AAEA,EAAA,MAAM,WAAA,GAAc,WAAA,EAAa,WAAA,IAAe,QAAA,CAAS,WAAA;AACzD,EAAA,IAAI,WAAA,EAAa;AACf,IAAA,QAAA,CAAS,WAAA,GAAc,WAAA;AAAA,EACzB;AAEA,EAAA,MAAM,WAAA,GAAc,WAAA,EAAa,WAAA,IAAe,QAAA,CAAS,WAAA;AACzD,EAAA,IAAI,WAAA,EAAa;AACf,IAAA,QAAA,CAAS,WAAA,GAAc,WAAA;AAAA,EACzB;AAEA,EAAA,OAAO,QAAA;AACT,CAAA;AAEA,IAAM,gBAAA,GAAmB,CACvB,MAAA,EACA,YAAA,KACwB;AACxB,EAAA,MAAM,UAA+B,EAAC;AAEtC,EAAA,IAAI,OAAO,WAAA,EAAa;AACtB,IAAA,OAAA,CAAQ,cAAc,MAAA,CAAO,WAAA;AAAA,EAC/B;AAEA,EAAA,IAAI,OAAO,WAAA,EAAa;AACtB,IAAA,OAAA,CAAQ,cAAc,MAAA,CAAO,WAAA;AAAA,EAC/B;AAGA,EAAA,IAAI,MAAA,CAAO,MAAA,IAAU,CAAC,YAAA,EAAc,QAAA,EAAU;AAC5C,IAAA,OAAA,CAAQ,SAAS,MAAA,CAAO,MAAA;AAAA,EAC1B;AAGA,EAAA,IAAI,OAAO,SAAA,EAAW;AACpB,IAAA,OAAA,CAAQ,YAAY,MAAA,CAAO,SAAA;AAAA,EAC7B;AAEA,EAAA,OAAO,OAAA;AACT,CAAA;AAEA,IAAM,aAAA,GAAgB,gBAAA;AAsCf,IAAM,WAAA,GAAN,cAA0BA,iBAAA,CAAY;AAAA,EACnC,SAAA;AAAA,EACA,YAAA;AAAA,EACS,QAAA;AAAA,EACA,OAAA;AAAA,EACA,QAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAYjB,WAAA,CAAY,EAAE,cAAA,EAAgB,WAAA,EAAa,OAAA,EAAS,QAAA,GAAW,KAAA,EAAO,OAAA,EAAS,QAAA,EAAS,GAAuB,EAAC,EAAG;AACjH,IAAA,MAAM,aAAA,GAAgB,QAAQ,GAAA,CAAI,cAAA;AAClC,IAAA,MAAM,kBAAA,GAAqB,QAAQ,GAAA,CAAI,8BAAA;AACvC,IAAA,MAAM,cAAA,GAAiB,aAAA;AAGvB,IAAA,MAAM,eAAA,GAAkB,OAAA,IAAW,OAAA,CAAQ,GAAA,CAAI,oBAAA;AAC/C,IAAA,MAAM,gBAAA,GAAmB,QAAA,IAAY,OAAA,CAAQ,GAAA,CAAI,qBAAA,IAAyB,aAAA;AAG1E,IAAA,IAAI,QAAA,IAAY,CAAC,eAAA,EAAiB;AAChC,MAAA,MAAM,IAAI,KAAA;AAAA,QACR;AAAA,OAEF;AAAA,IACF;AAEA,IAAA,MAAM,YAAA,GAAe,EAAE,QAAA,EAAU,OAAA,EAAS,eAAA,EAAgB;AAE1D,IAAA,MAAM,cAAA,GAA6B;AAAA,MACjC,MAAA,EAAQ,aAAA,IAAiB,WAAA,EAAa,MAAA,IAAU,cAAA,EAAgB,MAAA;AAAA,MAChE,WAAA,EAAa,kBAAA,IAAsB,WAAA,EAAa,WAAA,IAAe,cAAA,EAAgB,WAAA;AAAA,MAC/E,WAAA,EAAa,WAAA,EAAa,WAAA,IAAe,cAAA,EAAgB,WAE3D,CAAA;AAEA,IAAA,MAAM,gBAAA,GAAmB,iBAAA,CAAkB,WAAA,EAAa,cAAA,EAAgB,YAAY,CAAA;AACpF,IAAA,MAAM,mBAAA,GAAsB,iBAAA,CAAkB,cAAA,EAAgB,cAAA,EAAgB,YAAY,CAAA;AAE1F,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,iBAAiB,MAAA,IAAU;AAAA,OACrC;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,oBAAoB,MAAA,IAAU;AAAA,OACxC;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,IAAA,CAAK,QAAA,GAAW,QAAA;AAChB,IAAA,IAAA,CAAK,OAAA,GAAU,eAAA;AACf,IAAA,IAAA,CAAK,QAAA,GAAW,gBAAA;AAEhB,IAAA,MAAM,aAAa,gBAAA,CAAiB,gBAAA,EAAkB,EAAE,QAAqC,CAAC,CAAA;AAC9F,IAAA,MAAM,gBAAgB,gBAAA,CAAiB,mBAAA,EAAqB,EAAE,QAAqC,CAAC,CAAA;AAEpG,IAAA,IAAA,CAAK,SAAA,GAAY,IAAIC,+BAAA,CAAmB,UAAU,CAAA;AAClD,IAAA,IAAA,CAAK,YAAA,GAAe,IAAIC,mBAAA,CAAa,aAAa,CAAA;AAAA,EACpD;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,eAAA,GAA2B;AACzB,IAAA,OAAO,IAAA,CAAK,QAAA;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,UAAA,GAAiC;AAC/B,IAAA,OAAO,IAAA,CAAK,OAAA;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,WAAA,GAAsB;AACpB,IAAA,OAAO,IAAA,CAAK,QAAA;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAM,WAAA,CAAY,EAAE,eAAe,OAAA,EAAQ,GAA+B,EAAC,EAAG;AAC5E,IAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,KAAK,SAAA,CAAU,UAAA,CAAW,EAAE,YAAA,EAA4B,CAAA;AACjF,IAAA,OAAA,CAAQ,QAAA,EAAU,MAAA,IAAU,EAAC,EAC1B,MAAA,CAAO,CAAA,KAAA,KAAS,KAAA,CAAM,IAAA,IAAQ,KAAA,CAAM,aAAa,CAAA,CACjD,GAAA,CAAI,CAAA,KAAA,MAAU;AAAA,MACb,SAAS,KAAA,CAAM,IAAA;AAAA,MACf,eAAe,KAAA,CAAM;AAAA,KACvB,CAAE,CAAA;AAAA,EACN;AAAA,EAEA,MAAc,eAAe,MAAA,EAAgD;AAC3E,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,MAAA,EAAQ;AAChC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,OAAO,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA,CAAE,SAAS,OAAO,CAAA;AAAA,EAC/C;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAWA,MAAM,KAAA,CACJ,KAAA,EACA,OAAA,EAKgC;AAChC,IAAA,MAAM,IAAA,GAAO,OAAO,KAAA,KAAU,QAAA,GAAW,QAAQ,MAAM,IAAA,CAAK,eAAe,KAAK,CAAA;AAEhF,IAAA,MAAM,OAAA,GAA4E;AAAA,MAChF,KAAA,EAAO,EAAE,IAAA,EAAK;AAAA,MACd,KAAA,EAAO;AAAA,QACL,IAAA,EAAM,OAAA,EAAS,OAAA,IAAW,IAAA,CAAK,OAAA;AAAA,QAC/B,YAAA,EAAc,OAAA,EAAS,YAAA,IAAgB,OAAA,EAAS,SAAS,KAAA,CAAM,GAAG,CAAA,CAAE,KAAA,CAAM,CAAA,EAAG,CAAC,CAAA,CAAE,IAAA,CAAK,GAAG,CAAA,IAAK;AAAA,OAC/F;AAAA,MACA,WAAA,EAAa,OAAA,EAAS,WAAA,IAAe,EAAE,eAAe,UAAA;AAAW,KACnE;AAEA,IAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,SAAA,CAAU,iBAAiB,OAAO,CAAA;AAEhE,IAAA,IAAI,CAAC,SAAS,YAAA,EAAc;AAC1B,MAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,IAC9C;AAEA,IAAA,IAAI,OAAO,QAAA,CAAS,YAAA,KAAiB,QAAA,EAAU;AAC7C,MAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,IAC9C;AAEA,IAAA,MAAMC,QAAA,GAAS,IAAIC,kBAAA,EAAY;AAC/B,IAAAD,QAAA,CAAO,GAAA,CAAI,MAAA,CAAO,IAAA,CAAK,QAAA,CAAS,YAAY,CAAC,CAAA;AAC7C,IAAA,OAAOA,QAAA;AAAA,EACT;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAOA,MAAM,WAAA,GAAc;AAClB,IAAA,OAAO,EAAE,SAAS,IAAA,EAAK;AAAA,EACzB;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASA,MAAM,MAAA,CACJ,WAAA,EACA,OAAA,EACiB;AACjB,IAAA,MAAM,SAAmB,EAAC;AAC1B,IAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,MAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,QAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,MAChC,CAAA,MAAO;AACL,QAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,MACnB;AAAA,IACF;AACA,IAAA,MAAM,MAAA,GAAS,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAEnC,IAAA,IAAI,OAAA,GAAU;AAAA,MACZ,MAAA,EAAQ;AAAA,QACN,QAAA,EAAU,UAAA;AAAA,QACV,YAAA,EAAc,OAAA;AAAA,QACd,GAAG,OAAA,EAAS;AAAA,OACd;AAAA,MACA,KAAA,EAAO;AAAA,QACL,OAAA,EAAS,MAAA,CAAO,QAAA,CAAS,QAAQ;AAAA;AACnC,KACF;AACA,IAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,YAAA,CAAa,UAAU,OAAwD,CAAA;AAE7G,IAAA,IAAI,CAAC,QAAA,CAAS,OAAA,IAAW,QAAA,CAAS,OAAA,CAAQ,WAAW,CAAA,EAAG;AACtD,MAAA,MAAM,IAAI,MAAM,mCAAmC,CAAA;AAAA,IACrD;AAEA,IAAA,MAAM,aAAA,GAAgB,QAAA,CAAS,OAAA,CAC5B,GAAA,CAAI,CAAC,MAAA,KAAgB;AACpB,MAAA,IAAI,CAAC,MAAA,CAAO,YAAA,IAAgB,MAAA,CAAO,YAAA,CAAa,WAAW,CAAA,EAAG;AAC5D,QAAA,OAAO,EAAA;AAAA,MACT;AACA,MAAA,OAAO,MAAA,CAAO,YAAA,CAAa,CAAC,CAAA,CAAE,UAAA,IAAc,EAAA;AAAA,IAC9C,CAAC,CAAA,CACA,MAAA,CAAO,CAAC,IAAA,KAAiB,KAAK,MAAA,GAAS,CAAC,CAAA,CACxC,IAAA,CAAK,GAAG,CAAA;AAEX,IAAA,IAAI,CAAC,aAAA,EAAe;AAClB,MAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,IAC3D;AAEA,IAAA,OAAO,aAAA;AAAA,EACT;AACF","file":"index.cjs","sourcesContent":["import { PassThrough } from 'node:stream';\n\nimport { SpeechClient } from '@google-cloud/speech';\nimport type { google as SpeechTypes } from '@google-cloud/speech/build/protos/protos';\nimport { TextToSpeechClient } from '@google-cloud/text-to-speech';\nimport type { google as TextToSpeechTypes } from '@google-cloud/text-to-speech/build/protos/protos';\nimport { MastraVoice } from '@mastra/core/voice';\n\n/**\n * Configuration for Google Cloud Voice models\n * @interface GoogleModelConfig\n * @property {string} [apiKey] - Optional Google Cloud API key. If not provided, will use GOOGLE_API_KEY environment variable\n * @property {string} [keyFilename] - Optional path to a service account key file. If not provided, will use GOOGLE_APPLICATION_CREDENTIALS environment variable\n * @property {{ client_email?: string; private_key?: string }} [credentials] - Optional in-memory service account credentials\n */\nexport interface GoogleModelConfig {\n  apiKey?: string;\n  keyFilename?: string;\n  credentials?: {\n    client_email?: string;\n    private_key?: string;\n    [key: string]: unknown;\n  };\n}\n\n/**\n * Configuration options for GoogleVoice\n * @interface GoogleVoiceConfig\n */\nexport interface GoogleVoiceConfig {\n  /** Configuration for speech synthesis (TTS) */\n  speechModel?: GoogleModelConfig;\n  /** Configuration for speech recognition (STT) */\n  listeningModel?: GoogleModelConfig;\n  /** Default voice ID to use for speech synthesis */\n  speaker?: string;\n  /**\n   * Enable Vertex AI mode for enterprise deployments.\n   * When true, uses Google Cloud project-based authentication instead of API keys.\n   * Requires `project` to be set or GOOGLE_CLOUD_PROJECT environment variable.\n   */\n  vertexAI?: boolean;\n  /**\n   * Google Cloud project ID (required when vertexAI is true).\n   * Falls back to GOOGLE_CLOUD_PROJECT environment variable.\n   */\n  project?: string;\n  /**\n   * Google Cloud region for Vertex AI endpoints.\n   * Falls back to GOOGLE_CLOUD_LOCATION environment variable.\n   * @default 'us-central1'\n   */\n  location?: string;\n}\n\ntype AuthConfig = Pick<GoogleModelConfig, 'apiKey' | 'keyFilename' | 'credentials'> & {\n  projectId?: string;\n};\n\ntype GoogleClientOptions = AuthConfig;\n\nconst resolveAuthConfig = (\n  modelConfig: GoogleModelConfig | undefined,\n  fallback: AuthConfig,\n  vertexConfig?: { vertexAI?: boolean; project?: string },\n): AuthConfig => {\n  const resolved: AuthConfig = {};\n\n  // For Vertex AI, prioritize project-based auth over API keys\n  if (vertexConfig?.vertexAI) {\n    const projectId = vertexConfig.project || process.env.GOOGLE_CLOUD_PROJECT;\n    if (projectId) {\n      resolved.projectId = projectId;\n    }\n  }\n\n  const apiKey = modelConfig?.apiKey ?? fallback.apiKey;\n  // Only use API key if not in Vertex AI mode\n  if (apiKey && !vertexConfig?.vertexAI) {\n    resolved.apiKey = apiKey;\n  }\n\n  const keyFilename = modelConfig?.keyFilename ?? fallback.keyFilename;\n  if (keyFilename) {\n    resolved.keyFilename = keyFilename;\n  }\n\n  const credentials = modelConfig?.credentials ?? fallback.credentials;\n  if (credentials) {\n    resolved.credentials = credentials;\n  }\n\n  return resolved;\n};\n\nconst buildAuthOptions = (\n  config: AuthConfig,\n  vertexConfig?: { vertexAI?: boolean; location?: string },\n): GoogleClientOptions => {\n  const options: GoogleClientOptions = {};\n\n  if (config.credentials) {\n    options.credentials = config.credentials;\n  }\n\n  if (config.keyFilename) {\n    options.keyFilename = config.keyFilename;\n  }\n\n  // Only use API key if not using Vertex AI\n  if (config.apiKey && !vertexConfig?.vertexAI) {\n    options.apiKey = config.apiKey;\n  }\n\n  // For Vertex AI, set the project ID\n  if (config.projectId) {\n    options.projectId = config.projectId;\n  }\n\n  return options;\n};\n\nconst DEFAULT_VOICE = 'en-US-Casual-K';\n\n/**\n * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services.\n * Supports both standard Google Cloud API authentication and Vertex AI mode for enterprise deployments.\n *\n * @class GoogleVoice\n * @extends MastraVoice\n *\n * @example Standard usage with API key\n * ```typescript\n * const voice = new GoogleVoice({\n *   speechModel: { apiKey: 'your-api-key' },\n *   speaker: 'en-US-Studio-O',\n * });\n * ```\n *\n * @example Vertex AI mode (recommended for production)\n * ```typescript\n * const voice = new GoogleVoice({\n *   vertexAI: true,\n *   project: 'your-gcp-project',\n *   location: 'us-central1',\n *   speaker: 'en-US-Studio-O',\n * });\n * ```\n *\n * @example Vertex AI with service account\n * ```typescript\n * const voice = new GoogleVoice({\n *   vertexAI: true,\n *   project: 'your-gcp-project',\n *   speechModel: {\n *     keyFilename: '/path/to/service-account.json',\n *   },\n * });\n * ```\n */\nexport class GoogleVoice extends MastraVoice {\n  private ttsClient: TextToSpeechClient;\n  private speechClient: SpeechClient;\n  private readonly vertexAI: boolean;\n  private readonly project?: string;\n  private readonly location: string;\n\n  /**\n   * Creates an instance of GoogleVoice\n   * @param {GoogleVoiceConfig} config - Configuration options\n   * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis\n   * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition\n   * @param {string} [config.speaker] - Default voice ID to use for speech synthesis\n   * @param {boolean} [config.vertexAI] - Enable Vertex AI mode\n   * @param {string} [config.project] - Google Cloud project ID (required for Vertex AI)\n   * @param {string} [config.location] - Google Cloud region (default: 'us-central1')\n   */\n  constructor({ listeningModel, speechModel, speaker, vertexAI = false, project, location }: GoogleVoiceConfig = {}) {\n    const defaultApiKey = process.env.GOOGLE_API_KEY;\n    const defaultKeyFilename = process.env.GOOGLE_APPLICATION_CREDENTIALS;\n    const defaultSpeaker = DEFAULT_VOICE;\n\n    // Resolve Vertex AI configuration\n    const resolvedProject = project || process.env.GOOGLE_CLOUD_PROJECT;\n    const resolvedLocation = location || process.env.GOOGLE_CLOUD_LOCATION || 'us-central1';\n\n    // Validate Vertex AI configuration\n    if (vertexAI && !resolvedProject) {\n      throw new Error(\n        'Google Cloud project ID is required when using Vertex AI. ' +\n          'Set GOOGLE_CLOUD_PROJECT environment variable or pass project to constructor.',\n      );\n    }\n\n    const vertexConfig = { vertexAI, project: resolvedProject };\n\n    const sharedFallback: AuthConfig = {\n      apiKey: defaultApiKey ?? speechModel?.apiKey ?? listeningModel?.apiKey,\n      keyFilename: defaultKeyFilename ?? speechModel?.keyFilename ?? listeningModel?.keyFilename,\n      credentials: speechModel?.credentials ?? listeningModel?.credentials,\n      projectId: resolvedProject,\n    };\n\n    const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback, vertexConfig);\n    const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback, vertexConfig);\n\n    super({\n      speechModel: {\n        name: '',\n        apiKey: speechAuthConfig.apiKey ?? defaultApiKey,\n      },\n      listeningModel: {\n        name: '',\n        apiKey: listeningAuthConfig.apiKey ?? defaultApiKey,\n      },\n      speaker: speaker ?? defaultSpeaker,\n    });\n\n    this.vertexAI = vertexAI;\n    this.project = resolvedProject;\n    this.location = resolvedLocation;\n\n    const ttsOptions = buildAuthOptions(speechAuthConfig, { vertexAI, location: resolvedLocation });\n    const speechOptions = buildAuthOptions(listeningAuthConfig, { vertexAI, location: resolvedLocation });\n\n    this.ttsClient = new TextToSpeechClient(ttsOptions);\n    this.speechClient = new SpeechClient(speechOptions);\n  }\n\n  /**\n   * Check if Vertex AI mode is enabled\n   * @returns {boolean} True if using Vertex AI\n   */\n  isUsingVertexAI(): boolean {\n    return this.vertexAI;\n  }\n\n  /**\n   * Get the configured Google Cloud project ID\n   * @returns {string | undefined} The project ID or undefined if not set\n   */\n  getProject(): string | undefined {\n    return this.project;\n  }\n\n  /**\n   * Get the configured Google Cloud location/region\n   * @returns {string} The location (default: 'us-central1')\n   */\n  getLocation(): string {\n    return this.location;\n  }\n\n  /**\n   * Gets a list of available voices\n   * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.\n   */\n  async getSpeakers({ languageCode = 'en-US' }: { languageCode?: string } = {}) {\n    const [response] = await this.ttsClient.listVoices({ languageCode: languageCode });\n    return (response?.voices || [])\n      .filter(voice => voice.name && voice.languageCodes)\n      .map(voice => ({\n        voiceId: voice.name!,\n        languageCodes: voice.languageCodes!,\n      }));\n  }\n\n  private async streamToString(stream: NodeJS.ReadableStream): Promise<string> {\n    const chunks: Buffer[] = [];\n    for await (const chunk of stream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    return Buffer.concat(chunks).toString('utf-8');\n  }\n\n  /**\n   * Converts text to speech\n   * @param {string | NodeJS.ReadableStream} input - Text or stream to convert to speech\n   * @param {Object} [options] - Speech synthesis options\n   * @param {string} [options.speaker] - Voice ID to use\n   * @param {string} [options.languageCode] - Language code for the voice\n   * @param {TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig']} [options.audioConfig] - Audio configuration options\n   * @returns {Promise<NodeJS.ReadableStream>} Stream of synthesized audio. Default encoding is LINEAR16.\n   */\n  async speak(\n    input: string | NodeJS.ReadableStream,\n    options?: {\n      speaker?: string;\n      languageCode?: string;\n      audioConfig?: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig'];\n    },\n  ): Promise<NodeJS.ReadableStream> {\n    const text = typeof input === 'string' ? input : await this.streamToString(input);\n\n    const request: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest = {\n      input: { text },\n      voice: {\n        name: options?.speaker || this.speaker,\n        languageCode: options?.languageCode || options?.speaker?.split('-').slice(0, 2).join('-') || 'en-US',\n      },\n      audioConfig: options?.audioConfig || { audioEncoding: 'LINEAR16' },\n    };\n\n    const [response] = await this.ttsClient.synthesizeSpeech(request);\n\n    if (!response.audioContent) {\n      throw new Error('No audio content returned.');\n    }\n\n    if (typeof response.audioContent === 'string') {\n      throw new Error('Audio content is a string.');\n    }\n\n    const stream = new PassThrough();\n    stream.end(Buffer.from(response.audioContent));\n    return stream;\n  }\n\n  /**\n   * Checks if listening capabilities are enabled.\n   *\n   * @returns {Promise<{ enabled: boolean }>}\n   */\n  async getListener() {\n    return { enabled: true };\n  }\n\n  /**\n   * Converts speech to text\n   * @param {NodeJS.ReadableStream} audioStream - Audio stream to transcribe. Default encoding is LINEAR16.\n   * @param {Object} [options] - Recognition options\n   * @param {SpeechTypes.cloud.speech.v1.IRecognitionConfig} [options.config] - Recognition configuration\n   * @returns {Promise<string>} Transcribed text\n   */\n  async listen(\n    audioStream: NodeJS.ReadableStream,\n    options?: { stream?: boolean; config?: SpeechTypes.cloud.speech.v1.IRecognitionConfig },\n  ): Promise<string> {\n    const chunks: Buffer[] = [];\n    for await (const chunk of audioStream) {\n      if (typeof chunk === 'string') {\n        chunks.push(Buffer.from(chunk));\n      } else {\n        chunks.push(chunk);\n      }\n    }\n    const buffer = Buffer.concat(chunks);\n\n    let request = {\n      config: {\n        encoding: 'LINEAR16',\n        languageCode: 'en-US',\n        ...options?.config,\n      },\n      audio: {\n        content: buffer.toString('base64'),\n      },\n    };\n    const [response] = await this.speechClient.recognize(request as SpeechTypes.cloud.speech.v1.IRecognizeRequest);\n\n    if (!response.results || response.results.length === 0) {\n      throw new Error('No transcription results returned');\n    }\n\n    const transcription = response.results\n      .map((result: any) => {\n        if (!result.alternatives || result.alternatives.length === 0) {\n          return '';\n        }\n        return result.alternatives[0].transcript || '';\n      })\n      .filter((text: string) => text.length > 0)\n      .join(' ');\n\n    if (!transcription) {\n      throw new Error('No valid transcription found in results');\n    }\n\n    return transcription;\n  }\n}\n"]}

package/dist/index.d.ts

@@ -18,25 +18,102 @@ export interface GoogleModelConfig {
     };
 }
 /**
- * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services
+ * Configuration options for GoogleVoice
+ * @interface GoogleVoiceConfig
+ */
+export interface GoogleVoiceConfig {
+    /** Configuration for speech synthesis (TTS) */
+    speechModel?: GoogleModelConfig;
+    /** Configuration for speech recognition (STT) */
+    listeningModel?: GoogleModelConfig;
+    /** Default voice ID to use for speech synthesis */
+    speaker?: string;
+    /**
+     * Enable Vertex AI mode for enterprise deployments.
+     * When true, uses Google Cloud project-based authentication instead of API keys.
+     * Requires `project` to be set or GOOGLE_CLOUD_PROJECT environment variable.
+     */
+    vertexAI?: boolean;
+    /**
+     * Google Cloud project ID (required when vertexAI is true).
+     * Falls back to GOOGLE_CLOUD_PROJECT environment variable.
+     */
+    project?: string;
+    /**
+     * Google Cloud region for Vertex AI endpoints.
+     * Falls back to GOOGLE_CLOUD_LOCATION environment variable.
+     * @default 'us-central1'
+     */
+    location?: string;
+}
+/**
+ * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services.
+ * Supports both standard Google Cloud API authentication and Vertex AI mode for enterprise deployments.
+ *
  * @class GoogleVoice
  * @extends MastraVoice
+ *
+ * @example Standard usage with API key
+ * ```typescript
+ * const voice = new GoogleVoice({
+ *   speechModel: { apiKey: 'your-api-key' },
+ *   speaker: 'en-US-Studio-O',
+ * });
+ * ```
+ *
+ * @example Vertex AI mode (recommended for production)
+ * ```typescript
+ * const voice = new GoogleVoice({
+ *   vertexAI: true,
+ *   project: 'your-gcp-project',
+ *   location: 'us-central1',
+ *   speaker: 'en-US-Studio-O',
+ * });
+ * ```
+ *
+ * @example Vertex AI with service account
+ * ```typescript
+ * const voice = new GoogleVoice({
+ *   vertexAI: true,
+ *   project: 'your-gcp-project',
+ *   speechModel: {
+ *     keyFilename: '/path/to/service-account.json',
+ *   },
+ * });
+ * ```
  */
 export declare class GoogleVoice extends MastraVoice {
     private ttsClient;
     private speechClient;
+    private readonly vertexAI;
+    private readonly project?;
+    private readonly location;
     /**
      * Creates an instance of GoogleVoice
-     * @param {Object} config - Configuration options
+     * @param {GoogleVoiceConfig} config - Configuration options
      * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
      * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
      * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
+     * @param {boolean} [config.vertexAI] - Enable Vertex AI mode
+     * @param {string} [config.project] - Google Cloud project ID (required for Vertex AI)
+     * @param {string} [config.location] - Google Cloud region (default: 'us-central1')
      */
-    constructor({ listeningModel, speechModel, speaker, }?: {
-        listeningModel?: GoogleModelConfig;
-        speechModel?: GoogleModelConfig;
-        speaker?: string;
-    });
+    constructor({ listeningModel, speechModel, speaker, vertexAI, project, location }?: GoogleVoiceConfig);
+    /**
+     * Check if Vertex AI mode is enabled
+     * @returns {boolean} True if using Vertex AI
+     */
+    isUsingVertexAI(): boolean;
+    /**
+     * Get the configured Google Cloud project ID
+     * @returns {string | undefined} The project ID or undefined if not set
+     */
+    getProject(): string | undefined;
+    /**
+     * Get the configured Google Cloud location/region
+     * @returns {string} The location (default: 'us-central1')
+     */
+    getLocation(): string;
     /**
      * Gets a list of available voices
      * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.

package/dist/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,MAAM,IAAI,WAAW,EAAE,MAAM,0CAA0C,CAAC;AAEtF,OAAO,KAAK,EAAE,MAAM,IAAI,iBAAiB,EAAE,MAAM,kDAAkD,CAAC;AACpG,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAEjD;;;;;;GAMG;AACH,MAAM,WAAW,iBAAiB;IAChC,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,WAAW,CAAC,EAAE;QACZ,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC;KACxB,CAAC;CACH;AA6CD;;;;GAIG;AACH,qBAAa,WAAY,SAAQ,WAAW;IAC1C,OAAO,CAAC,SAAS,CAAqB;IACtC,OAAO,CAAC,YAAY,CAAe;IAEnC;;;;;;OAMG;gBACS,EACV,cAAc,EACd,WAAW,EACX,OAAO,GACR,GAAE;QACD,cAAc,CAAC,EAAE,iBAAiB,CAAC;QACnC,WAAW,CAAC,EAAE,iBAAiB,CAAC;QAChC,OAAO,CAAC,EAAE,MAAM,CAAC;KACb;IAkCN;;;OAGG;IACG,WAAW,CAAC,EAAE,YAAsB,EAAE,GAAE;QAAE,YAAY,CAAC,EAAE,MAAM,CAAA;KAAO;;;;YAU9D,cAAc;IAY5B;;;;;;;;OAQG;IACG,KAAK,CACT,KAAK,EAAE,MAAM,GAAG,MAAM,CAAC,cAAc,EACrC,OAAO,CAAC,EAAE;QACR,OAAO,CAAC,EAAE,MAAM,CAAC;QACjB,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,WAAW,CAAC,EAAE,iBAAiB,CAAC,KAAK,CAAC,YAAY,CAAC,EAAE,CAAC,wBAAwB,CAAC,aAAa,CAAC,CAAC;KAC/F,GACA,OAAO,CAAC,MAAM,CAAC,cAAc,CAAC;IA2BjC;;;;OAIG;IACG,WAAW;;;IAIjB;;;;;;OAMG;IACG,MAAM,CACV,WAAW,EAAE,MAAM,CAAC,cAAc,EAClC,OAAO,CAAC,EAAE;QAAE,MAAM,CAAC,EAAE,OAAO,CAAC;QAAC,MAAM,CAAC,EAAE,WAAW,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC,kBAAkB,CAAA;KAAE,GACtF,OAAO,CAAC,MAAM,CAAC;CA2CnB"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,MAAM,IAAI,WAAW,EAAE,MAAM,0CAA0C,CAAC;AAEtF,OAAO,KAAK,EAAE,MAAM,IAAI,iBAAiB,EAAE,MAAM,kDAAkD,CAAC;AACpG,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAEjD;;;;;;GAMG;AACH,MAAM,WAAW,iBAAiB;IAChC,MAAM,CAAC,EAAE,MAAM,CAAC;IAChB,WAAW,CAAC,EAAE,MAAM,CAAC;IACrB,WAAW,CAAC,EAAE;QACZ,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,WAAW,CAAC,EAAE,MAAM,CAAC;QACrB,CAAC,GAAG,EAAE,MAAM,GAAG,OAAO,CAAC;KACxB,CAAC;CACH;AAED;;;GAGG;AACH,MAAM,WAAW,iBAAiB;IAChC,+CAA+C;IAC/C,WAAW,CAAC,EAAE,iBAAiB,CAAC;IAChC,iDAAiD;IACjD,cAAc,CAAC,EAAE,iBAAiB,CAAC;IACnC,mDAAmD;IACnD,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB;;;;OAIG;IACH,QAAQ,CAAC,EAAE,OAAO,CAAC;IACnB;;;OAGG;IACH,OAAO,CAAC,EAAE,MAAM,CAAC;IACjB;;;;OAIG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;CACnB;AAuED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GAmCG;AACH,qBAAa,WAAY,SAAQ,WAAW;IAC1C,OAAO,CAAC,SAAS,CAAqB;IACtC,OAAO,CAAC,YAAY,CAAe;IACnC,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAU;IACnC,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAC,CAAS;IAClC,OAAO,CAAC,QAAQ,CAAC,QAAQ,CAAS;IAElC;;;;;;;;;OASG;gBACS,EAAE,cAAc,EAAE,WAAW,EAAE,OAAO,EAAE,QAAgB,EAAE,OAAO,EAAE,QAAQ,EAAE,GAAE,iBAAsB;IAoDjH;;;OAGG;IACH,eAAe,IAAI,OAAO;IAI1B;;;OAGG;IACH,UAAU,IAAI,MAAM,GAAG,SAAS;IAIhC;;;OAGG;IACH,WAAW,IAAI,MAAM;IAIrB;;;OAGG;IACG,WAAW,CAAC,EAAE,YAAsB,EAAE,GAAE;QAAE,YAAY,CAAC,EAAE,MAAM,CAAA;KAAO;;;;YAU9D,cAAc;IAY5B;;;;;;;;OAQG;IACG,KAAK,CACT,KAAK,EAAE,MAAM,GAAG,MAAM,CAAC,cAAc,EACrC,OAAO,CAAC,EAAE;QACR,OAAO,CAAC,EAAE,MAAM,CAAC;QACjB,YAAY,CAAC,EAAE,MAAM,CAAC;QACtB,WAAW,CAAC,EAAE,iBAAiB,CAAC,KAAK,CAAC,YAAY,CAAC,EAAE,CAAC,wBAAwB,CAAC,aAAa,CAAC,CAAC;KAC/F,GACA,OAAO,CAAC,MAAM,CAAC,cAAc,CAAC;IA2BjC;;;;OAIG;IACG,WAAW;;;IAIjB;;;;;;OAMG;IACG,MAAM,CACV,WAAW,EAAE,MAAM,CAAC,cAAc,EAClC,OAAO,CAAC,EAAE;QAAE,MAAM,CAAC,EAAE,OAAO,CAAC;QAAC,MAAM,CAAC,EAAE,WAAW,CAAC,KAAK,CAAC,MAAM,CAAC,EAAE,CAAC,kBAAkB,CAAA;KAAE,GACtF,OAAO,CAAC,MAAM,CAAC;CA2CnB"}

package/dist/index.js

@@ -4,10 +4,16 @@ import { TextToSpeechClient } from '@google-cloud/text-to-speech';
 import { MastraVoice } from '@mastra/core/voice';
 
 // src/index.ts
-var resolveAuthConfig = (modelConfig, fallback) => {
+var resolveAuthConfig = (modelConfig, fallback, vertexConfig) => {
   const resolved = {};
+  if (vertexConfig?.vertexAI) {
+    const projectId = vertexConfig.project || process.env.GOOGLE_CLOUD_PROJECT;
+    if (projectId) {
+      resolved.projectId = projectId;
+    }
+  }
   const apiKey = modelConfig?.apiKey ?? fallback.apiKey;
-  if (apiKey) {
+  if (apiKey && !vertexConfig?.vertexAI) {
     resolved.apiKey = apiKey;
   }
   const keyFilename = modelConfig?.keyFilename ?? fallback.keyFilename;
@@ -20,44 +26,57 @@ var resolveAuthConfig = (modelConfig, fallback) => {
   }
   return resolved;
 };
-var buildAuthOptions = (config) => {
+var buildAuthOptions = (config, vertexConfig) => {
+  const options = {};
   if (config.credentials) {
-    return { credentials: config.credentials };
+    options.credentials = config.credentials;
   }
   if (config.keyFilename) {
-    return { keyFilename: config.keyFilename };
+    options.keyFilename = config.keyFilename;
   }
-  if (config.apiKey) {
-    return { apiKey: config.apiKey };
+  if (config.apiKey && !vertexConfig?.vertexAI) {
+    options.apiKey = config.apiKey;
   }
-  return {};
+  if (config.projectId) {
+    options.projectId = config.projectId;
+  }
+  return options;
 };
 var DEFAULT_VOICE = "en-US-Casual-K";
 var GoogleVoice = class extends MastraVoice {
   ttsClient;
   speechClient;
+  vertexAI;
+  project;
+  location;
   /**
    * Creates an instance of GoogleVoice
-   * @param {Object} config - Configuration options
+   * @param {GoogleVoiceConfig} config - Configuration options
    * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
    * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
    * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
+   * @param {boolean} [config.vertexAI] - Enable Vertex AI mode
+   * @param {string} [config.project] - Google Cloud project ID (required for Vertex AI)
+   * @param {string} [config.location] - Google Cloud region (default: 'us-central1')
    */
-  constructor({
-    listeningModel,
-    speechModel,
-    speaker
-  } = {}) {
+  constructor({ listeningModel, speechModel, speaker, vertexAI = false, project, location } = {}) {
     const defaultApiKey = process.env.GOOGLE_API_KEY;
     const defaultKeyFilename = process.env.GOOGLE_APPLICATION_CREDENTIALS;
     const defaultSpeaker = DEFAULT_VOICE;
+    const resolvedProject = project || process.env.GOOGLE_CLOUD_PROJECT;
+    const resolvedLocation = location || process.env.GOOGLE_CLOUD_LOCATION || "us-central1";
+    if (vertexAI && !resolvedProject) {
+      throw new Error(
+        "Google Cloud project ID is required when using Vertex AI. Set GOOGLE_CLOUD_PROJECT environment variable or pass project to constructor."
+      );
+    }
+    const vertexConfig = { vertexAI, project: resolvedProject };
     const sharedFallback = {
       apiKey: defaultApiKey ?? speechModel?.apiKey ?? listeningModel?.apiKey,
       keyFilename: defaultKeyFilename ?? speechModel?.keyFilename ?? listeningModel?.keyFilename,
-      credentials: speechModel?.credentials ?? listeningModel?.credentials
-    };
-    const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback);
-    const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback);
+      credentials: speechModel?.credentials ?? listeningModel?.credentials};
+    const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback, vertexConfig);
+    const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback, vertexConfig);
     super({
       speechModel: {
         name: "",
@@ -69,11 +88,35 @@ var GoogleVoice = class extends MastraVoice {
       },
       speaker: speaker ?? defaultSpeaker
     });
-    const ttsOptions = buildAuthOptions(speechAuthConfig);
-    const speechOptions = buildAuthOptions(listeningAuthConfig);
+    this.vertexAI = vertexAI;
+    this.project = resolvedProject;
+    this.location = resolvedLocation;
+    const ttsOptions = buildAuthOptions(speechAuthConfig, { vertexAI});
+    const speechOptions = buildAuthOptions(listeningAuthConfig, { vertexAI});
     this.ttsClient = new TextToSpeechClient(ttsOptions);
     this.speechClient = new SpeechClient(speechOptions);
   }
+  /**
+   * Check if Vertex AI mode is enabled
+   * @returns {boolean} True if using Vertex AI
+   */
+  isUsingVertexAI() {
+    return this.vertexAI;
+  }
+  /**
+   * Get the configured Google Cloud project ID
+   * @returns {string | undefined} The project ID or undefined if not set
+   */
+  getProject() {
+    return this.project;
+  }
+  /**
+   * Get the configured Google Cloud location/region
+   * @returns {string} The location (default: 'us-central1')
+   */
+  getLocation() {
+    return this.location;
+  }
   /**
    * Gets a list of available voices
    * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.