@mastra/voice-google 0.1.1-alpha.0 → 0.1.1-alpha.3

package/.turbo/turbo-build.log

@@ -1,18 +1,23 @@
 
-> @mastra/voice-google@0.1.1-alpha.0 build /home/runner/work/mastra/mastra/voice/google
-> tsup src/index.ts --format esm --experimental-dts --clean --treeshake
+> @mastra/voice-google@0.1.1-alpha.3 build /home/runner/work/mastra/mastra/voice/google
+> tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake
 
 CLI Building entry: src/index.ts
 CLI Using tsconfig: tsconfig.json
 CLI tsup v8.3.6
 TSC Build start
-TSC ⚡️ Build success in 10798ms
+TSC ⚡️ Build success in 10277ms
 DTS Build start
 CLI Target: es2022
 Analysis will use the bundled TypeScript version 5.7.3
 Writing package typings: /home/runner/work/mastra/mastra/voice/google/dist/_tsup-dts-rollup.d.ts
-DTS ⚡️ Build success in 9155ms
+Analysis will use the bundled TypeScript version 5.7.3
+Writing package typings: /home/runner/work/mastra/mastra/voice/google/dist/_tsup-dts-rollup.d.cts
+DTS ⚡️ Build success in 15583ms
 CLI Cleaning output folder
 ESM Build start
+CJS Build start
+CJS dist/index.cjs 5.48 KB
+CJS ⚡️ Build success in 550ms
 ESM dist/index.js 5.45 KB
-ESM ⚡️ Build success in 290ms
+ESM ⚡️ Build success in 556ms

package/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @mastra/voice-google
 
+## 0.1.1-alpha.3
+
+### Patch Changes
+
+- bb4f447: Add support for commonjs
+- Updated dependencies [0fd78ac]
+- Updated dependencies [0d25b75]
+- Updated dependencies [fd14a3f]
+- Updated dependencies [3f369a2]
+- Updated dependencies [4d4e1e1]
+- Updated dependencies [bb4f447]
+  - @mastra/core@0.4.3-alpha.3
+
+## 0.1.1-alpha.2
+
+### Patch Changes
+
+- Updated dependencies [2512a93]
+- Updated dependencies [e62de74]
+  - @mastra/core@0.4.3-alpha.2
+
+## 0.1.1-alpha.1
+
+### Patch Changes
+
+- Updated dependencies [0d185b1]
+- Updated dependencies [ed55f1d]
+- Updated dependencies [8d13b14]
+- Updated dependencies [3ee4831]
+- Updated dependencies [108793c]
+- Updated dependencies [5f28f44]
+  - @mastra/core@0.4.3-alpha.1
+
 ## 0.1.1-alpha.0
 
 ### Patch Changes

package/dist/_tsup-dts-rollup.d.cts

@@ -0,0 +1,73 @@
+import type { google } from '@google-cloud/text-to-speech/build/protos/protos';
+import type { google as google_2 } from '@google-cloud/speech/build/protos/protos';
+import { MastraVoice } from '@mastra/core/voice';
+
+/**
+ * Configuration for Google Cloud Voice models
+ * @interface GoogleModelConfig
+ * @property {string} [apiKey] - Optional Google Cloud API key. If not provided, will use GOOGLE_API_KEY environment variable
+ */
+export declare interface GoogleModelConfig {
+    apiKey?: string;
+}
+
+/**
+ * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services
+ * @class GoogleVoice
+ * @extends MastraVoice
+ */
+export declare class GoogleVoice extends MastraVoice {
+    private ttsClient;
+    private speechClient;
+    /**
+     * Creates an instance of GoogleVoice
+     * @param {Object} 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
+     * @throws {Error} If no API key is provided via config or environment variable
+     */
+    constructor({ listeningModel, speechModel, speaker, }?: {
+        listeningModel?: GoogleModelConfig;
+        speechModel?: GoogleModelConfig;
+        speaker?: 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.
+     */
+    getSpeakers({ languageCode }?: {
+        languageCode?: string;
+    }): Promise<{
+        voiceId: string;
+        languageCodes: string[];
+    }[]>;
+    private streamToString;
+    /**
+     * Converts text to speech
+     * @param {string | NodeJS.ReadableStream} input - Text or stream to convert to speech
+     * @param {Object} [options] - Speech synthesis options
+     * @param {string} [options.speaker] - Voice ID to use
+     * @param {string} [options.languageCode] - Language code for the voice
+     * @param {TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig']} [options.audioConfig] - Audio configuration options
+     * @returns {Promise<NodeJS.ReadableStream>} Stream of synthesized audio. Default encoding is LINEAR16.
+     */
+    speak(input: string | NodeJS.ReadableStream, options?: {
+        speaker?: string;
+        languageCode?: string;
+        audioConfig?: google.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig'];
+    }): Promise<NodeJS.ReadableStream>;
+    /**
+     * Converts speech to text
+     * @param {NodeJS.ReadableStream} audioStream - Audio stream to transcribe. Default encoding is LINEAR16.
+     * @param {Object} [options] - Recognition options
+     * @param {SpeechTypes.cloud.speech.v1.IRecognitionConfig} [options.config] - Recognition configuration
+     * @returns {Promise<string>} Transcribed text
+     */
+    listen(audioStream: NodeJS.ReadableStream, options?: {
+        stream?: boolean;
+        config?: google_2.cloud.speech.v1.IRecognitionConfig;
+    }): Promise<string>;
+}
+
+export { }

package/dist/index.cjs

@@ -0,0 +1,148 @@
+'use strict';
+
+var stream = require('stream');
+var speech = require('@google-cloud/speech');
+var textToSpeech = require('@google-cloud/text-to-speech');
+var voice = require('@mastra/core/voice');
+
+// src/index.ts
+var DEFAULT_VOICE = "en-US-Casual-K";
+var GoogleVoice = class extends voice.MastraVoice {
+  ttsClient;
+  speechClient;
+  /**
+   * Creates an instance of GoogleVoice
+   * @param {Object} 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
+   * @throws {Error} If no API key is provided via config or environment variable
+   */
+  constructor({
+    listeningModel,
+    speechModel,
+    speaker
+  } = {}) {
+    const defaultApiKey = process.env.GOOGLE_API_KEY;
+    const defaultSpeaker = DEFAULT_VOICE;
+    super({
+      speechModel: {
+        name: "",
+        apiKey: speechModel?.apiKey ?? defaultApiKey
+      },
+      listeningModel: {
+        name: "",
+        apiKey: listeningModel?.apiKey ?? defaultApiKey
+      },
+      speaker: speaker ?? defaultSpeaker
+    });
+    const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;
+    if (!apiKey) {
+      throw new Error(
+        "Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor"
+      );
+    }
+    this.ttsClient = new textToSpeech.TextToSpeechClient({
+      apiKey: this.speechModel?.apiKey || defaultApiKey
+    });
+    this.speechClient = new speech.SpeechClient({
+      apiKey: this.listeningModel?.apiKey || defaultApiKey
+    });
+  }
+  /**
+   * 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.
+   */
+  async getSpeakers({ languageCode = "en-US" } = {}) {
+    return this.traced(async () => {
+      const [response] = await this.ttsClient.listVoices({ languageCode });
+      return (response?.voices || []).filter((voice) => voice.name && voice.languageCodes).map((voice) => ({
+        voiceId: voice.name,
+        languageCodes: voice.languageCodes
+      }));
+    }, "voice.google.getSpeakers")();
+  }
+  async streamToString(stream) {
+    const chunks = [];
+    for await (const chunk of stream) {
+      chunks.push(Buffer.from(chunk));
+    }
+    return Buffer.concat(chunks).toString("utf-8");
+  }
+  /**
+   * Converts text to speech
+   * @param {string | NodeJS.ReadableStream} input - Text or stream to convert to speech
+   * @param {Object} [options] - Speech synthesis options
+   * @param {string} [options.speaker] - Voice ID to use
+   * @param {string} [options.languageCode] - Language code for the voice
+   * @param {TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig']} [options.audioConfig] - Audio configuration options
+   * @returns {Promise<NodeJS.ReadableStream>} Stream of synthesized audio. Default encoding is LINEAR16.
+   */
+  async speak(input, options) {
+    return this.traced(async () => {
+      const text = typeof input === "string" ? input : await this.streamToString(input);
+      const request = {
+        input: { text },
+        voice: {
+          name: options?.speaker || this.speaker,
+          languageCode: options?.languageCode || options?.speaker?.split("-").slice(0, 2).join("-") || "en-US"
+        },
+        audioConfig: options?.audioConfig || { audioEncoding: "LINEAR16" }
+      };
+      const [response] = await this.ttsClient.synthesizeSpeech(request);
+      if (!response.audioContent) {
+        throw new Error("No audio content returned.");
+      }
+      if (typeof response.audioContent === "string") {
+        throw new Error("Audio content is a string.");
+      }
+      const stream$1 = new stream.PassThrough();
+      stream$1.end(Buffer.from(response.audioContent));
+      return stream$1;
+    }, "voice.google.speak")();
+  }
+  /**
+   * Converts speech to text
+   * @param {NodeJS.ReadableStream} audioStream - Audio stream to transcribe. Default encoding is LINEAR16.
+   * @param {Object} [options] - Recognition options
+   * @param {SpeechTypes.cloud.speech.v1.IRecognitionConfig} [options.config] - Recognition configuration
+   * @returns {Promise<string>} Transcribed text
+   */
+  async listen(audioStream, options) {
+    return this.traced(async () => {
+      const chunks = [];
+      for await (const chunk of audioStream) {
+        chunks.push(Buffer.from(chunk));
+      }
+      const buffer = Buffer.concat(chunks);
+      let request = {
+        config: {
+          encoding: "LINEAR16",
+          languageCode: "en-US",
+          ...options?.config
+        },
+        audio: {
+          content: buffer.toString("base64")
+        }
+      };
+      console.log(`BEFORE REQUEST`);
+      const [response] = await this.speechClient.recognize(request);
+      console.log(`AFTER REQUEST`);
+      if (!response.results || response.results.length === 0) {
+        throw new Error("No transcription results returned");
+      }
+      const transcription = response.results.map((result) => {
+        if (!result.alternatives || result.alternatives.length === 0) {
+          return "";
+        }
+        return result.alternatives[0].transcript || "";
+      }).filter((text) => text.length > 0).join(" ");
+      if (!transcription) {
+        throw new Error("No valid transcription found in results");
+      }
+      return transcription;
+    }, "voice.google.listen")();
+  }
+};
+
+exports.GoogleVoice = GoogleVoice;

package/dist/index.d.cts

@@ -0,0 +1,2 @@
+export { GoogleModelConfig } from './_tsup-dts-rollup.cjs';
+export { GoogleVoice } from './_tsup-dts-rollup.cjs';

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/voice-google",
-  "version": "0.1.1-alpha.0",
+  "version": "0.1.1-alpha.3",
   "description": "Mastra Google voice integration",
   "type": "module",
   "main": "dist/index.js",
@@ -10,6 +10,10 @@
       "import": {
         "types": "./dist/index.d.ts",
         "default": "./dist/index.js"
+      },
+      "require": {
+        "types": "./dist/index.d.cts",
+        "default": "./dist/index.cjs"
       }
     },
     "./package.json": "./package.json"
@@ -18,7 +22,7 @@
     "@google-cloud/speech": "^6.7.0",
     "@google-cloud/text-to-speech": "^5.0.1",
     "zod": "^3.24.1",
-    "@mastra/core": "^0.4.3-alpha.0"
+    "@mastra/core": "^0.4.3-alpha.3"
   },
   "devDependencies": {
     "@types/node": "^22.13.1",
@@ -29,7 +33,7 @@
     "@internal/lint": "0.0.0"
   },
   "scripts": {
-    "build": "tsup src/index.ts --format esm --experimental-dts --clean --treeshake",
+    "build": "tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake",
     "build:watch": "pnpm build --watch",
     "test": "vitest run",
     "lint": "eslint ."