@mastra/voice-google 0.1.3-alpha.9 → 0.1.4-alpha.0

package/dist/index.cjs

@@ -65,7 +65,11 @@ var GoogleVoice = class extends voice.MastraVoice {
   async streamToString(stream) {
     const chunks = [];
     for await (const chunk of stream) {
-      chunks.push(Buffer.from(chunk));
+      if (typeof chunk === "string") {
+        chunks.push(Buffer.from(chunk));
+      } else {
+        chunks.push(chunk);
+      }
     }
     return Buffer.concat(chunks).toString("utf-8");
   }
@@ -112,7 +116,11 @@ var GoogleVoice = class extends voice.MastraVoice {
     return this.traced(async () => {
       const chunks = [];
       for await (const chunk of audioStream) {
-        chunks.push(Buffer.from(chunk));
+        if (typeof chunk === "string") {
+          chunks.push(Buffer.from(chunk));
+        } else {
+          chunks.push(chunk);
+        }
       }
       const buffer = Buffer.concat(chunks);
       let request = {

package/dist/index.js

@@ -63,7 +63,11 @@ var GoogleVoice = class extends MastraVoice {
   async streamToString(stream) {
     const chunks = [];
     for await (const chunk of stream) {
-      chunks.push(Buffer.from(chunk));
+      if (typeof chunk === "string") {
+        chunks.push(Buffer.from(chunk));
+      } else {
+        chunks.push(chunk);
+      }
     }
     return Buffer.concat(chunks).toString("utf-8");
   }
@@ -110,7 +114,11 @@ var GoogleVoice = class extends MastraVoice {
     return this.traced(async () => {
       const chunks = [];
       for await (const chunk of audioStream) {
-        chunks.push(Buffer.from(chunk));
+        if (typeof chunk === "string") {
+          chunks.push(Buffer.from(chunk));
+        } else {
+          chunks.push(chunk);
+        }
       }
       const buffer = Buffer.concat(chunks);
       let request = {

package/package.json

@@ -1,8 +1,11 @@
 {
   "name": "@mastra/voice-google",
-  "version": "0.1.3-alpha.9",
+  "version": "0.1.4-alpha.0",
   "description": "Mastra Google voice integration",
   "type": "module",
+  "files": [
+    "dist"
+  ],
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
   "exports": {
@@ -19,21 +22,21 @@
     "./package.json": "./package.json"
   },
   "dependencies": {
-    "@google-cloud/speech": "^6.7.0",
-    "@google-cloud/text-to-speech": "^5.0.1",
-    "zod": "^3.24.1",
-    "@mastra/core": "^0.5.0-alpha.9"
+    "@google-cloud/speech": "^6.7.1",
+    "@google-cloud/text-to-speech": "^5.8.1",
+    "zod": "^3.24.2",
+    "@mastra/core": "^0.5.1-alpha.0"
   },
   "devDependencies": {
-    "@types/node": "^22.13.1",
-    "tsup": "^8.0.1",
-    "typescript": "^5.7.3",
-    "vitest": "^2.1.8",
-    "eslint": "^9.20.1",
-    "@internal/lint": "0.0.0"
+    "@types/node": "^22.13.10",
+    "eslint": "^9.22.0",
+    "tsup": "^8.4.0",
+    "typescript": "^5.8.2",
+    "vitest": "^2.1.9",
+    "@internal/lint": "0.0.1"
   },
   "scripts": {
-    "build": "tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake",
+    "build": "tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake=smallest --splitting",
     "build:watch": "pnpm build --watch",
     "test": "vitest run",
     "lint": "eslint ."

package/.turbo/turbo-build.log

@@ -1,23 +0,0 @@
-
-> @mastra/voice-google@0.1.3-alpha.9 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 11591ms
-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
-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 15442ms
-CLI Cleaning output folder
-ESM Build start
-CJS Build start
-ESM dist/index.js 5.45 KB
-ESM ⚡️ Build success in 671ms
-CJS dist/index.cjs 5.48 KB
-CJS ⚡️ Build success in 671ms

package/CHANGELOG.md

@@ -1,237 +0,0 @@
-# @mastra/voice-google
-
-## 0.1.3-alpha.9
-
-### Patch Changes
-
-- Updated dependencies [e9fbac5]
-- Updated dependencies [1e8bcbc]
-- Updated dependencies [aeb5e36]
-- Updated dependencies [f2301de]
-  - @mastra/core@0.5.0-alpha.9
-
-## 0.1.3-alpha.8
-
-### Patch Changes
-
-- Updated dependencies [506f1d5]
-  - @mastra/core@0.5.0-alpha.8
-
-## 0.1.3-alpha.7
-
-### Patch Changes
-
-- Updated dependencies [ee667a2]
-  - @mastra/core@0.5.0-alpha.7
-
-## 0.1.3-alpha.6
-
-### Patch Changes
-
-- Updated dependencies [f6678e4]
-  - @mastra/core@0.5.0-alpha.6
-
-## 0.1.3-alpha.5
-
-### Patch Changes
-
-- Updated dependencies [22643eb]
-- Updated dependencies [6feb23f]
-- Updated dependencies [f2d6727]
-- Updated dependencies [301e4ee]
-- Updated dependencies [dfbe4e9]
-- Updated dependencies [9e81f35]
-- Updated dependencies [caefaa2]
-- Updated dependencies [c151ae6]
-- Updated dependencies [52e0418]
-- Updated dependencies [03236ec]
-- Updated dependencies [3764e71]
-- Updated dependencies [df982db]
-- Updated dependencies [0461849]
-- Updated dependencies [2259379]
-- Updated dependencies [358f069]
-  - @mastra/core@0.5.0-alpha.5
-
-## 0.1.3-alpha.4
-
-### Patch Changes
-
-- Updated dependencies [d79aedf]
-  - @mastra/core@0.5.0-alpha.4
-
-## 0.1.3-alpha.3
-
-### Patch Changes
-
-- Updated dependencies [3d0e290]
-  - @mastra/core@0.5.0-alpha.3
-
-## 0.1.3-alpha.2
-
-### Patch Changes
-
-- Updated dependencies [02ffb7b]
-  - @mastra/core@0.5.0-alpha.2
-
-## 0.1.3-alpha.1
-
-### Patch Changes
-
-- Updated dependencies [dab255b]
-  - @mastra/core@0.5.0-alpha.1
-
-## 0.1.3-alpha.0
-
-### Patch Changes
-
-- Updated dependencies [59df7b6]
-- Updated dependencies [29f3a82]
-- Updated dependencies [59df7b6]
-- Updated dependencies [c139344]
-  - @mastra/core@0.5.0-alpha.0
-
-## 0.1.2
-
-### Patch Changes
-
-- Updated dependencies [1da20e7]
-  - @mastra/core@0.4.4
-
-## 0.1.2-alpha.0
-
-### Patch Changes
-
-- Updated dependencies [1da20e7]
-  - @mastra/core@0.4.4-alpha.0
-
-## 0.1.1
-
-### Patch Changes
-
-- bb4f447: Add support for commonjs
-- Updated dependencies [0d185b1]
-- Updated dependencies [ed55f1d]
-- Updated dependencies [06aa827]
-- Updated dependencies [0fd78ac]
-- Updated dependencies [2512a93]
-- Updated dependencies [e62de74]
-- Updated dependencies [0d25b75]
-- Updated dependencies [fd14a3f]
-- Updated dependencies [8d13b14]
-- Updated dependencies [3f369a2]
-- Updated dependencies [3ee4831]
-- Updated dependencies [4d4e1e1]
-- Updated dependencies [bb4f447]
-- Updated dependencies [108793c]
-- Updated dependencies [5f28f44]
-- Updated dependencies [dabecf4]
-  - @mastra/core@0.4.3
-
-## 0.1.1-alpha.4
-
-### Patch Changes
-
-- Updated dependencies [dabecf4]
-  - @mastra/core@0.4.3-alpha.4
-
-## 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
-
-- Updated dependencies [06aa827]
-  - @mastra/core@0.4.3-alpha.0
-
-## 0.1.0
-
-### Patch Changes
-
-- 5e0f727: deprecate @mastra/speech-google for @mastra/voice-google
-- Updated dependencies [7fceae1]
-- Updated dependencies [8d94c3e]
-- Updated dependencies [99dcdb5]
-- Updated dependencies [6cb63e0]
-- Updated dependencies [f626fbb]
-- Updated dependencies [e752340]
-- Updated dependencies [eb91535]
-  - @mastra/core@0.4.2
-
-## 0.1.0-alpha.4
-
-### Patch Changes
-
-- Updated dependencies [8d94c3e]
-- Updated dependencies [99dcdb5]
-- Updated dependencies [e752340]
-- Updated dependencies [eb91535]
-  - @mastra/core@0.4.2-alpha.2
-
-## 0.1.0-alpha.3
-
-### Patch Changes
-
-- Updated dependencies [6cb63e0]
-  - @mastra/core@0.4.2-alpha.1
-
-## 0.1.0-alpha.2
-
-### Patch Changes
-
-- 5e0f727: deprecate @mastra/speech-google for @mastra/voice-google
-
-## 0.1.0
-
-### Minor Changes
-
-- Initial release of @mastra/voice-google
-- Combines functionality from deprecated @mastra/speech-google
-- Adds Speech-to-Text capabilities
-- Implements new MastraVoice interface from @mastra/core
-
-### Notes
-
-This package replaces @mastra/speech-google, which reached version 0.1.3-alpha.1. Key features from the previous package:
-
-- Neural Text-to-Speech synthesis
-- Multiple voice options
-- Streaming support
-- Integration with Google Cloud services
-
-The new package adds:
-
-- Speech-to-Text recognition
-- Combined speech and listening models
-- Improved voice management
-- Better type safety and error handling

package/eslint.config.js

@@ -1,6 +0,0 @@
-import { createConfig } from '@internal/lint/eslint';
-
-const config = await createConfig();
-
-/** @type {import("eslint").Linter.Config[]} */
-export default [...config];

package/src/index.test.ts

@@ -1,133 +0,0 @@
-import { createWriteStream, mkdirSync, readFileSync } from 'node:fs';
-import { join } from 'node:path';
-import { Readable } from 'node:stream';
-import { describe, expect, it, beforeAll } from 'vitest';
-
-import { GoogleVoice } from './index';
-
-describe('GoogleVoice Integration Tests', () => {
-  let voice: GoogleVoice;
-  const outputDir = join(process.cwd(), 'test-outputs');
-
-  beforeAll(() => {
-    // Create output directory if it doesn't exist
-    try {
-      mkdirSync(outputDir, { recursive: true });
-    } catch (err) {
-      console.error(err);
-      // Ignore if directory already exists
-    }
-
-    voice = new GoogleVoice();
-  });
-
-  describe('getSpeakers', () => {
-    it('should list available voices', async () => {
-      const voices = await voice.getSpeakers();
-      expect(voices.length).toBeGreaterThan(0);
-      expect(voices[0]).toHaveProperty('voiceId');
-      expect(voices[0]).toHaveProperty('languageCodes');
-    }, 10000);
-  });
-
-  describe('speak', () => {
-    it('should generate audio from text and save to file', async () => {
-      const audioStream = await voice.speak('Hello World', {
-        speaker: 'en-US-Standard-F',
-      });
-
-      return new Promise((resolve, reject) => {
-        const outputPath = join(outputDir, 'speech-test.wav');
-        const fileStream = createWriteStream(outputPath);
-        const chunks: Buffer[] = [];
-
-        audioStream.on('data', (chunk: Buffer) => chunks.push(chunk));
-        audioStream.pipe(fileStream);
-
-        fileStream.on('finish', () => {
-          expect(chunks.length).toBeGreaterThan(0);
-          resolve(undefined);
-        });
-
-        audioStream.on('error', reject);
-        fileStream.on('error', reject);
-      });
-    }, 10000);
-
-    it('should work with default voice', async () => {
-      const audioStream = await voice.speak('Test with default voice');
-
-      return new Promise((resolve, reject) => {
-        const outputPath = join(outputDir, 'speech-test-default.wav');
-        const fileStream = createWriteStream(outputPath);
-        const chunks: Buffer[] = [];
-
-        audioStream.on('data', (chunk: Buffer) => chunks.push(chunk));
-        audioStream.pipe(fileStream);
-
-        fileStream.on('finish', () => {
-          expect(chunks.length).toBeGreaterThan(0);
-          resolve(undefined);
-        });
-
-        audioStream.on('error', reject);
-        fileStream.on('error', reject);
-      });
-    }, 10000);
-
-    it('should handle stream input', async () => {
-      const textStream = Readable.from(['Hello', ' from', ' stream', ' input!']);
-
-      const audioStream = await voice.speak(textStream);
-
-      return new Promise((resolve, reject) => {
-        const outputPath = join(outputDir, 'speech-stream-input-test.wav');
-        const fileStream = createWriteStream(outputPath);
-        const chunks: Buffer[] = [];
-
-        audioStream.on('data', (chunk: Buffer) => chunks.push(chunk));
-        audioStream.pipe(fileStream);
-
-        fileStream.on('finish', () => {
-          expect(chunks.length).toBeGreaterThan(0);
-          resolve(undefined);
-        });
-
-        audioStream.on('error', reject);
-        fileStream.on('error', reject);
-      });
-    }, 10000);
-  });
-
-  describe('listen', () => {
-    it('should transcribe audio stream to text', async () => {
-      const audioStream = Readable.from(readFileSync(join(outputDir, 'speech-test.wav')));
-
-      const result = await voice.listen(audioStream);
-      console.log(result);
-      expect(typeof result).toBe('string');
-      expect(result).toContain('hello world');
-    }, 10000);
-
-    // it('should support streaming transcription', async () => {
-    //   const audioStream = Readable.from(
-    //     readFileSync(join(outputDir, 'speech-test.mp3'))
-    //   );
-
-    //   const outputStream = await voice.listen(audioStream, { stream: true });
-    //   expect(outputStream).toBeInstanceOf(PassThrough);
-
-    //   return new Promise((resolve, reject) => {
-    //     const chunks: string[] = [];
-    //     (outputStream as PassThrough).on('data', (chunk: string) => chunks.push(chunk));
-    //     (outputStream as PassThrough).on('end', () => {
-    //       expect(chunks.length).toBeGreaterThan(0);
-    //       const transcription = chunks.join('');
-    //       expect(transcription).toContain('hello world');
-    //       resolve(undefined);
-    //     });
-    //     (outputStream as PassThrough).on('error', reject);
-    //   });
-    // });
-  });
-});

package/src/index.ts

@@ -1,199 +0,0 @@
-import { PassThrough } from 'stream';
-
-import { SpeechClient } from '@google-cloud/speech';
-import type { google as SpeechTypes } from '@google-cloud/speech/build/protos/protos';
-import { TextToSpeechClient } from '@google-cloud/text-to-speech';
-import type { google as TextToSpeechTypes } from '@google-cloud/text-to-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 interface GoogleModelConfig {
-  apiKey?: string;
-}
-
-const DEFAULT_VOICE = 'en-US-Casual-K';
-
-/**
- * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services
- * @class GoogleVoice
- * @extends MastraVoice
- */
-export class GoogleVoice extends MastraVoice {
-  private ttsClient: TextToSpeechClient;
-  private speechClient: 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;
-  } = {}) {
-    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 TextToSpeechClient({
-      apiKey: this.speechModel?.apiKey || defaultApiKey,
-    });
-
-    this.speechClient = new 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' }: { languageCode?: string } = {}) {
-    return this.traced(async () => {
-      const [response] = await this.ttsClient.listVoices({ languageCode: languageCode });
-      return (response?.voices || [])
-        .filter(voice => voice.name && voice.languageCodes)
-        .map(voice => ({
-          voiceId: voice.name!,
-          languageCodes: voice.languageCodes!,
-        }));
-    }, 'voice.google.getSpeakers')();
-  }
-
-  private async streamToString(stream: NodeJS.ReadableStream): Promise<string> {
-    const chunks: Buffer[] = [];
-    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: string | NodeJS.ReadableStream,
-    options?: {
-      speaker?: string;
-      languageCode?: string;
-      audioConfig?: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig'];
-    },
-  ): Promise<NodeJS.ReadableStream> {
-    return this.traced(async () => {
-      const text = typeof input === 'string' ? input : await this.streamToString(input);
-
-      const request: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest = {
-        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 = new PassThrough();
-      stream.end(Buffer.from(response.audioContent));
-      return stream;
-    }, '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: NodeJS.ReadableStream,
-    options?: { stream?: boolean; config?: SpeechTypes.cloud.speech.v1.IRecognitionConfig },
-  ): Promise<string> {
-    return this.traced(async () => {
-      const chunks: Buffer[] = [];
-      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 as SpeechTypes.cloud.speech.v1.IRecognizeRequest);
-      console.log(`AFTER REQUEST`);
-
-      if (!response.results || response.results.length === 0) {
-        throw new Error('No transcription results returned');
-      }
-
-      const transcription = response.results
-        .map((result: any) => {
-          if (!result.alternatives || result.alternatives.length === 0) {
-            return '';
-          }
-          return result.alternatives[0].transcript || '';
-        })
-        .filter((text: string) => text.length > 0)
-        .join(' ');
-
-      if (!transcription) {
-        throw new Error('No valid transcription found in results');
-      }
-
-      return transcription;
-    }, 'voice.google.listen')();
-  }
-}

package/tsconfig.json

@@ -1,5 +0,0 @@
-{
-  "extends": "../../tsconfig.node.json",
-  "include": ["src/**/*"],
-  "exclude": ["node_modules", "**/*.test.ts"]
-}

package/vitest.config.ts

@@ -1,8 +0,0 @@
-import { defineConfig } from 'vitest/config';
-
-export default defineConfig({
-  test: {
-    globals: true,
-    environment: 'node',
-  },
-});