@pie-players/tts-server-google 0.1.0 → 0.1.3

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@pie-players/tts-server-google",
-	"version": "0.1.0",
+	"version": "0.1.3",
 	"description": "Google Cloud Text-to-Speech provider for server-side TTS with speech marks support",
 	"type": "module",
 	"main": "./dist/index.js",
@@ -11,10 +11,13 @@
 			"import": "./dist/index.js"
 		}
 	},
+	"files": [
+		"dist"
+	],
 	"scripts": {
 		"build": "tsc",
 		"dev": "tsc --watch",
-		"test": "vitest",
+		"test": "vitest run --passWithNoTests",
 		"test:coverage": "vitest --coverage"
 	},
 	"keywords": [
@@ -29,7 +32,7 @@
 	"license": "MIT",
 	"dependencies": {
 		"@google-cloud/text-to-speech": "^5.0.0",
-		"@pie-players/tts-server-core": "workspace:*"
+		"@pie-players/tts-server-core": "0.1.3"
 	},
 	"devDependencies": {
 		"typescript": "^5.3.3",

package/.turbo/turbo-build.log

@@ -1 +0,0 @@
-$ tsc

package/examples/INTEGRATION-GUIDE.md

@@ -1,532 +0,0 @@
-# Google Cloud TTS Integration Guide
-
-This guide shows how to integrate the Google Cloud Text-to-Speech provider into your server-side application.
-
-## Prerequisites
-
-1. **Google Cloud Project**: Create a project at [console.cloud.google.com](https://console.cloud.google.com)
-2. **Enable Text-to-Speech API**: Go to APIs & Services → Enable "Cloud Text-to-Speech API"
-3. **Authentication**: Set up one of the authentication methods below
-
-## Authentication Setup
-
-### Option 1: Service Account (Recommended for Production)
-
-1. Go to IAM & Admin → Service Accounts
-2. Create a service account
-3. Grant the role: "Cloud Text-to-Speech User"
-4. Create and download a JSON key file
-
-```typescript
-import { GoogleCloudTTSProvider } from '@pie-players/tts-server-google';
-
-const provider = new GoogleCloudTTSProvider();
-
-await provider.initialize({
-  projectId: 'your-project-id',
-  credentials: './config/service-account.json',
-  voiceType: 'wavenet',
-});
-```
-
-### Option 2: API Key (Simple but Less Secure)
-
-1. Go to APIs & Services → Credentials
-2. Create credentials → API Key
-3. Restrict the key to "Cloud Text-to-Speech API"
-
-```typescript
-await provider.initialize({
-  projectId: 'your-project-id',
-  credentials: {
-    apiKey: process.env.GOOGLE_TTS_API_KEY!,
-  },
-});
-```
-
-### Option 3: Application Default Credentials (Local Development)
-
-1. Install Google Cloud SDK
-2. Run: `gcloud auth application-default login`
-
-```typescript
-await provider.initialize({
-  projectId: 'your-project-id',
-  // No credentials needed - uses ADC
-});
-```
-
-## SvelteKit Integration
-
-### 1. Install Dependencies
-
-```bash
-npm install @pie-players/tts-server-google
-```
-
-### 2. Create TTS API Route
-
-**File: `src/routes/api/tts/synthesize/+server.ts`**
-
-```typescript
-import { GoogleCloudTTSProvider } from '@pie-players/tts-server-google';
-import { json } from '@sveltejs/kit';
-import type { RequestHandler } from './$types';
-
-// Initialize provider once (singleton pattern)
-let ttsProvider: GoogleCloudTTSProvider | null = null;
-
-async function getTTSProvider() {
-  if (!ttsProvider) {
-    ttsProvider = new GoogleCloudTTSProvider();
-    await ttsProvider.initialize({
-      projectId: process.env.GOOGLE_CLOUD_PROJECT!,
-      credentials: process.env.GOOGLE_APPLICATION_CREDENTIALS,
-      voiceType: 'wavenet',
-      defaultVoice: 'en-US-Wavenet-A',
-    });
-  }
-  return ttsProvider;
-}
-
-export const POST: RequestHandler = async ({ request }) => {
-  try {
-    const { text, voice, includeSpeechMarks } = await request.json();
-
-    const provider = await getTTSProvider();
-
-    const result = await provider.synthesize({
-      text,
-      voice,
-      includeSpeechMarks: includeSpeechMarks ?? true,
-    });
-
-    // Convert audio buffer to base64 for JSON response
-    const audioBase64 = result.audio.toString('base64');
-
-    return json({
-      audio: audioBase64,
-      contentType: result.contentType,
-      speechMarks: result.speechMarks,
-      metadata: result.metadata,
-    });
-  } catch (error) {
-    console.error('TTS synthesis failed:', error);
-    return json(
-      { error: error instanceof Error ? error.message : 'TTS synthesis failed' },
-      { status: 500 }
-    );
-  }
-};
-```
-
-### 3. Create Voices API Route
-
-**File: `src/routes/api/tts/voices/+server.ts`**
-
-```typescript
-import { GoogleCloudTTSProvider } from '@pie-players/tts-server-google';
-import { json } from '@sveltejs/kit';
-import type { RequestHandler } from './$types';
-
-let ttsProvider: GoogleCloudTTSProvider | null = null;
-
-async function getTTSProvider() {
-  if (!ttsProvider) {
-    ttsProvider = new GoogleCloudTTSProvider();
-    await ttsProvider.initialize({
-      projectId: process.env.GOOGLE_CLOUD_PROJECT!,
-      credentials: process.env.GOOGLE_APPLICATION_CREDENTIALS,
-      voiceType: 'wavenet',
-    });
-  }
-  return ttsProvider;
-}
-
-export const GET: RequestHandler = async ({ url }) => {
-  try {
-    const language = url.searchParams.get('language') || undefined;
-    const gender = url.searchParams.get('gender') as 'male' | 'female' | 'neutral' | undefined;
-
-    const provider = await getTTSProvider();
-
-    const voices = await provider.getVoices({ language, gender });
-
-    return json({ voices });
-  } catch (error) {
-    console.error('Failed to fetch voices:', error);
-    return json(
-      { error: error instanceof Error ? error.message : 'Failed to fetch voices' },
-      { status: 500 }
-    );
-  }
-};
-```
-
-### 4. Environment Variables
-
-**File: `.env`**
-
-```bash
-# Google Cloud Configuration
-GOOGLE_CLOUD_PROJECT=your-project-id
-GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
-
-# Or use API key
-# GOOGLE_TTS_API_KEY=AIza...
-```
-
-### 5. Client-Side Usage
-
-**File: `src/lib/tts-client.ts`**
-
-```typescript
-export interface TTSResult {
-  audio: string; // Base64 encoded
-  contentType: string;
-  speechMarks: Array<{
-    time: number;
-    type: string;
-    start: number;
-    end: number;
-    value: string;
-  }>;
-  metadata: {
-    providerId: string;
-    voice: string;
-    duration: number;
-  };
-}
-
-export async function synthesizeSpeech(
-  text: string,
-  voice?: string
-): Promise<TTSResult> {
-  const response = await fetch('/api/tts/synthesize', {
-    method: 'POST',
-    headers: { 'Content-Type': 'application/json' },
-    body: JSON.stringify({ text, voice, includeSpeechMarks: true }),
-  });
-
-  if (!response.ok) {
-    throw new Error(`TTS failed: ${response.statusText}`);
-  }
-
-  return response.json();
-}
-
-export async function playAudio(result: TTSResult): Promise<void> {
-  // Convert base64 to blob
-  const audioData = atob(result.audio);
-  const audioArray = new Uint8Array(audioData.length);
-  for (let i = 0; i < audioData.length; i++) {
-    audioArray[i] = audioData.charCodeAt(i);
-  }
-  const blob = new Blob([audioArray], { type: result.contentType });
-
-  // Play audio
-  const url = URL.createObjectURL(blob);
-  const audio = new Audio(url);
-  await audio.play();
-
-  // Clean up
-  audio.onended = () => URL.revokeObjectURL(url);
-}
-
-export async function getVoices(language?: string) {
-  const params = new URLSearchParams();
-  if (language) params.set('language', language);
-
-  const response = await fetch(`/api/tts/voices?${params}`);
-  const { voices } = await response.json();
-  return voices;
-}
-```
-
-**File: `src/routes/+page.svelte`**
-
-```svelte
-<script lang="ts">
-  import { synthesizeSpeech, playAudio, getVoices } from '$lib/tts-client';
-  import { onMount } from 'svelte';
-
-  let text = 'Hello world, this is Google Cloud Text to Speech!';
-  let voice = 'en-US-Wavenet-A';
-  let voices: any[] = [];
-  let speechMarks: any[] = [];
-  let isPlaying = false;
-
-  onMount(async () => {
-    voices = await getVoices('en-US');
-  });
-
-  async function handleSpeak() {
-    try {
-      isPlaying = true;
-      const result = await synthesizeSpeech(text, voice);
-      speechMarks = result.speechMarks;
-      await playAudio(result);
-    } catch (error) {
-      console.error('Speech failed:', error);
-      alert('Speech synthesis failed');
-    } finally {
-      isPlaying = false;
-    }
-  }
-</script>
-
-<div class="container">
-  <h1>Google Cloud TTS Demo</h1>
-
-  <div class="controls">
-    <label>
-      Text to speak:
-      <textarea bind:value={text} rows="4"></textarea>
-    </label>
-
-    <label>
-      Voice:
-      <select bind:value={voice}>
-        {#each voices as v}
-          <option value={v.id}>{v.name} ({v.gender})</option>
-        {/each}
-      </select>
-    </label>
-
-    <button on:click={handleSpeak} disabled={isPlaying}>
-      {isPlaying ? 'Speaking...' : 'Speak'}
-    </button>
-  </div>
-
-  {#if speechMarks.length > 0}
-    <div class="speech-marks">
-      <h2>Speech Marks</h2>
-      <ul>
-        {#each speechMarks as mark}
-          <li>
-            {mark.value} ({mark.time}ms)
-          </li>
-        {/each}
-      </ul>
-    </div>
-  {/if}
-</div>
-
-<style>
-  .container {
-    max-width: 800px;
-    margin: 2rem auto;
-    padding: 2rem;
-  }
-
-  .controls {
-    display: flex;
-    flex-direction: column;
-    gap: 1rem;
-  }
-
-  textarea {
-    width: 100%;
-    padding: 0.5rem;
-    font-family: inherit;
-  }
-
-  select {
-    width: 100%;
-    padding: 0.5rem;
-  }
-
-  button {
-    padding: 0.75rem 1.5rem;
-    background: #4285f4;
-    color: white;
-    border: none;
-    border-radius: 4px;
-    cursor: pointer;
-    font-size: 1rem;
-  }
-
-  button:disabled {
-    background: #ccc;
-    cursor: not-allowed;
-  }
-
-  .speech-marks {
-    margin-top: 2rem;
-    padding: 1rem;
-    background: #f5f5f5;
-    border-radius: 4px;
-  }
-
-  .speech-marks ul {
-    list-style: none;
-    padding: 0;
-  }
-
-  .speech-marks li {
-    padding: 0.25rem;
-    font-family: monospace;
-  }
-</style>
-```
-
-## Express.js Integration
-
-```typescript
-import express from 'express';
-import { GoogleCloudTTSProvider } from '@pie-players/tts-server-google';
-
-const app = express();
-app.use(express.json());
-
-// Initialize provider
-const ttsProvider = new GoogleCloudTTSProvider();
-await ttsProvider.initialize({
-  projectId: process.env.GOOGLE_CLOUD_PROJECT!,
-  credentials: process.env.GOOGLE_APPLICATION_CREDENTIALS,
-  voiceType: 'wavenet',
-});
-
-// Synthesize endpoint
-app.post('/api/tts/synthesize', async (req, res) => {
-  try {
-    const { text, voice, includeSpeechMarks } = req.body;
-
-    const result = await ttsProvider.synthesize({
-      text,
-      voice,
-      includeSpeechMarks: includeSpeechMarks ?? true,
-    });
-
-    // Return audio as buffer
-    res.json({
-      audio: result.audio.toString('base64'),
-      contentType: result.contentType,
-      speechMarks: result.speechMarks,
-      metadata: result.metadata,
-    });
-  } catch (error) {
-    console.error('TTS synthesis failed:', error);
-    res.status(500).json({ error: 'TTS synthesis failed' });
-  }
-});
-
-// Voices endpoint
-app.get('/api/tts/voices', async (req, res) => {
-  try {
-    const { language, gender } = req.query;
-
-    const voices = await ttsProvider.getVoices({
-      language: language as string,
-      gender: gender as 'male' | 'female' | 'neutral',
-    });
-
-    res.json({ voices });
-  } catch (error) {
-    console.error('Failed to fetch voices:', error);
-    res.status(500).json({ error: 'Failed to fetch voices' });
-  }
-});
-
-app.listen(3000, () => {
-  console.log('Server running on http://localhost:3000');
-});
-```
-
-## Next.js App Router Integration
-
-**File: `app/api/tts/synthesize/route.ts`**
-
-```typescript
-import { GoogleCloudTTSProvider } from '@pie-players/tts-server-google';
-import { NextResponse } from 'next/server';
-
-let ttsProvider: GoogleCloudTTSProvider | null = null;
-
-async function getTTSProvider() {
-  if (!ttsProvider) {
-    ttsProvider = new GoogleCloudTTSProvider();
-    await ttsProvider.initialize({
-      projectId: process.env.GOOGLE_CLOUD_PROJECT!,
-      credentials: process.env.GOOGLE_APPLICATION_CREDENTIALS,
-      voiceType: 'wavenet',
-    });
-  }
-  return ttsProvider;
-}
-
-export async function POST(request: Request) {
-  try {
-    const { text, voice, includeSpeechMarks } = await request.json();
-
-    const provider = await getTTSProvider();
-
-    const result = await provider.synthesize({
-      text,
-      voice,
-      includeSpeechMarks: includeSpeechMarks ?? true,
-    });
-
-    return NextResponse.json({
-      audio: result.audio.toString('base64'),
-      contentType: result.contentType,
-      speechMarks: result.speechMarks,
-      metadata: result.metadata,
-    });
-  } catch (error) {
-    console.error('TTS synthesis failed:', error);
-    return NextResponse.json(
-      { error: 'TTS synthesis failed' },
-      { status: 500 }
-    );
-  }
-}
-```
-
-## Security Best Practices
-
-1. **Never expose API keys in client code** - Always use server-side endpoints
-2. **Restrict API keys** - Limit to specific APIs and IP addresses
-3. **Use service accounts in production** - More secure than API keys
-4. **Rate limiting** - Implement rate limiting to prevent abuse
-5. **Cache results** - Cache TTS output to reduce API calls and costs
-6. **Validate input** - Sanitize and validate user input before synthesis
-
-## Cost Optimization
-
-1. **Cache frequently used phrases** - Store audio for common text
-2. **Use standard voices when possible** - $4/1M vs $16/1M for neural
-3. **Batch requests** - Group multiple synthesis requests when feasible
-4. **Monitor usage** - Set up billing alerts in Google Cloud Console
-
-## Troubleshooting
-
-### Authentication Errors
-
-```
-Error: Google Cloud authentication failed
-```
-
-**Solution**: Verify your credentials are correct and the service account has the "Cloud Text-to-Speech User" role.
-
-### Rate Limit Exceeded
-
-```
-Error: Google Cloud rate limit exceeded
-```
-
-**Solution**: Implement exponential backoff and request rate limiting. Consider increasing your quota in Google Cloud Console.
-
-### No Audio Content
-
-```
-Error: No audio content received from Google Cloud TTS
-```
-
-**Solution**: Check that your project has the Text-to-Speech API enabled and your billing is active.
-
-## Support
-
-For issues specific to this package, please file an issue on GitHub.
-
-For Google Cloud TTS API issues, see the [official documentation](https://cloud.google.com/text-to-speech/docs).

package/src/GoogleCloudTTSProvider.ts

@@ -1,688 +0,0 @@
-/**
- * Google Cloud Text-to-Speech server-side TTS provider
- * @module @pie-players/tts-server-google
- */
-
-import { v1beta1, protos } from "@google-cloud/text-to-speech";
-
-import {
-	BaseTTSProvider,
-	type GetVoicesOptions,
-	type ServerProviderCapabilities,
-	type SpeechMark,
-	type SynthesizeRequest,
-	type SynthesizeResponse,
-	TTSError,
-	TTSErrorCode,
-	type TTSServerConfig,
-	type Voice,
-} from "@pie-players/tts-server-core";
-
-/**
- * Google Cloud Text-to-Speech provider configuration.
- *
- * This extends the base TTSServerConfig with Google Cloud-specific settings.
- */
-export interface GoogleCloudTTSConfig extends TTSServerConfig {
-	/**
-	 * Google Cloud project ID (required)
-	 *
-	 * @example 'my-project-123456'
-	 * @required
-	 */
-	projectId: string;
-
-	/**
-	 * Authentication credentials
-	 *
-	 * Supports multiple authentication methods:
-	 * - Service account JSON file path (recommended for production)
-	 * - Service account key object (for containers/serverless)
-	 * - API key (for simple applications)
-	 * - Omit to use Application Default Credentials (ADC) for local development
-	 *
-	 * @example '/path/to/service-account.json'
-	 * @example { client_email: '...', private_key: '...' }
-	 * @example { apiKey: 'AIza...' }
-	 * @see https://cloud.google.com/docs/authentication
-	 */
-	credentials?:
-		| string // Path to service account JSON file
-		| {
-				// Service account key object
-				client_email: string;
-				private_key: string;
-				project_id?: string;
-		  }
-		| {
-				// API key
-				apiKey: string;
-		  };
-
-	/**
-	 * Voice type: 'wavenet' (neural), 'standard', or 'studio' (premium)
-	 *
-	 * @default 'wavenet'
-	 * @note WaveNet: $16/1M chars, Standard: $4/1M chars, Studio: $16/1M chars
-	 */
-	voiceType?: "wavenet" | "standard" | "studio";
-
-	/**
-	 * Default voice name if not specified in synthesis requests
-	 *
-	 * @default 'en-US-Wavenet-A'
-	 * @example 'en-US-Wavenet-A', 'en-GB-Standard-B', 'es-ES-Studio-C'
-	 * @see https://cloud.google.com/text-to-speech/docs/voices
-	 */
-	defaultVoice?: string;
-
-	/**
-	 * Audio encoding format
-	 *
-	 * @default 'MP3'
-	 */
-	audioEncoding?: "MP3" | "LINEAR16" | "OGG_OPUS";
-
-	/**
-	 * Enable detailed logging for debugging
-	 *
-	 * @default false
-	 */
-	enableLogging?: boolean;
-}
-
-/**
- * Google Cloud Text-to-Speech Server Provider
- *
- * Provides high-quality neural text-to-speech with precise word-level timing
- * through Google Cloud Text-to-Speech API.
- *
- * Features:
- * - Speech marks support via SSML mark injection (millisecond precision)
- * - WaveNet (neural), Standard, and Studio voice types
- * - 200+ voices across 50+ languages
- * - Full SSML support
- * - Single API call for audio + speech marks
- */
-export class GoogleCloudTTSProvider extends BaseTTSProvider {
-	readonly providerId = "google-cloud-tts";
-	readonly providerName = "Google Cloud Text-to-Speech";
-	readonly version = "1.0.0";
-
-	private client!: v1beta1.TextToSpeechClient;
-	private voiceType: "wavenet" | "standard" | "studio" = "wavenet";
-	private defaultVoice = "en-US-Wavenet-A";
-	private audioEncoding: "MP3" | "LINEAR16" | "OGG_OPUS" = "MP3";
-	private enableLogging = false;
-
-	/**
-	 * Initialize the Google Cloud TTS provider.
-	 *
-	 * This is FAST and lightweight - only validates config and creates the client.
-	 * Does NOT fetch voices or make test API calls.
-	 *
-	 * @param config - Google Cloud TTS configuration
-	 * @performance Completes in ~10-50ms
-	 */
-	async initialize(config: GoogleCloudTTSConfig): Promise<void> {
-		if (!config.projectId) {
-			throw new TTSError(
-				TTSErrorCode.INITIALIZATION_ERROR,
-				"Google Cloud project ID is required",
-				undefined,
-				this.providerId,
-			);
-		}
-
-		this.config = config;
-		this.voiceType = config.voiceType || "wavenet";
-		this.defaultVoice = config.defaultVoice || "en-US-Wavenet-A";
-		this.audioEncoding = config.audioEncoding || "MP3";
-		this.enableLogging = config.enableLogging || false;
-
-		try {
-			// Initialize Google Cloud TTS client
-			const clientConfig: any = {
-				projectId: config.projectId,
-			};
-
-			// Handle different credential types
-			if (config.credentials) {
-				if (typeof config.credentials === "string") {
-					// Path to service account JSON file
-					clientConfig.keyFilename = config.credentials;
-				} else if ("apiKey" in config.credentials) {
-					// API key authentication
-					clientConfig.apiKey = config.credentials.apiKey;
-				} else {
-					// Service account key object
-					clientConfig.credentials = config.credentials;
-				}
-			}
-			// Else: Use Application Default Credentials (ADC)
-
-			this.client = new v1beta1.TextToSpeechClient(clientConfig);
-			this.initialized = true;
-
-			if (this.enableLogging) {
-				console.log("[GoogleCloudTTS] Initialized successfully");
-			}
-		} catch (error) {
-			throw new TTSError(
-				TTSErrorCode.INITIALIZATION_ERROR,
-				`Failed to initialize Google Cloud TTS: ${error instanceof Error ? error.message : String(error)}`,
-				{ error },
-				this.providerId,
-			);
-		}
-	}
-
-	/**
-	 * Synthesize speech with Google Cloud TTS
-	 */
-	async synthesize(request: SynthesizeRequest): Promise<SynthesizeResponse> {
-		this.ensureInitialized();
-
-		const capabilities = this.getCapabilities();
-		this.validateRequest(request, capabilities);
-
-		const voice = request.voice || this.defaultVoice;
-		const startTime = Date.now();
-
-		try {
-			// Check if speech marks are requested
-			if (request.includeSpeechMarks !== false) {
-				// Use SSML marks injection for precise word timing
-				const result = await this.synthesizeWithSpeechMarks(request, voice);
-				const duration = (Date.now() - startTime) / 1000;
-
-				return {
-					audio: result.audio,
-					contentType: result.contentType,
-					speechMarks: result.speechMarks,
-					metadata: {
-						providerId: this.providerId,
-						voice,
-						duration,
-						charCount: request.text.length,
-						cached: false,
-						timestamp: new Date().toISOString(),
-					},
-				};
-			} else {
-				// Audio only (no speech marks)
-				const result = await this.synthesizeAudio(request, voice);
-				const duration = (Date.now() - startTime) / 1000;
-
-				return {
-					audio: result.audio,
-					contentType: result.contentType,
-					speechMarks: [],
-					metadata: {
-						providerId: this.providerId,
-						voice,
-						duration,
-						charCount: request.text.length,
-						cached: false,
-						timestamp: new Date().toISOString(),
-					},
-				};
-			}
-		} catch (error) {
-			throw this.mapGoogleErrorToTTSError(error);
-		}
-	}
-
-	/**
-	 * Synthesize audio stream only (no speech marks)
-	 */
-	private async synthesizeAudio(
-		request: SynthesizeRequest,
-		voice: string,
-	): Promise<{ audio: Buffer; contentType: string }> {
-		// Detect if text contains SSML tags
-		const isSsml = this.detectSSML(request.text);
-
-		if (isSsml && this.enableLogging) {
-			console.log("[GoogleCloudTTS] Detected SSML content");
-		}
-
-		// Parse voice name to extract language code
-		const languageCode = voice.split("-").slice(0, 2).join("-"); // e.g., "en-US" from "en-US-Wavenet-A"
-
-		// Map our audio encoding to Google's enum
-		const audioEncodingMap = {
-			MP3: "MP3" as const,
-			LINEAR16: "LINEAR16" as const,
-			OGG_OPUS: "OGG_OPUS" as const,
-		};
-
-		const [response] = await this.client.synthesizeSpeech({
-			input: isSsml ? { ssml: request.text } : { text: request.text },
-			voice: {
-				languageCode,
-				name: voice,
-			},
-			audioConfig: {
-				audioEncoding: audioEncodingMap[this.audioEncoding],
-				sampleRateHertz: request.sampleRate || 24000,
-			},
-		});
-
-		if (!response.audioContent) {
-			throw new Error("No audio content received from Google Cloud TTS");
-		}
-
-		// Convert Uint8Array to Buffer
-		const audioBuffer = Buffer.from(response.audioContent);
-
-		const contentTypeMap = {
-			MP3: "audio/mpeg",
-			LINEAR16: "audio/wav",
-			OGG_OPUS: "audio/ogg",
-		};
-
-		return {
-			audio: audioBuffer,
-			contentType: contentTypeMap[this.audioEncoding],
-		};
-	}
-
-	/**
-	 * Synthesize with speech marks using SSML mark injection
-	 */
-	private async synthesizeWithSpeechMarks(
-		request: SynthesizeRequest,
-		voice: string,
-	): Promise<{
-		audio: Buffer;
-		contentType: string;
-		speechMarks: SpeechMark[];
-	}> {
-		// Check if the text is already SSML
-		const isUserSSML = this.detectSSML(request.text);
-
-		// If user provided SSML, we need to inject marks within the existing SSML
-		// For simplicity in v1, we'll inject marks for plain text only
-		const { ssml, wordMap } = isUserSSML
-			? this.extractWordsFromSSML(request.text)
-			: this.injectSSMLMarks(request.text);
-
-		if (this.enableLogging) {
-			console.log(`[GoogleCloudTTS] Injected ${wordMap.length} SSML marks`);
-		}
-
-		// Parse voice name to extract language code
-		const languageCode = voice.split("-").slice(0, 2).join("-");
-
-		// Map our audio encoding to Google's enum
-		const audioEncodingMap = {
-			MP3: "MP3" as const,
-			LINEAR16: "LINEAR16" as const,
-			OGG_OPUS: "OGG_OPUS" as const,
-		};
-
-		// Single API call with timepoint tracking enabled
-		const responseArray = await this.client.synthesizeSpeech({
-			input: { ssml },
-			voice: {
-				languageCode,
-				name: voice,
-			},
-			audioConfig: {
-				audioEncoding: audioEncodingMap[this.audioEncoding],
-				sampleRateHertz: request.sampleRate || 24000,
-			},
-			enableTimePointing: [
-				protos.google.cloud.texttospeech.v1beta1.SynthesizeSpeechRequest
-					.TimepointType.SSML_MARK,
-			],
-		});
-		const response = responseArray[0];
-
-		if (!response.audioContent) {
-			throw new Error("No audio content received from Google Cloud TTS");
-		}
-
-		// Convert Uint8Array to Buffer
-		const audioBuffer = Buffer.from(response.audioContent);
-
-		const contentTypeMap = {
-			MP3: "audio/mpeg",
-			LINEAR16: "audio/wav",
-			OGG_OPUS: "audio/ogg",
-		};
-
-		// Extract speech marks from timepoints
-		const speechMarks = this.extractSpeechMarksFromTimepoints(
-			response.timepoints || [],
-			wordMap,
-		);
-
-		if (this.enableLogging) {
-			console.log(
-				`[GoogleCloudTTS] Extracted ${speechMarks.length} speech marks`,
-			);
-		}
-
-		return {
-			audio: audioBuffer,
-			contentType: contentTypeMap[this.audioEncoding],
-			speechMarks,
-		};
-	}
-
-	/**
-	 * Inject SSML marks before each word in plain text
-	 */
-	private injectSSMLMarks(text: string): {
-		ssml: string;
-		wordMap: Array<{
-			word: string;
-			start: number;
-			end: number;
-			markName: string;
-		}>;
-	} {
-		const words: Array<{
-			word: string;
-			start: number;
-			end: number;
-			markName: string;
-		}> = [];
-		const wordRegex = /\b[\w']+\b/g;
-		let match;
-		let markIndex = 0;
-
-		while ((match = wordRegex.exec(text)) !== null) {
-			const word = match[0];
-			const start = match.index;
-			const end = start + word.length;
-			const markName = `w${markIndex++}`;
-
-			words.push({ word, start, end, markName });
-		}
-
-		// Build SSML with marks
-		let ssml = "<speak>";
-		let lastEnd = 0;
-
-		for (const { word, start, end, markName } of words) {
-			// Add text before word (including whitespace and punctuation)
-			ssml += this.escapeSSML(text.slice(lastEnd, start));
-			// Add marked word
-			ssml += `<mark name="${markName}"/>${this.escapeSSML(word)}`;
-			lastEnd = end;
-		}
-
-		// Add remaining text
-		ssml += this.escapeSSML(text.slice(lastEnd)) + "</speak>";
-
-		return { ssml, wordMap: words };
-	}
-
-	/**
-	 * Extract words from existing SSML (simplified version for v1)
-	 */
-	private extractWordsFromSSML(ssmlText: string): {
-		ssml: string;
-		wordMap: Array<{
-			word: string;
-			start: number;
-			end: number;
-			markName: string;
-		}>;
-	} {
-		// For now, just strip SSML tags and inject marks
-		// More sophisticated SSML parsing can be added in future versions
-		const plainText = ssmlText
-			.replace(/<[^>]+>/g, " ") // Remove all tags
-			.replace(/\s+/g, " ") // Normalize whitespace
-			.trim();
-
-		return this.injectSSMLMarks(plainText);
-	}
-
-	/**
-	 * Escape special XML characters for SSML
-	 */
-	private escapeSSML(text: string): string {
-		return text
-			.replace(/&/g, "&amp;")
-			.replace(/</g, "&lt;")
-			.replace(/>/g, "&gt;")
-			.replace(/"/g, "&quot;")
-			.replace(/'/g, "&apos;");
-	}
-
-	/**
-	 * Extract speech marks from Google's timepoints
-	 */
-	private extractSpeechMarksFromTimepoints(
-		timepoints:
-			| protos.google.cloud.texttospeech.v1beta1.ITimepoint[]
-			| null
-			| undefined,
-		wordMap: Array<{
-			word: string;
-			start: number;
-			end: number;
-			markName: string;
-		}>,
-	): SpeechMark[] {
-		if (!timepoints || timepoints.length === 0) {
-			return [];
-		}
-
-		const speechMarks: SpeechMark[] = [];
-
-		for (const timepoint of timepoints) {
-			// Find corresponding word in our map
-			const wordInfo = wordMap.find((w) => w.markName === timepoint.markName);
-
-			if (
-				wordInfo &&
-				timepoint.timeSeconds !== undefined &&
-				timepoint.timeSeconds !== null
-			) {
-				speechMarks.push({
-					time: Math.round(timepoint.timeSeconds * 1000), // Convert to ms
-					type: "word",
-					start: wordInfo.start,
-					end: wordInfo.end,
-					value: wordInfo.word,
-				});
-			}
-		}
-
-		// Sort by time
-		return speechMarks.sort((a, b) => a.time - b.time);
-	}
-
-	/**
-	 * Detect if text contains SSML markup
-	 */
-	private detectSSML(text: string): boolean {
-		return (
-			text.includes("<speak") ||
-			text.includes("<prosody") ||
-			text.includes("<emphasis") ||
-			text.includes("<break") ||
-			text.includes("<phoneme") ||
-			text.includes("<say-as") ||
-			text.includes("<mark")
-		);
-	}
-
-	/**
-	 * Get available voices from Google Cloud TTS
-	 */
-	async getVoices(options?: GetVoicesOptions): Promise<Voice[]> {
-		this.ensureInitialized();
-
-		try {
-			const [response] = await this.client.listVoices({
-				languageCode: options?.language,
-			});
-
-			if (!response.voices) {
-				return [];
-			}
-
-			return response.voices
-				.map((voice) => this.mapGoogleVoiceToVoice(voice))
-				.filter((voice) => {
-					// Apply filters
-					if (options?.gender && voice.gender !== options.gender) {
-						return false;
-					}
-					if (options?.quality && voice.quality !== options.quality) {
-						return false;
-					}
-					return true;
-				});
-		} catch (error) {
-			throw new TTSError(
-				TTSErrorCode.PROVIDER_ERROR,
-				`Failed to get voices: ${error instanceof Error ? error.message : String(error)}`,
-				{ error },
-				this.providerId,
-			);
-		}
-	}
-
-	/**
-	 * Map Google Cloud voice to unified Voice interface
-	 */
-	private mapGoogleVoiceToVoice(
-		googleVoice: protos.google.cloud.texttospeech.v1beta1.IVoice,
-	): Voice {
-		const voiceName = googleVoice.name || "";
-
-		// Determine quality based on voice type
-		let quality: "standard" | "neural" | "premium" = "standard";
-		if (voiceName.includes("Wavenet")) {
-			quality = "neural";
-		} else if (voiceName.includes("Studio")) {
-			quality = "premium";
-		}
-
-		// Map SSML gender to our gender type
-		const genderMap: Record<string, "male" | "female" | "neutral"> = {
-			MALE: "male",
-			FEMALE: "female",
-			NEUTRAL: "neutral",
-		};
-		const gender = genderMap[googleVoice.ssmlGender || "NEUTRAL"] || "neutral";
-
-		return {
-			id: voiceName,
-			name: voiceName,
-			language: googleVoice.languageCodes?.[0] || "Unknown",
-			languageCode: googleVoice.languageCodes?.[0] || "",
-			gender,
-			quality,
-			supportedFeatures: {
-				ssml: true,
-				emotions: false, // Google doesn't have built-in emotions
-				styles: false, // Google doesn't have speaking styles
-			},
-			providerMetadata: {
-				naturalSampleRateHertz: googleVoice.naturalSampleRateHertz,
-				languageCodes: googleVoice.languageCodes,
-				ssmlGender: googleVoice.ssmlGender,
-			},
-		};
-	}
-
-	/**
-	 * Get Google Cloud TTS capabilities
-	 */
-	getCapabilities(): ServerProviderCapabilities {
-		return {
-			// W3C Standard features
-			standard: {
-				supportsSSML: true, // ✅ Full SSML 1.1 support
-				supportsPitch: true, // ✅ Via SSML <prosody pitch>
-				supportsRate: true, // ✅ Via SSML <prosody rate>
-				supportsVolume: false, // ❌ Not supported (handle client-side)
-				supportsMultipleVoices: true, // ✅ 200+ voices across 50+ languages
-				maxTextLength: 5000, // Google Cloud TTS limit per request
-			},
-
-			// Provider-specific extensions
-			extensions: {
-				supportsSpeechMarks: true, // ✅ Via SSML marks + timepoints
-				supportedFormats: ["mp3", "wav", "ogg"], // MP3, LINEAR16, OGG_OPUS
-				supportsSampleRate: true, // ✅ Configurable sample rate
-
-				// Google Cloud-specific features
-				providerSpecific: {
-					voiceTypes: ["standard", "wavenet", "studio"],
-					voicesCount: 200, // ~200+ voices available
-					languagesCount: 50, // 50+ languages supported
-					supportsAudioProfiles: true, // Audio device profiles
-					supportsEffects: false, // No built-in effects
-					supportsEmotions: false, // No emotion control
-					supportsStyles: false, // No speaking styles
-				},
-			},
-		};
-	}
-
-	/**
-	 * Map Google Cloud errors to TTSError codes
-	 */
-	private mapGoogleErrorToTTSError(error: any): TTSError {
-		const message = error.message || String(error);
-
-		// Check for specific Google Cloud error codes
-		if (error.code === 7) {
-			// PERMISSION_DENIED
-			return new TTSError(
-				TTSErrorCode.AUTHENTICATION_ERROR,
-				`Google Cloud authentication failed: ${message}`,
-				{ error },
-				this.providerId,
-			);
-		}
-
-		if (error.code === 8) {
-			// RESOURCE_EXHAUSTED
-			return new TTSError(
-				TTSErrorCode.RATE_LIMIT_EXCEEDED,
-				`Google Cloud rate limit exceeded: ${message}`,
-				{ error },
-				this.providerId,
-			);
-		}
-
-		if (error.code === 3) {
-			// INVALID_ARGUMENT
-			return new TTSError(
-				TTSErrorCode.INVALID_REQUEST,
-				`Invalid request to Google Cloud TTS: ${message}`,
-				{ error },
-				this.providerId,
-			);
-		}
-
-		// Default to provider error
-		return new TTSError(
-			TTSErrorCode.PROVIDER_ERROR,
-			`Google Cloud TTS error: ${message}`,
-			{ error },
-			this.providerId,
-		);
-	}
-
-	/**
-	 * Clean up Google Cloud TTS client
-	 */
-	async destroy(): Promise<void> {
-		if (this.client) {
-			await this.client.close();
-		}
-		await super.destroy();
-	}
-}

package/src/index.ts

@@ -1,7 +0,0 @@
-/**
- * Google Cloud Text-to-Speech server-side TTS provider
- * @module @pie-players/tts-server-google
- */
-
-export type { GoogleCloudTTSConfig } from "./GoogleCloudTTSProvider.js";
-export { GoogleCloudTTSProvider } from "./GoogleCloudTTSProvider.js";

package/tsconfig.json

@@ -1,9 +0,0 @@
-{
-	"extends": "../tts-server-core/tsconfig.json",
-	"compilerOptions": {
-		"outDir": "./dist",
-		"rootDir": "./src"
-	},
-	"include": ["src/**/*"],
-	"exclude": ["node_modules", "dist", "**/*.test.ts"]
-}