@mastra/voice-google 0.0.0-tsconfig-compile-20250703214351 → 0.0.0-unified-sidebar-20251010130811

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/LICENSE.md CHANGED
@@ -1,46 +1,15 @@
1
- # Elastic License 2.0 (ELv2)
1
+ # Apache License 2.0
2
2
 
3
- Copyright (c) 2025 Mastra AI, Inc.
3
+ Copyright (c) 2025 Kepler Software, Inc.
4
4
 
5
- **Acceptance**
6
- By using the software, you agree to all of the terms and conditions below.
5
+ Licensed under the Apache License, Version 2.0 (the "License");
6
+ you may not use this file except in compliance with the License.
7
+ You may obtain a copy of the License at
7
8
 
8
- **Copyright License**
9
- The licensor grants you a non-exclusive, royalty-free, worldwide, non-sublicensable, non-transferable license to use, copy, distribute, make available, and prepare derivative works of the software, in each case subject to the limitations and conditions below
9
+ http://www.apache.org/licenses/LICENSE-2.0
10
10
 
11
- **Limitations**
12
- You may not provide the software to third parties as a hosted or managed service, where the service provides users with access to any substantial set of the features or functionality of the software.
13
-
14
- You may not move, change, disable, or circumvent the license key functionality in the software, and you may not remove or obscure any functionality in the software that is protected by the license key.
15
-
16
- You may not alter, remove, or obscure any licensing, copyright, or other notices of the licensor in the software. Any use of the licensor’s trademarks is subject to applicable law.
17
-
18
- **Patents**
19
- The licensor grants you a license, under any patent claims the licensor can license, or becomes able to license, to make, have made, use, sell, offer for sale, import and have imported the software, in each case subject to the limitations and conditions in this license. This license does not cover any patent claims that you cause to be infringed by modifications or additions to the software. If you or your company make any written claim that the software infringes or contributes to infringement of any patent, your patent license for the software granted under these terms ends immediately. If your company makes such a claim, your patent license ends immediately for work on behalf of your company.
20
-
21
- **Notices**
22
- You must ensure that anyone who gets a copy of any part of the software from you also gets a copy of these terms.
23
-
24
- If you modify the software, you must include in any modified copies of the software prominent notices stating that you have modified the software.
25
-
26
- **No Other Rights**
27
- These terms do not imply any licenses other than those expressly granted in these terms.
28
-
29
- **Termination**
30
- If you use the software in violation of these terms, such use is not licensed, and your licenses will automatically terminate. If the licensor provides you with a notice of your violation, and you cease all violation of this license no later than 30 days after you receive that notice, your licenses will be reinstated retroactively. However, if you violate these terms after such reinstatement, any additional violation of these terms will cause your licenses to terminate automatically and permanently.
31
-
32
- **No Liability**
33
- As far as the law allows, the software comes as is, without any warranty or condition, and the licensor will not be liable to you for any damages arising out of these terms or the use or nature of the software, under any kind of legal claim.
34
-
35
- **Definitions**
36
- The _licensor_ is the entity offering these terms, and the _software_ is the software the licensor makes available under these terms, including any portion of it.
37
-
38
- _you_ refers to the individual or entity agreeing to these terms.
39
-
40
- _your company_ is any legal entity, sole proprietorship, or other kind of organization that you work for, plus all organizations that have control over, are under the control of, or are under common control with that organization. _control_ means ownership of substantially all the assets of an entity, or the power to direct its management and policies by vote, contract, or otherwise. Control can be direct or indirect.
41
-
42
- _your licenses_ are all the licenses granted to you for the software under these terms.
43
-
44
- _use_ means anything you do with the software requiring one of your licenses.
45
-
46
- _trademark_ means trademarks, service marks, and similar rights.
11
+ Unless required by applicable law or agreed to in writing, software
12
+ distributed under the License is distributed on an "AS IS" BASIS,
13
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ See the License for the specific language governing permissions and
15
+ limitations under the License.
package/README.md CHANGED
@@ -12,10 +12,12 @@ npm install @mastra/voice-google
12
12
 
13
13
  ## Configuration
14
14
 
15
- The module requires the following environment variable:
15
+ You can authenticate in one of the following ways:
16
16
 
17
17
  ```bash
18
18
  GOOGLE_API_KEY=your_api_key
19
+ # or provide a service account key picked up by ADC
20
+ GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
19
21
  ```
20
22
 
21
23
  ## Usage
@@ -26,10 +28,11 @@ import { GoogleVoice } from '@mastra/voice-google';
26
28
  // Initialize with configuration
27
29
  const voice = new GoogleVoice({
28
30
  speechModel: {
29
- apiKey: 'your-api-key', // Optional, can use GOOGLE_API_KEY env var
31
+ apiKey: 'your-api-key', // Optional, can rely on GOOGLE_API_KEY or ADC
32
+ keyFilename: '/path/to/service-account.json', // Optional, can rely on GOOGLE_APPLICATION_CREDENTIALS
30
33
  },
31
34
  listeningModel: {
32
- apiKey: 'your-api-key', // Optional, can use GOOGLE_API_KEY env var
35
+ keyFilename: '/path/to/service-account.json', // Optional, can rely on ADC
33
36
  },
34
37
  speaker: 'en-US-Standard-F', // Default voice
35
38
  });
package/dist/index.cjs CHANGED
@@ -6,6 +6,34 @@ var textToSpeech = require('@google-cloud/text-to-speech');
6
6
  var voice = require('@mastra/core/voice');
7
7
 
8
8
  // src/index.ts
9
+ var resolveAuthConfig = (modelConfig, fallback) => {
10
+ const resolved = {};
11
+ const apiKey = modelConfig?.apiKey ?? fallback.apiKey;
12
+ if (apiKey) {
13
+ resolved.apiKey = apiKey;
14
+ }
15
+ const keyFilename = modelConfig?.keyFilename ?? fallback.keyFilename;
16
+ if (keyFilename) {
17
+ resolved.keyFilename = keyFilename;
18
+ }
19
+ const credentials = modelConfig?.credentials ?? fallback.credentials;
20
+ if (credentials) {
21
+ resolved.credentials = credentials;
22
+ }
23
+ return resolved;
24
+ };
25
+ var buildAuthOptions = (config) => {
26
+ if (config.credentials) {
27
+ return { credentials: config.credentials };
28
+ }
29
+ if (config.keyFilename) {
30
+ return { keyFilename: config.keyFilename };
31
+ }
32
+ if (config.apiKey) {
33
+ return { apiKey: config.apiKey };
34
+ }
35
+ return {};
36
+ };
9
37
  var DEFAULT_VOICE = "en-US-Casual-K";
10
38
  var GoogleVoice = class extends voice.MastraVoice {
11
39
  ttsClient;
@@ -16,7 +44,6 @@ var GoogleVoice = class extends voice.MastraVoice {
16
44
  * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
17
45
  * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
18
46
  * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
19
- * @throws {Error} If no API key is provided via config or environment variable
20
47
  */
21
48
  constructor({
22
49
  listeningModel,
@@ -24,30 +51,30 @@ var GoogleVoice = class extends voice.MastraVoice {
24
51
  speaker
25
52
  } = {}) {
26
53
  const defaultApiKey = process.env.GOOGLE_API_KEY;
54
+ const defaultKeyFilename = process.env.GOOGLE_APPLICATION_CREDENTIALS;
27
55
  const defaultSpeaker = DEFAULT_VOICE;
56
+ const sharedFallback = {
57
+ apiKey: defaultApiKey ?? speechModel?.apiKey ?? listeningModel?.apiKey,
58
+ keyFilename: defaultKeyFilename ?? speechModel?.keyFilename ?? listeningModel?.keyFilename,
59
+ credentials: speechModel?.credentials ?? listeningModel?.credentials
60
+ };
61
+ const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback);
62
+ const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback);
28
63
  super({
29
64
  speechModel: {
30
65
  name: "",
31
- apiKey: speechModel?.apiKey ?? defaultApiKey
66
+ apiKey: speechAuthConfig.apiKey ?? defaultApiKey
32
67
  },
33
68
  listeningModel: {
34
69
  name: "",
35
- apiKey: listeningModel?.apiKey ?? defaultApiKey
70
+ apiKey: listeningAuthConfig.apiKey ?? defaultApiKey
36
71
  },
37
72
  speaker: speaker ?? defaultSpeaker
38
73
  });
39
- const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;
40
- if (!apiKey) {
41
- throw new Error(
42
- "Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor"
43
- );
44
- }
45
- this.ttsClient = new textToSpeech.TextToSpeechClient({
46
- apiKey: this.speechModel?.apiKey || defaultApiKey
47
- });
48
- this.speechClient = new speech.SpeechClient({
49
- apiKey: this.listeningModel?.apiKey || defaultApiKey
50
- });
74
+ const ttsOptions = buildAuthOptions(speechAuthConfig);
75
+ const speechOptions = buildAuthOptions(listeningAuthConfig);
76
+ this.ttsClient = new textToSpeech.TextToSpeechClient(ttsOptions);
77
+ this.speechClient = new speech.SpeechClient(speechOptions);
51
78
  }
52
79
  /**
53
80
  * Gets a list of available voices
@@ -141,9 +168,7 @@ var GoogleVoice = class extends voice.MastraVoice {
141
168
  content: buffer.toString("base64")
142
169
  }
143
170
  };
144
- console.log(`BEFORE REQUEST`);
145
171
  const [response] = await this.speechClient.recognize(request);
146
- console.log(`AFTER REQUEST`);
147
172
  if (!response.results || response.results.length === 0) {
148
173
  throw new Error("No transcription results returned");
149
174
  }
@@ -162,3 +187,5 @@ var GoogleVoice = class extends voice.MastraVoice {
162
187
  };
163
188
 
164
189
  exports.GoogleVoice = GoogleVoice;
190
+ //# sourceMappingURL=index.cjs.map
191
+ //# sourceMappingURL=index.cjs.map
@@ -0,0 +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,OAAO,IAAA,CAAK,OAAO,YAAY;AAC7B,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,KAAK,SAAA,CAAU,UAAA,CAAW,EAAE,YAAA,EAA4B,CAAA;AACjF,MAAA,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,QACb,SAAS,KAAA,CAAM,IAAA;AAAA,QACf,eAAe,KAAA,CAAM;AAAA,OACvB,CAAE,CAAA;AAAA,IACN,CAAA,EAAG,0BAA0B,CAAA,EAAE;AAAA,EACjC;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,OAAO,IAAA,CAAK,OAAO,YAAY;AAC7B,MAAA,MAAM,IAAA,GAAO,OAAO,KAAA,KAAU,QAAA,GAAW,QAAQ,MAAM,IAAA,CAAK,eAAe,KAAK,CAAA;AAEhF,MAAA,MAAM,OAAA,GAA4E;AAAA,QAChF,KAAA,EAAO,EAAE,IAAA,EAAK;AAAA,QACd,KAAA,EAAO;AAAA,UACL,IAAA,EAAM,OAAA,EAAS,OAAA,IAAW,IAAA,CAAK,OAAA;AAAA,UAC/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,SAC/F;AAAA,QACA,WAAA,EAAa,OAAA,EAAS,WAAA,IAAe,EAAE,eAAe,UAAA;AAAW,OACnE;AAEA,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,SAAA,CAAU,iBAAiB,OAAO,CAAA;AAEhE,MAAA,IAAI,CAAC,SAAS,YAAA,EAAc;AAC1B,QAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,MAC9C;AAEA,MAAA,IAAI,OAAO,QAAA,CAAS,YAAA,KAAiB,QAAA,EAAU;AAC7C,QAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,MAC9C;AAEA,MAAA,MAAMC,QAAA,GAAS,IAAIC,kBAAA,EAAY;AAC/B,MAAAD,QAAA,CAAO,GAAA,CAAI,MAAA,CAAO,IAAA,CAAK,QAAA,CAAS,YAAY,CAAC,CAAA;AAC7C,MAAA,OAAOA,QAAA;AAAA,IACT,CAAA,EAAG,oBAAoB,CAAA,EAAE;AAAA,EAC3B;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,OAAO,IAAA,CAAK,OAAO,YAAY;AAC7B,MAAA,MAAM,SAAmB,EAAC;AAC1B,MAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,QAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,UAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,QAChC,CAAA,MAAO;AACL,UAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,QACnB;AAAA,MACF;AACA,MAAA,MAAM,MAAA,GAAS,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAEnC,MAAA,IAAI,OAAA,GAAU;AAAA,QACZ,MAAA,EAAQ;AAAA,UACN,QAAA,EAAU,UAAA;AAAA,UACV,YAAA,EAAc,OAAA;AAAA,UACd,GAAG,OAAA,EAAS;AAAA,SACd;AAAA,QACA,KAAA,EAAO;AAAA,UACL,OAAA,EAAS,MAAA,CAAO,QAAA,CAAS,QAAQ;AAAA;AACnC,OACF;AACA,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,YAAA,CAAa,UAAU,OAAwD,CAAA;AAE7G,MAAA,IAAI,CAAC,QAAA,CAAS,OAAA,IAAW,QAAA,CAAS,OAAA,CAAQ,WAAW,CAAA,EAAG;AACtD,QAAA,MAAM,IAAI,MAAM,mCAAmC,CAAA;AAAA,MACrD;AAEA,MAAA,MAAM,aAAA,GAAgB,QAAA,CAAS,OAAA,CAC5B,GAAA,CAAI,CAAC,MAAA,KAAgB;AACpB,QAAA,IAAI,CAAC,MAAA,CAAO,YAAA,IAAgB,MAAA,CAAO,YAAA,CAAa,WAAW,CAAA,EAAG;AAC5D,UAAA,OAAO,EAAA;AAAA,QACT;AACA,QAAA,OAAO,MAAA,CAAO,YAAA,CAAa,CAAC,CAAA,CAAE,UAAA,IAAc,EAAA;AAAA,MAC9C,CAAC,CAAA,CACA,MAAA,CAAO,CAAC,IAAA,KAAiB,KAAK,MAAA,GAAS,CAAC,CAAA,CACxC,IAAA,CAAK,GAAG,CAAA;AAEX,MAAA,IAAI,CAAC,aAAA,EAAe;AAClB,QAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,MAC3D;AAEA,MAAA,OAAO,aAAA;AAAA,IACT,CAAA,EAAG,qBAAqB,CAAA,EAAE;AAAA,EAC5B;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 return this.traced(async () => {\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 }, 'voice.google.getSpeakers')();\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 return this.traced(async () => {\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 }, 'voice.google.speak')();\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 return this.traced(async () => {\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 }, 'voice.google.listen')();\n }\n}\n"]}
package/dist/index.d.ts CHANGED
@@ -1,2 +1,85 @@
1
- export { GoogleModelConfig } from './_tsup-dts-rollup.js';
2
- export { GoogleVoice } from './_tsup-dts-rollup.js';
1
+ import type { google as SpeechTypes } from '@google-cloud/speech/build/protos/protos';
2
+ import type { google as TextToSpeechTypes } from '@google-cloud/text-to-speech/build/protos/protos';
3
+ import { MastraVoice } from '@mastra/core/voice';
4
+ /**
5
+ * Configuration for Google Cloud Voice models
6
+ * @interface GoogleModelConfig
7
+ * @property {string} [apiKey] - Optional Google Cloud API key. If not provided, will use GOOGLE_API_KEY environment variable
8
+ * @property {string} [keyFilename] - Optional path to a service account key file. If not provided, will use GOOGLE_APPLICATION_CREDENTIALS environment variable
9
+ * @property {{ client_email?: string; private_key?: string }} [credentials] - Optional in-memory service account credentials
10
+ */
11
+ export interface GoogleModelConfig {
12
+ apiKey?: string;
13
+ keyFilename?: string;
14
+ credentials?: {
15
+ client_email?: string;
16
+ private_key?: string;
17
+ [key: string]: unknown;
18
+ };
19
+ }
20
+ /**
21
+ * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services
22
+ * @class GoogleVoice
23
+ * @extends MastraVoice
24
+ */
25
+ export declare class GoogleVoice extends MastraVoice {
26
+ private ttsClient;
27
+ private speechClient;
28
+ /**
29
+ * Creates an instance of GoogleVoice
30
+ * @param {Object} config - Configuration options
31
+ * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
32
+ * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
33
+ * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
34
+ */
35
+ constructor({ listeningModel, speechModel, speaker, }?: {
36
+ listeningModel?: GoogleModelConfig;
37
+ speechModel?: GoogleModelConfig;
38
+ speaker?: string;
39
+ });
40
+ /**
41
+ * Gets a list of available voices
42
+ * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.
43
+ */
44
+ getSpeakers({ languageCode }?: {
45
+ languageCode?: string;
46
+ }): Promise<{
47
+ voiceId: string;
48
+ languageCodes: string[];
49
+ }[]>;
50
+ private streamToString;
51
+ /**
52
+ * Converts text to speech
53
+ * @param {string | NodeJS.ReadableStream} input - Text or stream to convert to speech
54
+ * @param {Object} [options] - Speech synthesis options
55
+ * @param {string} [options.speaker] - Voice ID to use
56
+ * @param {string} [options.languageCode] - Language code for the voice
57
+ * @param {TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig']} [options.audioConfig] - Audio configuration options
58
+ * @returns {Promise<NodeJS.ReadableStream>} Stream of synthesized audio. Default encoding is LINEAR16.
59
+ */
60
+ speak(input: string | NodeJS.ReadableStream, options?: {
61
+ speaker?: string;
62
+ languageCode?: string;
63
+ audioConfig?: TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig'];
64
+ }): Promise<NodeJS.ReadableStream>;
65
+ /**
66
+ * Checks if listening capabilities are enabled.
67
+ *
68
+ * @returns {Promise<{ enabled: boolean }>}
69
+ */
70
+ getListener(): Promise<{
71
+ enabled: boolean;
72
+ }>;
73
+ /**
74
+ * Converts speech to text
75
+ * @param {NodeJS.ReadableStream} audioStream - Audio stream to transcribe. Default encoding is LINEAR16.
76
+ * @param {Object} [options] - Recognition options
77
+ * @param {SpeechTypes.cloud.speech.v1.IRecognitionConfig} [options.config] - Recognition configuration
78
+ * @returns {Promise<string>} Transcribed text
79
+ */
80
+ listen(audioStream: NodeJS.ReadableStream, options?: {
81
+ stream?: boolean;
82
+ config?: SpeechTypes.cloud.speech.v1.IRecognitionConfig;
83
+ }): Promise<string>;
84
+ }
85
+ //# sourceMappingURL=index.d.ts.map
@@ -0,0 +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;;;;YAY9D,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;IA6BjC;;;;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;CA6CnB"}
package/dist/index.js CHANGED
@@ -4,6 +4,34 @@ import { TextToSpeechClient } from '@google-cloud/text-to-speech';
4
4
  import { MastraVoice } from '@mastra/core/voice';
5
5
 
6
6
  // src/index.ts
7
+ var resolveAuthConfig = (modelConfig, fallback) => {
8
+ const resolved = {};
9
+ const apiKey = modelConfig?.apiKey ?? fallback.apiKey;
10
+ if (apiKey) {
11
+ resolved.apiKey = apiKey;
12
+ }
13
+ const keyFilename = modelConfig?.keyFilename ?? fallback.keyFilename;
14
+ if (keyFilename) {
15
+ resolved.keyFilename = keyFilename;
16
+ }
17
+ const credentials = modelConfig?.credentials ?? fallback.credentials;
18
+ if (credentials) {
19
+ resolved.credentials = credentials;
20
+ }
21
+ return resolved;
22
+ };
23
+ var buildAuthOptions = (config) => {
24
+ if (config.credentials) {
25
+ return { credentials: config.credentials };
26
+ }
27
+ if (config.keyFilename) {
28
+ return { keyFilename: config.keyFilename };
29
+ }
30
+ if (config.apiKey) {
31
+ return { apiKey: config.apiKey };
32
+ }
33
+ return {};
34
+ };
7
35
  var DEFAULT_VOICE = "en-US-Casual-K";
8
36
  var GoogleVoice = class extends MastraVoice {
9
37
  ttsClient;
@@ -14,7 +42,6 @@ var GoogleVoice = class extends MastraVoice {
14
42
  * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
15
43
  * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
16
44
  * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
17
- * @throws {Error} If no API key is provided via config or environment variable
18
45
  */
19
46
  constructor({
20
47
  listeningModel,
@@ -22,30 +49,30 @@ var GoogleVoice = class extends MastraVoice {
22
49
  speaker
23
50
  } = {}) {
24
51
  const defaultApiKey = process.env.GOOGLE_API_KEY;
52
+ const defaultKeyFilename = process.env.GOOGLE_APPLICATION_CREDENTIALS;
25
53
  const defaultSpeaker = DEFAULT_VOICE;
54
+ const sharedFallback = {
55
+ apiKey: defaultApiKey ?? speechModel?.apiKey ?? listeningModel?.apiKey,
56
+ keyFilename: defaultKeyFilename ?? speechModel?.keyFilename ?? listeningModel?.keyFilename,
57
+ credentials: speechModel?.credentials ?? listeningModel?.credentials
58
+ };
59
+ const speechAuthConfig = resolveAuthConfig(speechModel, sharedFallback);
60
+ const listeningAuthConfig = resolveAuthConfig(listeningModel, sharedFallback);
26
61
  super({
27
62
  speechModel: {
28
63
  name: "",
29
- apiKey: speechModel?.apiKey ?? defaultApiKey
64
+ apiKey: speechAuthConfig.apiKey ?? defaultApiKey
30
65
  },
31
66
  listeningModel: {
32
67
  name: "",
33
- apiKey: listeningModel?.apiKey ?? defaultApiKey
68
+ apiKey: listeningAuthConfig.apiKey ?? defaultApiKey
34
69
  },
35
70
  speaker: speaker ?? defaultSpeaker
36
71
  });
37
- const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;
38
- if (!apiKey) {
39
- throw new Error(
40
- "Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor"
41
- );
42
- }
43
- this.ttsClient = new TextToSpeechClient({
44
- apiKey: this.speechModel?.apiKey || defaultApiKey
45
- });
46
- this.speechClient = new SpeechClient({
47
- apiKey: this.listeningModel?.apiKey || defaultApiKey
48
- });
72
+ const ttsOptions = buildAuthOptions(speechAuthConfig);
73
+ const speechOptions = buildAuthOptions(listeningAuthConfig);
74
+ this.ttsClient = new TextToSpeechClient(ttsOptions);
75
+ this.speechClient = new SpeechClient(speechOptions);
49
76
  }
50
77
  /**
51
78
  * Gets a list of available voices
@@ -139,9 +166,7 @@ var GoogleVoice = class extends MastraVoice {
139
166
  content: buffer.toString("base64")
140
167
  }
141
168
  };
142
- console.log(`BEFORE REQUEST`);
143
169
  const [response] = await this.speechClient.recognize(request);
144
- console.log(`AFTER REQUEST`);
145
170
  if (!response.results || response.results.length === 0) {
146
171
  throw new Error("No transcription results returned");
147
172
  }
@@ -160,3 +185,5 @@ var GoogleVoice = class extends MastraVoice {
160
185
  };
161
186
 
162
187
  export { GoogleVoice };
188
+ //# sourceMappingURL=index.js.map
189
+ //# sourceMappingURL=index.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"sources":["../src/index.ts"],"names":[],"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,cAA0B,WAAA,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,IAAI,kBAAA,CAAmB,UAAU,CAAA;AAElD,IAAA,IAAA,CAAK,YAAA,GAAe,IAAI,YAAA,CAAa,aAAa,CAAA;AAAA,EACpD;AAAA;AAAA;AAAA;AAAA;AAAA,EAMA,MAAM,WAAA,CAAY,EAAE,eAAe,OAAA,EAAQ,GAA+B,EAAC,EAAG;AAC5E,IAAA,OAAO,IAAA,CAAK,OAAO,YAAY;AAC7B,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,KAAK,SAAA,CAAU,UAAA,CAAW,EAAE,YAAA,EAA4B,CAAA;AACjF,MAAA,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,QACb,SAAS,KAAA,CAAM,IAAA;AAAA,QACf,eAAe,KAAA,CAAM;AAAA,OACvB,CAAE,CAAA;AAAA,IACN,CAAA,EAAG,0BAA0B,CAAA,EAAE;AAAA,EACjC;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,OAAO,IAAA,CAAK,OAAO,YAAY;AAC7B,MAAA,MAAM,IAAA,GAAO,OAAO,KAAA,KAAU,QAAA,GAAW,QAAQ,MAAM,IAAA,CAAK,eAAe,KAAK,CAAA;AAEhF,MAAA,MAAM,OAAA,GAA4E;AAAA,QAChF,KAAA,EAAO,EAAE,IAAA,EAAK;AAAA,QACd,KAAA,EAAO;AAAA,UACL,IAAA,EAAM,OAAA,EAAS,OAAA,IAAW,IAAA,CAAK,OAAA;AAAA,UAC/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,SAC/F;AAAA,QACA,WAAA,EAAa,OAAA,EAAS,WAAA,IAAe,EAAE,eAAe,UAAA;AAAW,OACnE;AAEA,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,SAAA,CAAU,iBAAiB,OAAO,CAAA;AAEhE,MAAA,IAAI,CAAC,SAAS,YAAA,EAAc;AAC1B,QAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,MAC9C;AAEA,MAAA,IAAI,OAAO,QAAA,CAAS,YAAA,KAAiB,QAAA,EAAU;AAC7C,QAAA,MAAM,IAAI,MAAM,4BAA4B,CAAA;AAAA,MAC9C;AAEA,MAAA,MAAM,MAAA,GAAS,IAAI,WAAA,EAAY;AAC/B,MAAA,MAAA,CAAO,GAAA,CAAI,MAAA,CAAO,IAAA,CAAK,QAAA,CAAS,YAAY,CAAC,CAAA;AAC7C,MAAA,OAAO,MAAA;AAAA,IACT,CAAA,EAAG,oBAAoB,CAAA,EAAE;AAAA,EAC3B;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,OAAO,IAAA,CAAK,OAAO,YAAY;AAC7B,MAAA,MAAM,SAAmB,EAAC;AAC1B,MAAA,WAAA,MAAiB,SAAS,WAAA,EAAa;AACrC,QAAA,IAAI,OAAO,UAAU,QAAA,EAAU;AAC7B,UAAA,MAAA,CAAO,IAAA,CAAK,MAAA,CAAO,IAAA,CAAK,KAAK,CAAC,CAAA;AAAA,QAChC,CAAA,MAAO;AACL,UAAA,MAAA,CAAO,KAAK,KAAK,CAAA;AAAA,QACnB;AAAA,MACF;AACA,MAAA,MAAM,MAAA,GAAS,MAAA,CAAO,MAAA,CAAO,MAAM,CAAA;AAEnC,MAAA,IAAI,OAAA,GAAU;AAAA,QACZ,MAAA,EAAQ;AAAA,UACN,QAAA,EAAU,UAAA;AAAA,UACV,YAAA,EAAc,OAAA;AAAA,UACd,GAAG,OAAA,EAAS;AAAA,SACd;AAAA,QACA,KAAA,EAAO;AAAA,UACL,OAAA,EAAS,MAAA,CAAO,QAAA,CAAS,QAAQ;AAAA;AACnC,OACF;AACA,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,YAAA,CAAa,UAAU,OAAwD,CAAA;AAE7G,MAAA,IAAI,CAAC,QAAA,CAAS,OAAA,IAAW,QAAA,CAAS,OAAA,CAAQ,WAAW,CAAA,EAAG;AACtD,QAAA,MAAM,IAAI,MAAM,mCAAmC,CAAA;AAAA,MACrD;AAEA,MAAA,MAAM,aAAA,GAAgB,QAAA,CAAS,OAAA,CAC5B,GAAA,CAAI,CAAC,MAAA,KAAgB;AACpB,QAAA,IAAI,CAAC,MAAA,CAAO,YAAA,IAAgB,MAAA,CAAO,YAAA,CAAa,WAAW,CAAA,EAAG;AAC5D,UAAA,OAAO,EAAA;AAAA,QACT;AACA,QAAA,OAAO,MAAA,CAAO,YAAA,CAAa,CAAC,CAAA,CAAE,UAAA,IAAc,EAAA;AAAA,MAC9C,CAAC,CAAA,CACA,MAAA,CAAO,CAAC,IAAA,KAAiB,KAAK,MAAA,GAAS,CAAC,CAAA,CACxC,IAAA,CAAK,GAAG,CAAA;AAEX,MAAA,IAAI,CAAC,aAAA,EAAe;AAClB,QAAA,MAAM,IAAI,MAAM,yCAAyC,CAAA;AAAA,MAC3D;AAEA,MAAA,OAAO,aAAA;AAAA,IACT,CAAA,EAAG,qBAAqB,CAAA,EAAE;AAAA,EAC5B;AACF","file":"index.js","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 return this.traced(async () => {\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 }, 'voice.google.getSpeakers')();\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 return this.traced(async () => {\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 }, 'voice.google.speak')();\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 return this.traced(async () => {\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 }, 'voice.google.listen')();\n }\n}\n"]}
package/package.json CHANGED
@@ -1,10 +1,11 @@
1
1
  {
2
2
  "name": "@mastra/voice-google",
3
- "version": "0.0.0-tsconfig-compile-20250703214351",
3
+ "version": "0.0.0-unified-sidebar-20251010130811",
4
4
  "description": "Mastra Google voice integration",
5
5
  "type": "module",
6
6
  "files": [
7
- "dist"
7
+ "dist",
8
+ "CHANGELOG.md"
8
9
  ],
9
10
  "main": "dist/index.js",
10
11
  "types": "dist/index.d.ts",
@@ -15,33 +16,43 @@
15
16
  "default": "./dist/index.js"
16
17
  },
17
18
  "require": {
18
- "types": "./dist/index.d.cts",
19
+ "types": "./dist/index.d.ts",
19
20
  "default": "./dist/index.cjs"
20
21
  }
21
22
  },
22
23
  "./package.json": "./package.json"
23
24
  },
24
- "license": "Elastic-2.0",
25
+ "license": "Apache-2.0",
25
26
  "dependencies": {
26
27
  "@google-cloud/speech": "^6.7.1",
27
- "@google-cloud/text-to-speech": "^6.1.0",
28
- "zod": "^3.25.67"
28
+ "@google-cloud/text-to-speech": "^6.3.0"
29
29
  },
30
30
  "devDependencies": {
31
31
  "@types/node": "^20.19.0",
32
- "eslint": "^9.29.0",
32
+ "eslint": "^9.36.0",
33
33
  "tsup": "^8.5.0",
34
34
  "typescript": "^5.8.3",
35
35
  "vitest": "^3.2.4",
36
- "@internal/lint": "0.0.0-tsconfig-compile-20250703214351",
37
- "@mastra/core": "0.0.0-tsconfig-compile-20250703214351"
36
+ "@internal/lint": "0.0.0-unified-sidebar-20251010130811",
37
+ "@internal/types-builder": "0.0.0-unified-sidebar-20251010130811",
38
+ "@mastra/core": "0.0.0-unified-sidebar-20251010130811"
38
39
  },
39
40
  "peerDependencies": {
40
- "@mastra/core": "0.0.0-tsconfig-compile-20250703214351"
41
+ "zod": "^3.25.0 || ^4.0.0",
42
+ "@mastra/core": "0.0.0-unified-sidebar-20251010130811"
43
+ },
44
+ "homepage": "https://mastra.ai",
45
+ "repository": {
46
+ "type": "git",
47
+ "url": "git+https://github.com/mastra-ai/mastra.git",
48
+ "directory": "voice/google"
49
+ },
50
+ "bugs": {
51
+ "url": "https://github.com/mastra-ai/mastra/issues"
41
52
  },
42
53
  "scripts": {
43
- "build": "tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake=smallest --splitting",
44
- "build:watch": "pnpm build --watch",
54
+ "build": "tsup --silent --config tsup.config.ts",
55
+ "build:watch": "tsup --watch --silent --config tsup.config.ts",
45
56
  "test": "vitest run",
46
57
  "lint": "eslint ."
47
58
  }
@@ -1,81 +0,0 @@
1
- import type { google } from '@google-cloud/text-to-speech/build/protos/protos';
2
- import type { google as google_2 } from '@google-cloud/speech/build/protos/protos';
3
- import { MastraVoice } from '@mastra/core/voice';
4
-
5
- /**
6
- * Configuration for Google Cloud Voice models
7
- * @interface GoogleModelConfig
8
- * @property {string} [apiKey] - Optional Google Cloud API key. If not provided, will use GOOGLE_API_KEY environment variable
9
- */
10
- export declare interface GoogleModelConfig {
11
- apiKey?: string;
12
- }
13
-
14
- /**
15
- * GoogleVoice class provides Text-to-Speech and Speech-to-Text capabilities using Google Cloud services
16
- * @class GoogleVoice
17
- * @extends MastraVoice
18
- */
19
- export declare class GoogleVoice extends MastraVoice {
20
- private ttsClient;
21
- private speechClient;
22
- /**
23
- * Creates an instance of GoogleVoice
24
- * @param {Object} config - Configuration options
25
- * @param {GoogleModelConfig} [config.speechModel] - Configuration for speech synthesis
26
- * @param {GoogleModelConfig} [config.listeningModel] - Configuration for speech recognition
27
- * @param {string} [config.speaker] - Default voice ID to use for speech synthesis
28
- * @throws {Error} If no API key is provided via config or environment variable
29
- */
30
- constructor({ listeningModel, speechModel, speaker, }?: {
31
- listeningModel?: GoogleModelConfig;
32
- speechModel?: GoogleModelConfig;
33
- speaker?: string;
34
- });
35
- /**
36
- * Gets a list of available voices
37
- * @returns {Promise<Array<{voiceId: string, languageCodes: string[]}>>} List of available voices and their supported languages. Default language is en-US.
38
- */
39
- getSpeakers({ languageCode }?: {
40
- languageCode?: string;
41
- }): Promise<{
42
- voiceId: string;
43
- languageCodes: string[];
44
- }[]>;
45
- private streamToString;
46
- /**
47
- * Converts text to speech
48
- * @param {string | NodeJS.ReadableStream} input - Text or stream to convert to speech
49
- * @param {Object} [options] - Speech synthesis options
50
- * @param {string} [options.speaker] - Voice ID to use
51
- * @param {string} [options.languageCode] - Language code for the voice
52
- * @param {TextToSpeechTypes.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig']} [options.audioConfig] - Audio configuration options
53
- * @returns {Promise<NodeJS.ReadableStream>} Stream of synthesized audio. Default encoding is LINEAR16.
54
- */
55
- speak(input: string | NodeJS.ReadableStream, options?: {
56
- speaker?: string;
57
- languageCode?: string;
58
- audioConfig?: google.cloud.texttospeech.v1.ISynthesizeSpeechRequest['audioConfig'];
59
- }): Promise<NodeJS.ReadableStream>;
60
- /**
61
- * Checks if listening capabilities are enabled.
62
- *
63
- * @returns {Promise<{ enabled: boolean }>}
64
- */
65
- getListener(): Promise<{
66
- enabled: boolean;
67
- }>;
68
- /**
69
- * Converts speech to text
70
- * @param {NodeJS.ReadableStream} audioStream - Audio stream to transcribe. Default encoding is LINEAR16.
71
- * @param {Object} [options] - Recognition options
72
- * @param {SpeechTypes.cloud.speech.v1.IRecognitionConfig} [options.config] - Recognition configuration
73
- * @returns {Promise<string>} Transcribed text
74
- */
75
- listen(audioStream: NodeJS.ReadableStream, options?: {
76
- stream?: boolean;
77
- config?: google_2.cloud.speech.v1.IRecognitionConfig;
78
- }): Promise<string>;
79
- }
80
-
81
- export { }