@mastra/voice-google 0.11.4 → 0.11.5-alpha.1

package/CHANGELOG.md

@@ -1,5 +1,23 @@
 # @mastra/voice-google
 
+## 0.11.5-alpha.1
+
+### Patch Changes
+
+- clean up console logs in monorepo ([#7926](https://github.com/mastra-ai/mastra/pull/7926))
+
+- Updated dependencies [[`197cbb2`](https://github.com/mastra-ai/mastra/commit/197cbb248fc8cb4bbf61bf70b770f1388b445df2), [`6590763`](https://github.com/mastra-ai/mastra/commit/65907630ef4bf4127067cecd1cb21b56f55d5f1b), [`c2eade3`](https://github.com/mastra-ai/mastra/commit/c2eade3508ef309662f065e5f340d7840295dd53), [`222965a`](https://github.com/mastra-ai/mastra/commit/222965a98ce8197b86673ec594244650b5960257), [`0324ceb`](https://github.com/mastra-ai/mastra/commit/0324ceb8af9d16c12a531f90e575f6aab797ac81), [`0f9d227`](https://github.com/mastra-ai/mastra/commit/0f9d227890a98db33865abbea39daf407cd55ef7), [`de056a0`](https://github.com/mastra-ai/mastra/commit/de056a02cbb43f6aa0380ab2150ea404af9ec0dd), [`c93532a`](https://github.com/mastra-ai/mastra/commit/c93532a340b80e4dd946d4c138d9381de5f70399), [`6cb1fcb`](https://github.com/mastra-ai/mastra/commit/6cb1fcbc8d0378ffed0d17784c96e68f30cb0272), [`2685a78`](https://github.com/mastra-ai/mastra/commit/2685a78f224b8b04e20d4fab5ac1adb638190071), [`239b5a4`](https://github.com/mastra-ai/mastra/commit/239b5a497aeae2e8b4d764f46217cfff2284788e)]:
+  - @mastra/core@0.17.0-alpha.6
+
+## 0.11.5-alpha.0
+
+### Patch Changes
+
+- Update peerdep of @mastra/core ([#7619](https://github.com/mastra-ai/mastra/pull/7619))
+
+- Updated dependencies [[`a1bb887`](https://github.com/mastra-ai/mastra/commit/a1bb887e8bfae44230f487648da72e96ef824561), [`a0f5f1c`](https://github.com/mastra-ai/mastra/commit/a0f5f1ca39c3c5c6d26202e9fcab986b4fe14568), [`b356f5f`](https://github.com/mastra-ai/mastra/commit/b356f5f7566cb3edb755d91f00b72fc1420b2a37), [`f5ce05f`](https://github.com/mastra-ai/mastra/commit/f5ce05f831d42c69559bf4c0fdb46ccb920fc3a3), [`9f6f30f`](https://github.com/mastra-ai/mastra/commit/9f6f30f04ec6648bbca798ea8aad59317c40d8db), [`d706fad`](https://github.com/mastra-ai/mastra/commit/d706fad6e6e4b72357b18d229ba38e6c913c0e70), [`5c3768f`](https://github.com/mastra-ai/mastra/commit/5c3768fa959454232ad76715c381f4aac00c6881), [`8a3f5e4`](https://github.com/mastra-ai/mastra/commit/8a3f5e4212ec36b302957deb4bd47005ab598382)]:
+  - @mastra/core@0.17.0-alpha.3
+
 ## 0.11.4
 
 ### Patch Changes

package/dist/index.cjs

@@ -141,9 +141,7 @@ var GoogleVoice = class extends voice.MastraVoice {
           content: buffer.toString("base64")
         }
       };
-      console.log(`BEFORE REQUEST`);
       const [response] = await this.speechClient.recognize(request);
-      console.log(`AFTER REQUEST`);
       if (!response.results || response.results.length === 0) {
         throw new Error("No transcription results returned");
       }

package/dist/index.cjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"names":["MastraVoice","TextToSpeechClient","SpeechClient","stream","PassThrough"],"mappings":";;;;;;;;AAiBA,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;AAAA,EAUR,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,cAAA,GAAiB,aAAA;AAEvB,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,aAAa,MAAA,IAAU;AAAA,OACjC;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,gBAAgB,MAAA,IAAU;AAAA,OACpC;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,MAAA,GAAS,aAAA,IAAiB,WAAA,EAAa,MAAA,IAAU,cAAA,EAAgB,MAAA;AACvE,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,MAAM,IAAI,KAAA;AAAA,QACR;AAAA,OACF;AAAA,IACF;AAEA,IAAA,IAAA,CAAK,SAAA,GAAY,IAAIC,+BAAA,CAAmB;AAAA,MACtC,MAAA,EAAQ,IAAA,CAAK,WAAA,EAAa,MAAA,IAAU;AAAA,KACrC,CAAA;AAED,IAAA,IAAA,CAAK,YAAA,GAAe,IAAIC,mBAAA,CAAa;AAAA,MACnC,MAAA,EAAQ,IAAA,CAAK,cAAA,EAAgB,MAAA,IAAU;AAAA,KACxC,CAAA;AAAA,EACH;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,OAAA,CAAQ,IAAI,CAAA,cAAA,CAAgB,CAAA;AAC5B,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,YAAA,CAAa,UAAU,OAAwD,CAAA;AAC7G,MAAA,OAAA,CAAQ,IAAI,CAAA,aAAA,CAAe,CAAA;AAE3B,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 */\nexport interface GoogleModelConfig {\n  apiKey?: string;\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   * @throws {Error} If no API key is provided via config or environment variable\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 defaultSpeaker = DEFAULT_VOICE;\n\n    super({\n      speechModel: {\n        name: '',\n        apiKey: speechModel?.apiKey ?? defaultApiKey,\n      },\n      listeningModel: {\n        name: '',\n        apiKey: listeningModel?.apiKey ?? defaultApiKey,\n      },\n      speaker: speaker ?? defaultSpeaker,\n    });\n\n    const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;\n    if (!apiKey) {\n      throw new Error(\n        'Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor',\n      );\n    }\n\n    this.ttsClient = new TextToSpeechClient({\n      apiKey: this.speechModel?.apiKey || defaultApiKey,\n    });\n\n    this.speechClient = new SpeechClient({\n      apiKey: this.listeningModel?.apiKey || defaultApiKey,\n    });\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      console.log(`BEFORE REQUEST`);\n      const [response] = await this.speechClient.recognize(request as SpeechTypes.cloud.speech.v1.IRecognizeRequest);\n      console.log(`AFTER REQUEST`);\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"]}
+{"version":3,"sources":["../src/index.ts"],"names":["MastraVoice","TextToSpeechClient","SpeechClient","stream","PassThrough"],"mappings":";;;;;;;;AAiBA,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;AAAA,EAUR,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,cAAA,GAAiB,aAAA;AAEvB,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,aAAa,MAAA,IAAU;AAAA,OACjC;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,gBAAgB,MAAA,IAAU;AAAA,OACpC;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,MAAA,GAAS,aAAA,IAAiB,WAAA,EAAa,MAAA,IAAU,cAAA,EAAgB,MAAA;AACvE,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,MAAM,IAAI,KAAA;AAAA,QACR;AAAA,OACF;AAAA,IACF;AAEA,IAAA,IAAA,CAAK,SAAA,GAAY,IAAIC,+BAAA,CAAmB;AAAA,MACtC,MAAA,EAAQ,IAAA,CAAK,WAAA,EAAa,MAAA,IAAU;AAAA,KACrC,CAAA;AAED,IAAA,IAAA,CAAK,YAAA,GAAe,IAAIC,mBAAA,CAAa;AAAA,MACnC,MAAA,EAAQ,IAAA,CAAK,cAAA,EAAgB,MAAA,IAAU;AAAA,KACxC,CAAA;AAAA,EACH;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 */\nexport interface GoogleModelConfig {\n  apiKey?: string;\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   * @throws {Error} If no API key is provided via config or environment variable\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 defaultSpeaker = DEFAULT_VOICE;\n\n    super({\n      speechModel: {\n        name: '',\n        apiKey: speechModel?.apiKey ?? defaultApiKey,\n      },\n      listeningModel: {\n        name: '',\n        apiKey: listeningModel?.apiKey ?? defaultApiKey,\n      },\n      speaker: speaker ?? defaultSpeaker,\n    });\n\n    const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;\n    if (!apiKey) {\n      throw new Error(\n        'Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor',\n      );\n    }\n\n    this.ttsClient = new TextToSpeechClient({\n      apiKey: this.speechModel?.apiKey || defaultApiKey,\n    });\n\n    this.speechClient = new SpeechClient({\n      apiKey: this.listeningModel?.apiKey || defaultApiKey,\n    });\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.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":"AAGA,OAAO,KAAK,EAAE,MAAM,IAAI,WAAW,EAAE,MAAM,0CAA0C,CAAC;AAEtF,OAAO,KAAK,EAAE,MAAM,IAAI,iBAAiB,EAAE,MAAM,kDAAkD,CAAC;AACpG,OAAO,EAAE,WAAW,EAAE,MAAM,oBAAoB,CAAC;AAEjD;;;;GAIG;AACH,MAAM,WAAW,iBAAiB;IAChC,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAID;;;;GAIG;AACH,qBAAa,WAAY,SAAQ,WAAW;IAC1C,OAAO,CAAC,SAAS,CAAqB;IACtC,OAAO,CAAC,YAAY,CAAe;IAEnC;;;;;;;OAOG;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;IAgCN;;;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;CA+CnB"}
+{"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;;;;GAIG;AACH,MAAM,WAAW,iBAAiB;IAChC,MAAM,CAAC,EAAE,MAAM,CAAC;CACjB;AAID;;;;GAIG;AACH,qBAAa,WAAY,SAAQ,WAAW;IAC1C,OAAO,CAAC,SAAS,CAAqB;IACtC,OAAO,CAAC,YAAY,CAAe;IAEnC;;;;;;;OAOG;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;IAgCN;;;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

@@ -139,9 +139,7 @@ var GoogleVoice = class extends MastraVoice {
           content: buffer.toString("base64")
         }
       };
-      console.log(`BEFORE REQUEST`);
       const [response] = await this.speechClient.recognize(request);
-      console.log(`AFTER REQUEST`);
       if (!response.results || response.results.length === 0) {
         throw new Error("No transcription results returned");
       }

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"names":[],"mappings":";;;;;;AAiBA,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;AAAA,EAUR,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,cAAA,GAAiB,aAAA;AAEvB,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,aAAa,MAAA,IAAU;AAAA,OACjC;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,gBAAgB,MAAA,IAAU;AAAA,OACpC;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,MAAA,GAAS,aAAA,IAAiB,WAAA,EAAa,MAAA,IAAU,cAAA,EAAgB,MAAA;AACvE,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,MAAM,IAAI,KAAA;AAAA,QACR;AAAA,OACF;AAAA,IACF;AAEA,IAAA,IAAA,CAAK,SAAA,GAAY,IAAI,kBAAA,CAAmB;AAAA,MACtC,MAAA,EAAQ,IAAA,CAAK,WAAA,EAAa,MAAA,IAAU;AAAA,KACrC,CAAA;AAED,IAAA,IAAA,CAAK,YAAA,GAAe,IAAI,YAAA,CAAa;AAAA,MACnC,MAAA,EAAQ,IAAA,CAAK,cAAA,EAAgB,MAAA,IAAU;AAAA,KACxC,CAAA;AAAA,EACH;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,OAAA,CAAQ,IAAI,CAAA,cAAA,CAAgB,CAAA;AAC5B,MAAA,MAAM,CAAC,QAAQ,CAAA,GAAI,MAAM,IAAA,CAAK,YAAA,CAAa,UAAU,OAAwD,CAAA;AAC7G,MAAA,OAAA,CAAQ,IAAI,CAAA,aAAA,CAAe,CAAA;AAE3B,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 */\nexport interface GoogleModelConfig {\n  apiKey?: string;\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   * @throws {Error} If no API key is provided via config or environment variable\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 defaultSpeaker = DEFAULT_VOICE;\n\n    super({\n      speechModel: {\n        name: '',\n        apiKey: speechModel?.apiKey ?? defaultApiKey,\n      },\n      listeningModel: {\n        name: '',\n        apiKey: listeningModel?.apiKey ?? defaultApiKey,\n      },\n      speaker: speaker ?? defaultSpeaker,\n    });\n\n    const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;\n    if (!apiKey) {\n      throw new Error(\n        'Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor',\n      );\n    }\n\n    this.ttsClient = new TextToSpeechClient({\n      apiKey: this.speechModel?.apiKey || defaultApiKey,\n    });\n\n    this.speechClient = new SpeechClient({\n      apiKey: this.listeningModel?.apiKey || defaultApiKey,\n    });\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      console.log(`BEFORE REQUEST`);\n      const [response] = await this.speechClient.recognize(request as SpeechTypes.cloud.speech.v1.IRecognizeRequest);\n      console.log(`AFTER REQUEST`);\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"]}
+{"version":3,"sources":["../src/index.ts"],"names":[],"mappings":";;;;;;AAiBA,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;AAAA,EAUR,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,cAAA,GAAiB,aAAA;AAEvB,IAAA,KAAA,CAAM;AAAA,MACJ,WAAA,EAAa;AAAA,QACX,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,aAAa,MAAA,IAAU;AAAA,OACjC;AAAA,MACA,cAAA,EAAgB;AAAA,QACd,IAAA,EAAM,EAAA;AAAA,QACN,MAAA,EAAQ,gBAAgB,MAAA,IAAU;AAAA,OACpC;AAAA,MACA,SAAS,OAAA,IAAW;AAAA,KACrB,CAAA;AAED,IAAA,MAAM,MAAA,GAAS,aAAA,IAAiB,WAAA,EAAa,MAAA,IAAU,cAAA,EAAgB,MAAA;AACvE,IAAA,IAAI,CAAC,MAAA,EAAQ;AACX,MAAA,MAAM,IAAI,KAAA;AAAA,QACR;AAAA,OACF;AAAA,IACF;AAEA,IAAA,IAAA,CAAK,SAAA,GAAY,IAAI,kBAAA,CAAmB;AAAA,MACtC,MAAA,EAAQ,IAAA,CAAK,WAAA,EAAa,MAAA,IAAU;AAAA,KACrC,CAAA;AAED,IAAA,IAAA,CAAK,YAAA,GAAe,IAAI,YAAA,CAAa;AAAA,MACnC,MAAA,EAAQ,IAAA,CAAK,cAAA,EAAgB,MAAA,IAAU;AAAA,KACxC,CAAA;AAAA,EACH;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 */\nexport interface GoogleModelConfig {\n  apiKey?: string;\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   * @throws {Error} If no API key is provided via config or environment variable\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 defaultSpeaker = DEFAULT_VOICE;\n\n    super({\n      speechModel: {\n        name: '',\n        apiKey: speechModel?.apiKey ?? defaultApiKey,\n      },\n      listeningModel: {\n        name: '',\n        apiKey: listeningModel?.apiKey ?? defaultApiKey,\n      },\n      speaker: speaker ?? defaultSpeaker,\n    });\n\n    const apiKey = defaultApiKey || speechModel?.apiKey || listeningModel?.apiKey;\n    if (!apiKey) {\n      throw new Error(\n        'Google API key is not set, set GOOGLE_API_KEY environment variable or pass apiKey to constructor',\n      );\n    }\n\n    this.ttsClient = new TextToSpeechClient({\n      apiKey: this.speechModel?.apiKey || defaultApiKey,\n    });\n\n    this.speechClient = new SpeechClient({\n      apiKey: this.listeningModel?.apiKey || defaultApiKey,\n    });\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

@@ -1,6 +1,6 @@
 {
   "name": "@mastra/voice-google",
-  "version": "0.11.4",
+  "version": "0.11.5-alpha.1",
   "description": "Mastra Google voice integration",
   "type": "module",
   "files": [
@@ -29,16 +29,16 @@
   },
   "devDependencies": {
     "@types/node": "^20.19.0",
-    "eslint": "^9.30.1",
+    "eslint": "^9.35.0",
     "tsup": "^8.5.0",
     "typescript": "^5.8.3",
     "vitest": "^3.2.4",
-    "@internal/lint": "0.0.36",
-    "@mastra/core": "0.16.0",
-    "@internal/types-builder": "0.0.11"
+    "@internal/lint": "0.0.39",
+    "@internal/types-builder": "0.0.14",
+    "@mastra/core": "0.17.0-alpha.6"
   },
   "peerDependencies": {
-    "@mastra/core": ">=0.15.3-0 <0.17.0-0",
+    "@mastra/core": ">=0.17.0-0 <0.18.0-0",
     "zod": "^3.25.0 || ^4.0.0"
   },
   "homepage": "https://mastra.ai",