@mastra/voice-elevenlabs 0.1.3-alpha.9 → 0.1.3

package/dist/index.cjs

@@ -63,7 +63,11 @@ var ElevenLabsVoice = class extends voice.MastraVoice {
   async streamToString(stream) {
     const chunks = [];
     for await (const chunk of stream) {
-      chunks.push(Buffer.from(chunk));
+      if (typeof chunk === "string") {
+        chunks.push(Buffer.from(chunk));
+      } else {
+        chunks.push(chunk);
+      }
     }
     return Buffer.concat(chunks).toString("utf-8");
   }
@@ -117,7 +121,11 @@ var ElevenLabsVoice = class extends voice.MastraVoice {
     const res = await this.traced(async () => {
       const chunks = [];
       for await (const chunk of input) {
-        chunks.push(Buffer.from(chunk));
+        if (typeof chunk === "string") {
+          chunks.push(Buffer.from(chunk));
+        } else {
+          chunks.push(chunk);
+        }
       }
       const buffer$1 = Buffer.concat(chunks);
       const { language_code, tag_audio_events, num_speakers, filetype, ...requestOptions } = options || {};

package/dist/index.js

@@ -61,7 +61,11 @@ var ElevenLabsVoice = class extends MastraVoice {
   async streamToString(stream) {
     const chunks = [];
     for await (const chunk of stream) {
-      chunks.push(Buffer.from(chunk));
+      if (typeof chunk === "string") {
+        chunks.push(Buffer.from(chunk));
+      } else {
+        chunks.push(chunk);
+      }
     }
     return Buffer.concat(chunks).toString("utf-8");
   }
@@ -115,7 +119,11 @@ var ElevenLabsVoice = class extends MastraVoice {
     const res = await this.traced(async () => {
       const chunks = [];
       for await (const chunk of input) {
-        chunks.push(Buffer.from(chunk));
+        if (typeof chunk === "string") {
+          chunks.push(Buffer.from(chunk));
+        } else {
+          chunks.push(chunk);
+        }
       }
       const buffer = Buffer.concat(chunks);
       const { language_code, tag_audio_events, num_speakers, filetype, ...requestOptions } = options || {};

package/package.json

@@ -1,8 +1,11 @@
 {
   "name": "@mastra/voice-elevenlabs",
-  "version": "0.1.3-alpha.9",
+  "version": "0.1.3",
   "description": "Mastra ElevenLabs voice integration",
   "type": "module",
+  "files": [
+    "dist"
+  ],
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
   "exports": {
@@ -19,21 +22,21 @@
     "./package.json": "./package.json"
   },
   "dependencies": {
-    "elevenlabs": "^1.50.2",
-    "zod": "^3.24.1",
-    "@mastra/core": "^0.5.0-alpha.9"
+    "elevenlabs": "^1.54.0",
+    "zod": "^3.24.2",
+    "@mastra/core": "^0.5.0"
   },
   "devDependencies": {
-    "@microsoft/api-extractor": "^7.49.2",
-    "@types/node": "^22.13.1",
-    "tsup": "^8.0.1",
-    "typescript": "^5.7.3",
-    "vitest": "^2.1.8",
-    "eslint": "^9.20.1",
-    "@internal/lint": "0.0.0"
+    "@microsoft/api-extractor": "^7.52.1",
+    "@types/node": "^22.13.10",
+    "eslint": "^9.22.0",
+    "tsup": "^8.4.0",
+    "typescript": "^5.8.2",
+    "vitest": "^2.1.9",
+    "@internal/lint": "0.0.1"
   },
   "scripts": {
-    "build": "tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake",
+    "build": "tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake=smallest --splitting",
     "build:watch": "tsup build --watch",
     "test": "vitest run",
     "lint": "eslint ."

package/.turbo/turbo-build.log

@@ -1,23 +0,0 @@
-
-> @mastra/voice-elevenlabs@0.1.3-alpha.9 build /home/runner/work/mastra/mastra/voice/elevenlabs
-> tsup src/index.ts --format esm,cjs --experimental-dts --clean --treeshake
-
-CLI Building entry: src/index.ts
-CLI Using tsconfig: tsconfig.json
-CLI tsup v8.3.6
-TSC Build start
-TSC ⚡️ Build success in 8109ms
-DTS Build start
-CLI Target: es2022
-Analysis will use the bundled TypeScript version 5.7.3
-Writing package typings: /home/runner/work/mastra/mastra/voice/elevenlabs/dist/_tsup-dts-rollup.d.ts
-Analysis will use the bundled TypeScript version 5.7.3
-Writing package typings: /home/runner/work/mastra/mastra/voice/elevenlabs/dist/_tsup-dts-rollup.d.cts
-DTS ⚡️ Build success in 8752ms
-CLI Cleaning output folder
-ESM Build start
-CJS Build start
-ESM dist/index.js 5.00 KB
-ESM ⚡️ Build success in 324ms
-CJS dist/index.cjs 5.04 KB
-CJS ⚡️ Build success in 323ms

package/CHANGELOG.md

@@ -1,234 +0,0 @@
-# @mastra/voice-elevenlabs
-
-## 0.1.3-alpha.9
-
-### Patch Changes
-
-- Updated dependencies [e9fbac5]
-- Updated dependencies [1e8bcbc]
-- Updated dependencies [aeb5e36]
-- Updated dependencies [f2301de]
-  - @mastra/core@0.5.0-alpha.9
-
-## 0.1.3-alpha.8
-
-### Patch Changes
-
-- Updated dependencies [506f1d5]
-  - @mastra/core@0.5.0-alpha.8
-
-## 0.1.3-alpha.7
-
-### Patch Changes
-
-- Updated dependencies [ee667a2]
-  - @mastra/core@0.5.0-alpha.7
-
-## 0.1.3-alpha.6
-
-### Patch Changes
-
-- Updated dependencies [f6678e4]
-  - @mastra/core@0.5.0-alpha.6
-
-## 0.1.3-alpha.5
-
-### Patch Changes
-
-- Updated dependencies [22643eb]
-- Updated dependencies [6feb23f]
-- Updated dependencies [f2d6727]
-- Updated dependencies [301e4ee]
-- Updated dependencies [dfbe4e9]
-- Updated dependencies [9e81f35]
-- Updated dependencies [caefaa2]
-- Updated dependencies [c151ae6]
-- Updated dependencies [52e0418]
-- Updated dependencies [03236ec]
-- Updated dependencies [3764e71]
-- Updated dependencies [df982db]
-- Updated dependencies [0461849]
-- Updated dependencies [2259379]
-- Updated dependencies [358f069]
-  - @mastra/core@0.5.0-alpha.5
-
-## 0.1.3-alpha.4
-
-### Patch Changes
-
-- Updated dependencies [d79aedf]
-  - @mastra/core@0.5.0-alpha.4
-
-## 0.1.3-alpha.3
-
-### Patch Changes
-
-- Updated dependencies [3d0e290]
-  - @mastra/core@0.5.0-alpha.3
-
-## 0.1.3-alpha.2
-
-### Patch Changes
-
-- Updated dependencies [02ffb7b]
-  - @mastra/core@0.5.0-alpha.2
-
-## 0.1.3-alpha.1
-
-### Patch Changes
-
-- Updated dependencies [dab255b]
-  - @mastra/core@0.5.0-alpha.1
-
-## 0.1.3-alpha.0
-
-### Patch Changes
-
-- Updated dependencies [59df7b6]
-- Updated dependencies [29f3a82]
-- Updated dependencies [59df7b6]
-- Updated dependencies [c139344]
-  - @mastra/core@0.5.0-alpha.0
-
-## 0.1.2
-
-### Patch Changes
-
-- Updated dependencies [1da20e7]
-  - @mastra/core@0.4.4
-
-## 0.1.2-alpha.0
-
-### Patch Changes
-
-- Updated dependencies [1da20e7]
-  - @mastra/core@0.4.4-alpha.0
-
-## 0.1.1
-
-### Patch Changes
-
-- bb4f447: Add support for commonjs
-- 705d69b: Add STT for ElevenlabsVoice
-- Updated dependencies [0d185b1]
-- Updated dependencies [ed55f1d]
-- Updated dependencies [06aa827]
-- Updated dependencies [0fd78ac]
-- Updated dependencies [2512a93]
-- Updated dependencies [e62de74]
-- Updated dependencies [0d25b75]
-- Updated dependencies [fd14a3f]
-- Updated dependencies [8d13b14]
-- Updated dependencies [3f369a2]
-- Updated dependencies [3ee4831]
-- Updated dependencies [4d4e1e1]
-- Updated dependencies [bb4f447]
-- Updated dependencies [108793c]
-- Updated dependencies [5f28f44]
-- Updated dependencies [dabecf4]
-  - @mastra/core@0.4.3
-
-## 0.1.1-alpha.4
-
-### Patch Changes
-
-- Updated dependencies [dabecf4]
-  - @mastra/core@0.4.3-alpha.4
-
-## 0.1.1-alpha.3
-
-### Patch Changes
-
-- bb4f447: Add support for commonjs
-- Updated dependencies [0fd78ac]
-- Updated dependencies [0d25b75]
-- Updated dependencies [fd14a3f]
-- Updated dependencies [3f369a2]
-- Updated dependencies [4d4e1e1]
-- Updated dependencies [bb4f447]
-  - @mastra/core@0.4.3-alpha.3
-
-## 0.1.1-alpha.2
-
-### Patch Changes
-
-- Updated dependencies [2512a93]
-- Updated dependencies [e62de74]
-  - @mastra/core@0.4.3-alpha.2
-
-## 0.1.1-alpha.1
-
-### Patch Changes
-
-- 705d69b: Add STT for ElevenlabsVoice
-- Updated dependencies [0d185b1]
-- Updated dependencies [ed55f1d]
-- Updated dependencies [8d13b14]
-- Updated dependencies [3ee4831]
-- Updated dependencies [108793c]
-- Updated dependencies [5f28f44]
-  - @mastra/core@0.4.3-alpha.1
-
-## 0.1.1-alpha.0
-
-### Patch Changes
-
-- Updated dependencies [06aa827]
-  - @mastra/core@0.4.3-alpha.0
-
-## 0.1.0
-
-### Patch Changes
-
-- f626fbb: deprecate @mastra/speech-deepgram for @mastra/voice-deepgram
-- Updated dependencies [7fceae1]
-- Updated dependencies [8d94c3e]
-- Updated dependencies [99dcdb5]
-- Updated dependencies [6cb63e0]
-- Updated dependencies [f626fbb]
-- Updated dependencies [e752340]
-- Updated dependencies [eb91535]
-  - @mastra/core@0.4.2
-
-## 0.1.0-alpha.4
-
-### Patch Changes
-
-- Updated dependencies [8d94c3e]
-- Updated dependencies [99dcdb5]
-- Updated dependencies [e752340]
-- Updated dependencies [eb91535]
-  - @mastra/core@0.4.2-alpha.2
-
-## 0.1.0-alpha.3
-
-### Patch Changes
-
-- Updated dependencies [6cb63e0]
-  - @mastra/core@0.4.2-alpha.1
-
-## 0.1.0-alpha.2
-
-### Patch Changes
-
-- f626fbb: deprecate @mastra/speech-deepgram for @mastra/voice-deepgram
-- Updated dependencies [7fceae1]
-- Updated dependencies [f626fbb]
-  - @mastra/core@0.4.2-alpha.0
-
-## 0.1.0 (2024-XX-XX)
-
-This package replaces the deprecated @mastra/speech-elevenlabs package. All functionality has been migrated to this new package with a more consistent naming scheme.
-
-### Changes from @mastra/speech-elevenlabs
-
-- Package renamed from @mastra/speech-elevenlabs to @mastra/voice-elevenlabs
-- API changes:
-  - `ElevenLabsTTS` class renamed to `ElevenLabsVoice`
-  - `generate()` method renamed to `speak()`
-  - `voices()` method renamed to `getSpeakers()`
-  - Constructor configuration simplified
-- All core functionality remains the same
-- Import paths should be updated from '@mastra/speech-elevenlabs' to '@mastra/voice-elevenlabs'
-
-For a complete history of changes prior to the rename, please see the changelog of the original package.

package/eslint.config.js

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

package/src/index.test.ts

@@ -1,141 +0,0 @@
-import { createWriteStream, writeFileSync, mkdirSync, createReadStream } from 'fs';
-import path from 'path';
-import { describe, expect, it, beforeAll } from 'vitest';
-
-import { ElevenLabsVoice } from './index.js';
-
-describe('ElevenLabsVoice Integration Tests', () => {
-  let voice: ElevenLabsVoice;
-  const outputDir = path.join(process.cwd(), 'test-outputs');
-
-  beforeAll(() => {
-    try {
-      mkdirSync(outputDir, { recursive: true });
-    } catch (err) {
-      console.log('Directory already exists: ', err);
-    }
-
-    voice = new ElevenLabsVoice({
-      speechModel: {
-        name: 'eleven_multilingual_v2',
-      },
-    });
-  });
-
-  describe('getSpeakers', () => {
-    it('should list available speakers', async () => {
-      const speakers = await voice.getSpeakers();
-      console.log(speakers);
-      expect(speakers.length).toBeGreaterThan(0);
-      expect(speakers[0]).toHaveProperty('voiceId');
-      expect(speakers[0]).toHaveProperty('name');
-      expect(speakers[0]).toHaveProperty('language');
-      expect(speakers[0]).toHaveProperty('gender');
-    });
-  });
-
-  describe('speak', () => {
-    it('should speak with default values', async () => {
-      const defaultVoice = new ElevenLabsVoice();
-      const audioStream = await defaultVoice.speak('Hello World, how are you?');
-
-      const outputPath = path.join(outputDir, 'elevenlabs-speech-test-default.mp3');
-      const fileStream = createWriteStream(outputPath);
-      const chunks: Buffer[] = [];
-
-      audioStream.on('data', (chunk: Buffer) => chunks.push(chunk));
-      audioStream.pipe(fileStream);
-      writeFileSync(outputPath, Buffer.concat(chunks));
-    }, 10000);
-
-    it('should generate audio from text and save to file', async () => {
-      const speakers = await voice.getSpeakers();
-      const speaker = speakers[0].voiceId;
-
-      const audioStream = await voice.speak('Hello World', { speaker });
-
-      return new Promise((resolve, reject) => {
-        const outputPath = path.join(outputDir, 'elevenlabs-speech-test.mp3');
-        const fileStream = createWriteStream(outputPath);
-        const chunks: Buffer[] = [];
-
-        audioStream.on('data', (chunk: Buffer) => chunks.push(chunk));
-        audioStream.pipe(fileStream);
-
-        fileStream.on('finish', () => {
-          expect(chunks.length).toBeGreaterThan(0);
-          resolve(undefined);
-        });
-
-        audioStream.on('error', reject);
-        fileStream.on('error', reject);
-      });
-    }, 10000);
-
-    it('should work with different speaker', async () => {
-      const speakers = await voice.getSpeakers();
-      const speaker = speakers[1]?.voiceId;
-
-      const audioStream = await voice.speak('Test with different speaker', { speaker });
-
-      return new Promise((resolve, reject) => {
-        const outputPath = path.join(outputDir, 'elevenlabs-speech-test-params.mp3');
-        const fileStream = createWriteStream(outputPath);
-        const chunks: Buffer[] = [];
-
-        audioStream.on('data', (chunk: Buffer) => chunks.push(chunk));
-        audioStream.pipe(fileStream);
-
-        fileStream.on('finish', () => {
-          expect(chunks.length).toBeGreaterThan(0);
-          resolve(undefined);
-        });
-
-        audioStream.on('error', reject);
-        fileStream.on('error', reject);
-      });
-    }, 10000);
-  });
-
-  describe('listen', () => {
-    it('should convert audio to text', async () => {
-      const outputPath = path.join(outputDir, 'elevenlabs-speech-test-params.mp3');
-      const audio = createReadStream(outputPath);
-      const result = await voice.listen(audio);
-
-      if (typeof result !== 'string') {
-        return expect(result).toBeInstanceOf(String);
-      }
-
-      expect(typeof result).toBe('string');
-      expect(result.length).toBeGreaterThan(0);
-    });
-
-    it('should handle API errors gracefully', async () => {
-      // Create a voice instance with an invalid API key to force an error
-      const invalidVoice = new ElevenLabsVoice({
-        listeningModel: {
-          name: 'eleven_multilingual_v2',
-          apiKey: 'invalid-api-key',
-        },
-      });
-
-      const outputPath = path.join(outputDir, 'elevenlabs-speech-test-params.mp3');
-      const audio = createReadStream(outputPath);
-
-      // The API call should fail with an authentication error
-      await expect(invalidVoice.listen(audio)).rejects.toThrow();
-    });
-
-    it('should handle invalid audio input', async () => {
-      // Create a path to a non-existent file
-      const nonExistentPath = path.join(outputDir, 'non-existent-file.mp3');
-
-      // Attempting to create a read stream from a non-existent file should throw
-      await expect(async () => {
-        const audio = createReadStream(nonExistentPath);
-        await voice.listen(audio);
-      }).rejects.toThrow();
-    });
-  });
-});

package/src/index.ts

@@ -1,185 +0,0 @@
-import { File } from 'node:buffer';
-import { MastraVoice } from '@mastra/core/voice';
-import { ElevenLabsClient } from 'elevenlabs';
-
-type ElevenLabsModel =
-  | 'eleven_multilingual_v2'
-  | 'eleven_flash_v2_5'
-  | 'eleven_flash_v2'
-  | 'eleven_multilingual_sts_v2'
-  | 'eleven_english_sts_v2'
-  | 'scribe_v1';
-
-interface ElevenLabsVoiceConfig {
-  name?: ElevenLabsModel;
-  apiKey?: string;
-}
-
-interface SpeechToTextOptions {
-  language_code?: string;
-  tag_audio_events?: boolean;
-  num_speakers?: number;
-  filetype?: string;
-}
-
-interface RequestOptions {
-  timeoutInSeconds?: number;
-  maxRetries?: number;
-  abortSignal?: AbortSignal;
-  apiKey?: string | undefined;
-  headers?: Record<string, string>;
-}
-
-// Combined options type
-type ElevenLabsListenOptions = SpeechToTextOptions & RequestOptions;
-
-export class ElevenLabsVoice extends MastraVoice {
-  private client: ElevenLabsClient;
-
-  /**
-   * Creates an instance of the ElevenLabsVoice class.
-   *
-   * @param {Object} options - The options for the voice configuration.
-   * @param {ElevenLabsVoiceConfig} [options.speechModel] - The configuration for the speech model, including the model name and API key.
-   * @param {string} [options.speaker] - The ID of the speaker to use. If not provided, a default speaker will be used.
-   *
-   * @throws {Error} If the ELEVENLABS_API_KEY is not set in the environment variables.
-   */
-  constructor({
-    speechModel,
-    listeningModel,
-    speaker,
-  }: { speechModel?: ElevenLabsVoiceConfig; listeningModel?: ElevenLabsVoiceConfig; speaker?: string } = {}) {
-    const apiKey = speechModel?.apiKey ?? process.env.ELEVENLABS_API_KEY;
-    super({
-      speechModel: {
-        name: speechModel?.name ?? 'eleven_multilingual_v2',
-        apiKey: speechModel?.apiKey,
-      },
-      listeningModel: {
-        name: listeningModel?.name ?? 'scribe_v1',
-        apiKey: listeningModel?.apiKey,
-      },
-      speaker,
-    });
-
-    if (!apiKey) {
-      throw new Error('ELEVENLABS_API_KEY is not set');
-    }
-
-    this.client = new ElevenLabsClient({
-      apiKey,
-    });
-
-    this.speaker = speaker || '9BWtsMINqrJLrRacOk9x'; // Aria is the default speaker
-  }
-
-  /**
-   * Retrieves a list of available speakers from the Eleven Labs API.
-   * Each speaker includes their ID, name, language, and gender.
-   *
-   * @returns {Promise<Array<{ voiceId: string, name: string, language: string, gender: string }>>}
-   * A promise that resolves to an array of speaker objects.
-   */
-  async getSpeakers() {
-    const res = await this.traced(async () => {
-      const voices = await this.client.voices.getAll();
-      return (
-        voices?.voices?.map(voice => ({
-          voiceId: voice.voice_id,
-          name: voice.name,
-          language: voice.labels?.language || 'en',
-          gender: voice.labels?.gender || 'neutral',
-        })) ?? []
-      );
-    }, 'voice.elevenlabs.voices')();
-
-    return res;
-  }
-
-  private async streamToString(stream: NodeJS.ReadableStream): Promise<string> {
-    const chunks: Buffer[] = [];
-    for await (const chunk of stream) {
-      chunks.push(Buffer.from(chunk));
-    }
-    return Buffer.concat(chunks).toString('utf-8');
-  }
-
-  /**
-   * Converts text or audio input into speech using the Eleven Labs API.
-   *
-   * @param {string | NodeJS.ReadableStream} input - The text to be converted to speech or a stream containing audio data.
-   * @param {Object} [options] - Optional parameters for the speech generation.
-   * @param {string} [options.speaker] - The ID of the speaker to use for the speech. If not provided, the default speaker will be used.
-   *
-   * @returns {Promise<NodeJS.ReadableStream>} A promise that resolves to a readable stream of the generated speech.
-   *
-   * @throws {Error} If no speaker is specified or if no speech model is set.
-   */
-  async speak(input: string | NodeJS.ReadableStream, options?: { speaker?: string }): Promise<NodeJS.ReadableStream> {
-    const speaker = options?.speaker || this.speaker;
-    if (!speaker) {
-      throw new Error('No speaker specified');
-    }
-
-    if (!this.speechModel?.name) {
-      throw new Error('No speech model specified');
-    }
-    const text = typeof input === 'string' ? input : await this.streamToString(input);
-    const res = await this.traced(async () => {
-      return await this.client.generate({
-        text,
-        voice: speaker,
-        model_id: this.speechModel?.name as ElevenLabsModel,
-        stream: true,
-      });
-    }, 'voice.elevenlabs.speak')();
-
-    return res;
-  }
-
-  /**
-   * Converts audio input to text using ElevenLabs Speech-to-Text API.
-   *
-   * @param input - A readable stream containing the audio data to transcribe
-   * @param options - Configuration options for the transcription
-   * @param options.language_code - ISO language code (e.g., 'en', 'fr', 'es')
-   * @param options.tag_audio_events - Whether to tag audio events like [MUSIC], [LAUGHTER], etc.
-   * @param options.num_speakers - Number of speakers to detect in the audio
-   * @param options.filetype - Audio file format (e.g., 'mp3', 'wav', 'ogg')
-   * @param options.timeoutInSeconds - Request timeout in seconds
-   * @param options.maxRetries - Maximum number of retry attempts
-   * @param options.abortSignal - Signal to abort the request
-   *
-   * @returns A Promise that resolves to the transcribed text
-   *
-   */
-  async listen(input: NodeJS.ReadableStream, options?: ElevenLabsListenOptions): Promise<string> {
-    const res = await this.traced(async () => {
-      const chunks: Buffer[] = [];
-      for await (const chunk of input) {
-        chunks.push(Buffer.from(chunk));
-      }
-      const buffer = Buffer.concat(chunks);
-
-      const { language_code, tag_audio_events, num_speakers, filetype, ...requestOptions } = options || {};
-
-      const file = new File([buffer], `audio.${filetype || 'mp3'}`);
-
-      const transcription = await this.client.speechToText.convert(
-        {
-          file: file,
-          model_id: this.listeningModel?.name as ElevenLabsModel,
-          language_code,
-          tag_audio_events,
-          num_speakers,
-        },
-        requestOptions,
-      );
-
-      return transcription.text;
-    }, 'voice.elevenlabs.listen')();
-
-    return res;
-  }
-}

package/tsconfig.json

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

package/vitest.config.ts

@@ -1,8 +0,0 @@
-import { defineConfig } from 'vitest/config';
-
-export default defineConfig({
-  test: {
-    globals: true,
-    include: ['src/**/*.test.ts'],
-  },
-});