@ai-sdk/elevenlabs 2.0.10 → 2.0.12

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # @ai-sdk/elevenlabs
 
+## 2.0.12
+
+### Patch Changes
+
+- Updated dependencies [462ad00]
+  - @ai-sdk/provider-utils@4.0.10
+
+## 2.0.11
+
+### Patch Changes
+
+- 4de5a1d: chore: excluded tests from src folder in npm package
+- Updated dependencies [4de5a1d]
+  - @ai-sdk/provider@3.0.5
+  - @ai-sdk/provider-utils@4.0.9
+
 ## 2.0.10
 
 ### Patch Changes

package/dist/index.js

@@ -364,7 +364,7 @@ var ElevenLabsSpeechModel = class {
 };
 
 // src/version.ts
-var VERSION = true ? "2.0.10" : "0.0.0-test";
+var VERSION = true ? "2.0.12" : "0.0.0-test";
 
 // src/elevenlabs-provider.ts
 function createElevenLabs(options = {}) {

package/dist/index.mjs

@@ -353,7 +353,7 @@ var ElevenLabsSpeechModel = class {
 };
 
 // src/version.ts
-var VERSION = true ? "2.0.10" : "0.0.0-test";
+var VERSION = true ? "2.0.12" : "0.0.0-test";
 
 // src/elevenlabs-provider.ts
 function createElevenLabs(options = {}) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/elevenlabs",
-  "version": "2.0.10",
+  "version": "2.0.12",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -10,6 +10,10 @@
     "dist/**/*",
     "docs/**/*",
     "src",
+    "!src/**/*.test.ts",
+    "!src/**/*.test-d.ts",
+    "!src/**/__snapshots__",
+    "!src/**/__fixtures__",
     "CHANGELOG.md",
     "README.md"
   ],
@@ -25,15 +29,15 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/provider": "3.0.4",
-    "@ai-sdk/provider-utils": "4.0.8"
+    "@ai-sdk/provider": "3.0.5",
+    "@ai-sdk/provider-utils": "4.0.10"
   },
   "devDependencies": {
     "@types/node": "20.17.24",
     "tsup": "^8",
     "typescript": "5.6.3",
     "zod": "3.25.76",
-    "@ai-sdk/test-server": "1.0.2",
+    "@ai-sdk/test-server": "1.0.3",
     "@vercel/ai-tsconfig": "0.0.0"
   },
   "peerDependencies": {

package/src/elevenlabs-error.test.ts

@@ -1,34 +0,0 @@
-import { safeParseJSON } from '@ai-sdk/provider-utils';
-import { elevenlabsErrorDataSchema } from './elevenlabs-error';
-import { describe, it, expect } from 'vitest';
-
-describe('elevenlabsErrorDataSchema', () => {
-  it('should parse ElevenLabs resource exhausted error', async () => {
-    const error = `
-{"error":{"message":"{\\n  \\"error\\": {\\n    \\"code\\": 429,\\n    \\"message\\": \\"Resource has been exhausted (e.g. check quota).\\",\\n    \\"status\\": \\"RESOURCE_EXHAUSTED\\"\\n  }\\n}\\n","code":429}}
-`;
-
-    const result = await safeParseJSON({
-      text: error,
-      schema: elevenlabsErrorDataSchema,
-    });
-
-    expect(result).toStrictEqual({
-      success: true,
-      value: {
-        error: {
-          message:
-            '{\n  "error": {\n    "code": 429,\n    "message": "Resource has been exhausted (e.g. check quota).",\n    "status": "RESOURCE_EXHAUSTED"\n  }\n}\n',
-          code: 429,
-        },
-      },
-      rawValue: {
-        error: {
-          message:
-            '{\n  "error": {\n    "code": 429,\n    "message": "Resource has been exhausted (e.g. check quota).",\n    "status": "RESOURCE_EXHAUSTED"\n  }\n}\n',
-          code: 429,
-        },
-      },
-    });
-  });
-});

package/src/elevenlabs-speech-model.test.ts

@@ -1,179 +0,0 @@
-import { createTestServer } from '@ai-sdk/test-server/with-vitest';
-import { describe, expect, it, vi } from 'vitest';
-import { createElevenLabs } from './elevenlabs-provider';
-
-vi.mock('./version', () => ({
-  VERSION: '0.0.0-test',
-}));
-
-const provider = createElevenLabs({ apiKey: 'test-api-key' });
-const model = provider.speech('eleven_multilingual_v2');
-
-const server = createTestServer({
-  'https://api.elevenlabs.io/v1/text-to-speech/*': {},
-});
-
-describe('ElevenLabsSpeechModel', () => {
-  function prepareAudioResponse({
-    headers,
-    format = 'mp3',
-  }: {
-    headers?: Record<string, string>;
-    format?: string;
-  } = {}) {
-    const audioBuffer = new Uint8Array(100); // Mock audio data
-    server.urls['https://api.elevenlabs.io/v1/text-to-speech/*'].response = {
-      type: 'binary',
-      headers: {
-        'content-type': `audio/${format}`,
-        ...headers,
-      },
-      body: Buffer.from(audioBuffer),
-    };
-    return audioBuffer;
-  }
-
-  describe('doGenerate', () => {
-    it('should generate speech with required parameters', async () => {
-      prepareAudioResponse();
-
-      await model.doGenerate({
-        text: 'Hello, world!',
-        voice: 'test-voice-id',
-      });
-
-      expect(await server.calls[0].requestBodyJson).toMatchObject({
-        text: 'Hello, world!',
-        model_id: 'eleven_multilingual_v2',
-      });
-
-      // Check output_format is in query params
-      expect(server.calls[0].requestUrl).toContain(
-        'output_format=mp3_44100_128',
-      );
-    });
-
-    it('should handle custom output format', async () => {
-      prepareAudioResponse();
-
-      await model.doGenerate({
-        text: 'Hello, world!',
-        voice: 'test-voice-id',
-        outputFormat: 'pcm_44100',
-      });
-
-      expect(await server.calls[0].requestBodyJson).toMatchObject({
-        text: 'Hello, world!',
-        model_id: 'eleven_multilingual_v2',
-      });
-
-      // Check output_format is in query params
-      expect(server.calls[0].requestUrl).toContain('output_format=pcm_44100');
-    });
-
-    it('should handle language parameter', async () => {
-      prepareAudioResponse();
-
-      await model.doGenerate({
-        text: 'Hola, mundo!',
-        voice: 'test-voice-id',
-        language: 'es',
-      });
-
-      expect(await server.calls[0].requestBodyJson).toMatchObject({
-        text: 'Hola, mundo!',
-        model_id: 'eleven_multilingual_v2',
-        language_code: 'es',
-      });
-
-      // Check output_format is in query params
-      expect(server.calls[0].requestUrl).toContain(
-        'output_format=mp3_44100_128',
-      );
-    });
-
-    it('should handle speed parameter in voice settings', async () => {
-      prepareAudioResponse();
-
-      await model.doGenerate({
-        text: 'Hello, world!',
-        voice: 'test-voice-id',
-        speed: 1.5,
-      });
-
-      expect(await server.calls[0].requestBodyJson).toMatchObject({
-        text: 'Hello, world!',
-        model_id: 'eleven_multilingual_v2',
-        voice_settings: {
-          speed: 1.5,
-        },
-      });
-    });
-
-    it('should warn about unsupported instructions parameter', async () => {
-      prepareAudioResponse();
-
-      const result = await model.doGenerate({
-        text: 'Hello, world!',
-        voice: 'test-voice-id',
-        instructions: 'Speak slowly',
-      });
-
-      expect(result.warnings).toMatchInlineSnapshot(`
-        [
-          {
-            "details": "ElevenLabs speech models do not support instructions. Instructions parameter was ignored.",
-            "feature": "instructions",
-            "type": "unsupported",
-          },
-        ]
-      `);
-    });
-
-    it('should pass provider-specific options', async () => {
-      prepareAudioResponse();
-
-      await model.doGenerate({
-        text: 'Hello, world!',
-        voice: 'test-voice-id',
-        providerOptions: {
-          elevenlabs: {
-            voiceSettings: {
-              stability: 0.5,
-              similarityBoost: 0.75,
-            },
-            seed: 123,
-          },
-        },
-      });
-
-      expect(await server.calls[0].requestBodyJson).toMatchObject({
-        text: 'Hello, world!',
-        model_id: 'eleven_multilingual_v2',
-        voice_settings: {
-          stability: 0.5,
-          similarity_boost: 0.75,
-        },
-        seed: 123,
-      });
-
-      // Check output_format is in query params
-      expect(server.calls[0].requestUrl).toContain(
-        'output_format=mp3_44100_128',
-      );
-    });
-
-    it('should include user-agent header', async () => {
-      prepareAudioResponse();
-
-      await model.doGenerate({
-        text: 'Hello, world!',
-        voice: 'test-voice-id',
-      });
-
-      expect(server.calls[0].requestUserAgent).toContain(
-        `ai-sdk/elevenlabs/0.0.0-test`,
-      );
-    });
-  });
-});

package/src/elevenlabs-transcription-model.test.ts

@@ -1,389 +0,0 @@
-import { createTestServer } from '@ai-sdk/test-server/with-vitest';
-import { ElevenLabsTranscriptionModel } from './elevenlabs-transcription-model';
-import { createElevenLabs } from './elevenlabs-provider';
-import { readFile } from 'node:fs/promises';
-import path from 'node:path';
-import { describe, it, expect, vi } from 'vitest';
-
-vi.mock('./version', () => ({
-  VERSION: '0.0.0-test',
-}));
-
-const audioData = await readFile(path.join(__dirname, 'transcript-test.mp3'));
-const provider = createElevenLabs({ apiKey: 'test-api-key' });
-const model = provider.transcription('scribe_v1');
-
-const server = createTestServer({
-  'https://api.elevenlabs.io/v1/speech-to-text': {},
-});
-
-describe('doGenerate', () => {
-  function prepareJsonResponse({
-    headers,
-  }: {
-    headers?: Record<string, string>;
-  } = {}) {
-    server.urls['https://api.elevenlabs.io/v1/speech-to-text'].response = {
-      type: 'json-value',
-      headers,
-      body: {
-        language_code: 'en',
-        language_probability: 0.98,
-        text: 'Hello world!',
-        words: [
-          {
-            text: 'Hello',
-            type: 'word',
-            start: 0,
-            end: 0.5,
-            speaker_id: 'speaker_1',
-            characters: [
-              {
-                text: 'text',
-                start: 0,
-                end: 0.1,
-              },
-            ],
-          },
-          {
-            text: ' ',
-            type: 'spacing',
-            start: 0.5,
-            end: 0.5,
-            speaker_id: 'speaker_1',
-            characters: [
-              {
-                text: 'text',
-                start: 0,
-                end: 0.1,
-              },
-            ],
-          },
-          {
-            text: 'world!',
-            type: 'word',
-            start: 0.5,
-            end: 1.2,
-            speaker_id: 'speaker_1',
-            characters: [
-              {
-                text: 'text',
-                start: 0,
-                end: 0.1,
-              },
-            ],
-          },
-        ],
-        additional_formats: [
-          {
-            requested_format: 'requested_format',
-            file_extension: 'file_extension',
-            content_type: 'content_type',
-            is_base64_encoded: true,
-            content: 'content',
-          },
-        ],
-      },
-    };
-  }
-
-  it('should pass the model', async () => {
-    prepareJsonResponse();
-
-    await model.doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-    });
-
-    expect(await server.calls[0].requestBodyMultipart).toMatchObject({
-      model_id: 'scribe_v1',
-    });
-  });
-
-  it('should pass headers', async () => {
-    prepareJsonResponse();
-
-    const provider = createElevenLabs({
-      apiKey: 'test-api-key',
-      headers: {
-        'Custom-Provider-Header': 'provider-header-value',
-      },
-    });
-
-    await provider.transcription('scribe_v1').doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-      headers: {
-        'Custom-Request-Header': 'request-header-value',
-      },
-    });
-
-    expect(server.calls[0].requestHeaders).toMatchObject({
-      'xi-api-key': 'test-api-key',
-      'content-type': expect.stringMatching(
-        /^multipart\/form-data; boundary=----formdata-undici-\d+$/,
-      ),
-      'custom-provider-header': 'provider-header-value',
-      'custom-request-header': 'request-header-value',
-    });
-    expect(server.calls[0].requestUserAgent).toContain(
-      `ai-sdk/elevenlabs/0.0.0-test`,
-    );
-  });
-
-  it('should extract the transcription text', async () => {
-    prepareJsonResponse();
-
-    const result = await model.doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-    });
-
-    expect(result.text).toBe('Hello world!');
-  });
-
-  it('should include response data with timestamp, modelId and headers', async () => {
-    prepareJsonResponse({
-      headers: {
-        'x-request-id': 'test-request-id',
-        'x-ratelimit-remaining': '123',
-      },
-    });
-
-    const testDate = new Date(0);
-    const customModel = new ElevenLabsTranscriptionModel('scribe_v1', {
-      provider: 'test-provider',
-      url: () => 'https://api.elevenlabs.io/v1/speech-to-text',
-      headers: () => ({}),
-      _internal: {
-        currentDate: () => testDate,
-      },
-    });
-
-    const result = await customModel.doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-    });
-
-    expect(result.response).toMatchObject({
-      timestamp: testDate,
-      modelId: 'scribe_v1',
-      headers: {
-        'content-type': 'application/json',
-        'x-request-id': 'test-request-id',
-        'x-ratelimit-remaining': '123',
-      },
-    });
-  });
-
-  it('should use real date when no custom date provider is specified', async () => {
-    prepareJsonResponse();
-
-    const testDate = new Date(0);
-    const customModel = new ElevenLabsTranscriptionModel('scribe_v1', {
-      provider: 'test-provider',
-      url: () => 'https://api.elevenlabs.io/v1/speech-to-text',
-      headers: () => ({}),
-      _internal: {
-        currentDate: () => testDate,
-      },
-    });
-
-    const result = await customModel.doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-    });
-
-    expect(result.response.timestamp.getTime()).toEqual(testDate.getTime());
-    expect(result.response.modelId).toBe('scribe_v1');
-  });
-
-  it('should work when no additional formats are returned', async () => {
-    server.urls['https://api.elevenlabs.io/v1/speech-to-text'].response = {
-      type: 'json-value',
-      body: {
-        language_code: 'en',
-        language_probability: 0.98,
-        text: 'Hello world!',
-        words: [
-          {
-            text: 'Hello',
-            type: 'word',
-            start: 0,
-            end: 0.5,
-            speaker_id: 'speaker_1',
-            characters: [
-              {
-                text: 'text',
-                start: 0,
-                end: 0.1,
-              },
-            ],
-          },
-          {
-            text: ' ',
-            type: 'spacing',
-            start: 0.5,
-            end: 0.5,
-            speaker_id: 'speaker_1',
-            characters: [
-              {
-                text: 'text',
-                start: 0,
-                end: 0.1,
-              },
-            ],
-          },
-          {
-            text: 'world!',
-            type: 'word',
-            start: 0.5,
-            end: 1.2,
-            speaker_id: 'speaker_1',
-            characters: [
-              {
-                text: 'text',
-                start: 0,
-                end: 0.1,
-              },
-            ],
-          },
-        ],
-      },
-    };
-
-    const testDate = new Date(0);
-    const customModel = new ElevenLabsTranscriptionModel('scribe_v1', {
-      provider: 'test-provider',
-      url: () => 'https://api.elevenlabs.io/v1/speech-to-text',
-      headers: () => ({}),
-      _internal: {
-        currentDate: () => testDate,
-      },
-    });
-
-    const result = await customModel.doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-    });
-
-    expect(result).toMatchInlineSnapshot(`
-      {
-        "durationInSeconds": 1.2,
-        "language": "en",
-        "response": {
-          "body": {
-            "language_code": "en",
-            "language_probability": 0.98,
-            "text": "Hello world!",
-            "words": [
-              {
-                "characters": [
-                  {
-                    "end": 0.1,
-                    "start": 0,
-                    "text": "text",
-                  },
-                ],
-                "end": 0.5,
-                "speaker_id": "speaker_1",
-                "start": 0,
-                "text": "Hello",
-                "type": "word",
-              },
-              {
-                "characters": [
-                  {
-                    "end": 0.1,
-                    "start": 0,
-                    "text": "text",
-                  },
-                ],
-                "end": 0.5,
-                "speaker_id": "speaker_1",
-                "start": 0.5,
-                "text": " ",
-                "type": "spacing",
-              },
-              {
-                "characters": [
-                  {
-                    "end": 0.1,
-                    "start": 0,
-                    "text": "text",
-                  },
-                ],
-                "end": 1.2,
-                "speaker_id": "speaker_1",
-                "start": 0.5,
-                "text": "world!",
-                "type": "word",
-              },
-            ],
-          },
-          "headers": {
-            "content-length": "467",
-            "content-type": "application/json",
-          },
-          "modelId": "scribe_v1",
-          "timestamp": 1970-01-01T00:00:00.000Z,
-        },
-        "segments": [
-          {
-            "endSecond": 0.5,
-            "startSecond": 0,
-            "text": "Hello",
-          },
-          {
-            "endSecond": 0.5,
-            "startSecond": 0.5,
-            "text": " ",
-          },
-          {
-            "endSecond": 1.2,
-            "startSecond": 0.5,
-            "text": "world!",
-          },
-        ],
-        "text": "Hello world!",
-        "warnings": [],
-      }
-    `);
-  });
-
-  it('should pass provider options correctly', async () => {
-    prepareJsonResponse();
-
-    await model.doGenerate({
-      audio: audioData,
-      mediaType: 'audio/wav',
-      providerOptions: {
-        elevenlabs: {
-          languageCode: 'en',
-          fileFormat: 'pcm_s16le_16',
-          tagAudioEvents: false,
-          numSpeakers: 2,
-          timestampsGranularity: 'character',
-          diarize: true,
-        },
-      },
-    });
-
-    expect(await server.calls[0].requestBodyMultipart).toMatchInlineSnapshot(`
-      {
-        "diarize": "true",
-        "file": File {
-          Symbol(kHandle): Blob {},
-          Symbol(kLength): 40169,
-          Symbol(kType): "audio/wav",
-        },
-        "file_format": "pcm_s16le_16",
-        "language_code": "en",
-        "model_id": "scribe_v1",
-        "num_speakers": "2",
-        "tag_audio_events": "false",
-        "timestamps_granularity": "character",
-      }
-    `);
-  });
-});