@ai-sdk/assemblyai 2.0.7 → 2.0.9

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @ai-sdk/assemblyai
 
+## 2.0.9
+
+### Patch Changes
+
+- 8dc54db: chore: add src folders to package bundle
+
+## 2.0.8
+
+### Patch Changes
+
+- Updated dependencies [5c090e7]
+  - @ai-sdk/provider@3.0.4
+  - @ai-sdk/provider-utils@4.0.8
+
 ## 2.0.7
 
 ### Patch Changes

package/dist/index.js

@@ -401,7 +401,7 @@ var assemblyaiTranscriptionResponseSchema = import_v42.z.object({
 });
 
 // src/version.ts
-var VERSION = true ? "2.0.7" : "0.0.0-test";
+var VERSION = true ? "2.0.9" : "0.0.0-test";
 
 // src/assemblyai-provider.ts
 function createAssemblyAI(options = {}) {

package/dist/index.mjs

@@ -385,7 +385,7 @@ var assemblyaiTranscriptionResponseSchema = z2.object({
 });
 
 // src/version.ts
-var VERSION = true ? "2.0.7" : "0.0.0-test";
+var VERSION = true ? "2.0.9" : "0.0.0-test";
 
 // src/assemblyai-provider.ts
 function createAssemblyAI(options = {}) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/assemblyai",
-  "version": "2.0.7",
+  "version": "2.0.9",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -8,6 +8,7 @@
   "types": "./dist/index.d.ts",
   "files": [
     "dist/**/*",
+    "src",
     "CHANGELOG.md",
     "README.md"
   ],
@@ -20,15 +21,15 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/provider": "3.0.3",
-    "@ai-sdk/provider-utils": "4.0.7"
+    "@ai-sdk/provider": "3.0.4",
+    "@ai-sdk/provider-utils": "4.0.8"
   },
   "devDependencies": {
     "@types/node": "20.17.24",
     "tsup": "^8",
     "typescript": "5.6.3",
     "zod": "3.25.76",
-    "@ai-sdk/test-server": "1.0.1",
+    "@ai-sdk/test-server": "1.0.2",
     "@vercel/ai-tsconfig": "0.0.0"
   },
   "peerDependencies": {

package/src/assemblyai-api-types.ts

@@ -0,0 +1,362 @@
+export type AssemblyAITranscriptionAPITypes = {
+  /**
+   * The URL of the audio or video file to transcribe.
+   */
+  audio_url: string;
+
+  /**
+   * The point in time, in milliseconds, to stop transcribing in your media file
+   */
+  audio_end_at?: number;
+
+  /**
+   * The point in time, in milliseconds, to begin transcribing in your media file
+   */
+  audio_start_from?: number;
+
+  /**
+   * Enable Auto Chapters, can be true or false
+   * @default false
+   */
+  auto_chapters?: boolean;
+
+  /**
+   * Enable Key Phrases, either true or false
+   * @default false
+   */
+  auto_highlights?: boolean;
+
+  /**
+   * How much to boost specified words
+   */
+  boost_param?: 'low' | 'default' | 'high';
+
+  /**
+   * Enable Content Moderation, can be true or false
+   * @default false
+   */
+  content_safety?: boolean;
+
+  /**
+   * The confidence threshold for the Content Moderation model. Values must be between 25 and 100.
+   * @default 50
+   */
+  content_safety_confidence?: number;
+
+  /**
+   * Customize how words are spelled and formatted using to and from values
+   */
+  custom_spelling?: Array<{
+    /**
+     * Words or phrases to replace
+     */
+    from: string[];
+    /**
+     * Word to replace with
+     */
+    to: string;
+  }>;
+
+  /**
+   * Transcribe Filler Words, like "umm", in your media file; can be true or false
+   * @default false
+   */
+  disfluencies?: boolean;
+
+  /**
+   * Enable Entity Detection, can be true or false
+   * @default false
+   */
+  entity_detection?: boolean;
+
+  /**
+   * Filter profanity from the transcribed text, can be true or false
+   * @default false
+   */
+  filter_profanity?: boolean;
+
+  /**
+   * Enable Text Formatting, can be true or false
+   * @default true
+   */
+  format_text?: boolean;
+
+  /**
+   * Enable Topic Detection, can be true or false
+   * @default false
+   */
+  iab_categories?: boolean;
+
+  /**
+   * The language of your audio file. Possible values are found in Supported Languages.
+   * @default 'en_us'
+   */
+  language_code?:
+    | 'en'
+    | 'en_au'
+    | 'en_uk'
+    | 'en_us'
+    | 'es'
+    | 'fr'
+    | 'de'
+    | 'it'
+    | 'pt'
+    | 'nl'
+    | 'af'
+    | 'sq'
+    | 'am'
+    | 'ar'
+    | 'hy'
+    | 'as'
+    | 'az'
+    | 'ba'
+    | 'eu'
+    | 'be'
+    | 'bn'
+    | 'bs'
+    | 'br'
+    | 'bg'
+    | 'my'
+    | 'ca'
+    | 'zh'
+    | 'hr'
+    | 'cs'
+    | 'da'
+    | 'et'
+    | 'fo'
+    | 'fi'
+    | 'gl'
+    | 'ka'
+    | 'el'
+    | 'gu'
+    | 'ht'
+    | 'ha'
+    | 'haw'
+    | 'he'
+    | 'hi'
+    | 'hu'
+    | 'is'
+    | 'id'
+    | 'ja'
+    | 'jw'
+    | 'kn'
+    | 'kk'
+    | 'km'
+    | 'ko'
+    | 'lo'
+    | 'la'
+    | 'lv'
+    | 'ln'
+    | 'lt'
+    | 'lb'
+    | 'mk'
+    | 'mg'
+    | 'ms'
+    | 'ml'
+    | 'mt'
+    | 'mi'
+    | 'mr'
+    | 'mn'
+    | 'ne'
+    | 'no'
+    | 'nn'
+    | 'oc'
+    | 'pa'
+    | 'ps'
+    | 'fa'
+    | 'pl'
+    | 'ro'
+    | 'ru'
+    | 'sa'
+    | 'sr'
+    | 'sn'
+    | 'sd'
+    | 'si'
+    | 'sk'
+    | 'sl'
+    | 'so'
+    | 'su'
+    | 'sw'
+    | 'sv'
+    | 'tl'
+    | 'tg'
+    | 'ta'
+    | 'tt'
+    | 'te'
+    | 'th'
+    | 'bo'
+    | 'tr'
+    | 'tk'
+    | 'uk'
+    | 'ur'
+    | 'uz'
+    | 'vi'
+    | 'cy'
+    | 'yi'
+    | 'yo';
+
+  /**
+   * The confidence threshold for the automatically detected language. An error will be returned if the language confidence is below this threshold.
+   * @default 0
+   */
+  language_confidence_threshold?: number;
+
+  /**
+   * Enable Automatic language detection, either true or false.
+   * @default false
+   */
+  language_detection?: boolean;
+
+  /**
+   * Enable Multichannel transcription, can be true or false.
+   * @default false
+   */
+  multichannel?: boolean;
+
+  /**
+   * Enable Automatic Punctuation, can be true or false
+   * @default true
+   */
+  punctuate?: boolean;
+
+  /**
+   * Redact PII from the transcribed text using the Redact PII model, can be true or false
+   * @default false
+   */
+  redact_pii?: boolean;
+
+  /**
+   * Generate a copy of the original media file with spoken PII "beeped" out, can be true or false.
+   * @default false
+   */
+  redact_pii_audio?: boolean;
+
+  /**
+   * Controls the filetype of the audio created by redact_pii_audio. Currently supports mp3 (default) and wav.
+   */
+  redact_pii_audio_quality?: 'mp3' | 'wav';
+
+  /**
+   * The list of PII Redaction policies to enable.
+   */
+  redact_pii_policies?: Array<
+    | 'account_number'
+    | 'banking_information'
+    | 'blood_type'
+    | 'credit_card_cvv'
+    | 'credit_card_expiration'
+    | 'credit_card_number'
+    | 'date'
+    | 'date_interval'
+    | 'date_of_birth'
+    | 'drivers_license'
+    | 'drug'
+    | 'duration'
+    | 'email_address'
+    | 'event'
+    | 'filename'
+    | 'gender_sexuality'
+    | 'healthcare_number'
+    | 'injury'
+    | 'ip_address'
+    | 'language'
+    | 'location'
+    | 'marital_status'
+    | 'medical_condition'
+    | 'medical_process'
+    | 'money_amount'
+    | 'nationality'
+    | 'number_sequence'
+    | 'occupation'
+    | 'organization'
+    | 'passport_number'
+    | 'password'
+    | 'person_age'
+    | 'person_name'
+    | 'phone_number'
+    | 'physical_attribute'
+    | 'political_affiliation'
+    | 'religion'
+    | 'statistics'
+    | 'time'
+    | 'url'
+    | 'us_social_security_number'
+    | 'username'
+    | 'vehicle_id'
+    | 'zodiac_sign'
+  >;
+
+  /**
+   * The replacement logic for detected PII, can be "entity_name" or "hash".
+   */
+  redact_pii_sub?: 'entity_name' | 'hash';
+
+  /**
+   * Enable Sentiment Analysis, can be true or false
+   * @default false
+   */
+  sentiment_analysis?: boolean;
+
+  /**
+   * Enable Speaker diarization, can be true or false
+   * @default false
+   */
+  speaker_labels?: boolean;
+
+  /**
+   * Tells the speaker label model how many speakers it should attempt to identify, up to 10.
+   */
+  speakers_expected?: number;
+
+  /**
+   * The speech model to use for the transcription.
+   */
+  speech_model?: 'best' | 'nano';
+
+  /**
+   * Reject audio files that contain less than this fraction of speech. Valid values are in the range [0, 1] inclusive.
+   */
+  speech_threshold?: number;
+
+  /**
+   * Enable Summarization, can be true or false
+   * @default false
+   */
+  summarization?: boolean;
+
+  /**
+   * The model to summarize the transcript
+   */
+  summary_model?: 'informative' | 'conversational' | 'catchy';
+
+  /**
+   * The type of summary
+   */
+  summary_type?:
+    | 'bullets'
+    | 'bullets_verbose'
+    | 'gist'
+    | 'headline'
+    | 'paragraph';
+
+  /**
+   * The header name to be sent with the transcript completed or failed webhook requests
+   */
+  webhook_auth_header_name?: string;
+
+  /**
+   * The header value to send back with the transcript completed or failed webhook requests for added security
+   */
+  webhook_auth_header_value?: string;
+
+  /**
+   * The URL to which we send webhook requests. We sends two different types of webhook requests.
+   * One request when a transcript is completed or failed, and one request when the redacted audio is ready if redact_pii_audio is enabled.
+   */
+  webhook_url?: string;
+
+  /**
+   * The list of custom vocabulary to boost transcription probability for
+   */
+  word_boost?: string[];
+};

package/src/assemblyai-config.ts

@@ -0,0 +1,9 @@
+import { FetchFunction } from '@ai-sdk/provider-utils';
+
+export type AssemblyAIConfig = {
+  provider: string;
+  url: (options: { modelId: string; path: string }) => string;
+  headers: () => Record<string, string | undefined>;
+  fetch?: FetchFunction;
+  generateId?: () => string;
+};

package/src/assemblyai-error.test.ts

@@ -0,0 +1,34 @@
+import { safeParseJSON } from '@ai-sdk/provider-utils';
+import { assemblyaiErrorDataSchema } from './assemblyai-error';
+import { describe, it, expect } from 'vitest';
+
+describe('assemblyaiErrorDataSchema', () => {
+  it('should parse AssemblyAI 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: assemblyaiErrorDataSchema,
+    });
+
+    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/assemblyai-error.ts

@@ -0,0 +1,16 @@
+import { z } from 'zod/v4';
+import { createJsonErrorResponseHandler } from '@ai-sdk/provider-utils';
+
+export const assemblyaiErrorDataSchema = z.object({
+  error: z.object({
+    message: z.string(),
+    code: z.number(),
+  }),
+});
+
+export type AssemblyAIErrorData = z.infer<typeof assemblyaiErrorDataSchema>;
+
+export const assemblyaiFailedResponseHandler = createJsonErrorResponseHandler({
+  errorSchema: assemblyaiErrorDataSchema,
+  errorToMessage: data => data.error.message,
+});

package/src/assemblyai-provider.ts

@@ -0,0 +1,112 @@
+import {
+  TranscriptionModelV3,
+  ProviderV3,
+  NoSuchModelError,
+} from '@ai-sdk/provider';
+import {
+  FetchFunction,
+  loadApiKey,
+  withUserAgentSuffix,
+} from '@ai-sdk/provider-utils';
+import { AssemblyAITranscriptionModel } from './assemblyai-transcription-model';
+import { AssemblyAITranscriptionModelId } from './assemblyai-transcription-settings';
+import { VERSION } from './version';
+
+export interface AssemblyAIProvider extends ProviderV3 {
+  (
+    modelId: 'best',
+    settings?: {},
+  ): {
+    transcription: AssemblyAITranscriptionModel;
+  };
+
+  /**
+Creates a model for transcription.
+   */
+  transcription(modelId: AssemblyAITranscriptionModelId): TranscriptionModelV3;
+
+  /**
+   * @deprecated Use `embeddingModel` instead.
+   */
+  textEmbeddingModel(modelId: string): never;
+}
+
+export interface AssemblyAIProviderSettings {
+  /**
+API key for authenticating requests.
+     */
+  apiKey?: string;
+
+  /**
+Custom headers to include in the requests.
+     */
+  headers?: Record<string, string>;
+
+  /**
+Custom fetch implementation. You can use it as a middleware to intercept requests,
+or to provide a custom fetch implementation for e.g. testing.
+    */
+  fetch?: FetchFunction;
+}
+
+/**
+Create an AssemblyAI provider instance.
+ */
+export function createAssemblyAI(
+  options: AssemblyAIProviderSettings = {},
+): AssemblyAIProvider {
+  const getHeaders = () =>
+    withUserAgentSuffix(
+      {
+        authorization: loadApiKey({
+          apiKey: options.apiKey,
+          environmentVariableName: 'ASSEMBLYAI_API_KEY',
+          description: 'AssemblyAI',
+        }),
+        ...options.headers,
+      },
+      `ai-sdk/assemblyai/${VERSION}`,
+    );
+
+  const createTranscriptionModel = (modelId: AssemblyAITranscriptionModelId) =>
+    new AssemblyAITranscriptionModel(modelId, {
+      provider: `assemblyai.transcription`,
+      url: ({ path }) => `https://api.assemblyai.com${path}`,
+      headers: getHeaders,
+      fetch: options.fetch,
+    });
+
+  const provider = function (modelId: AssemblyAITranscriptionModelId) {
+    return {
+      transcription: createTranscriptionModel(modelId),
+    };
+  };
+
+  provider.specificationVersion = 'v3' as const;
+  provider.transcription = createTranscriptionModel;
+  provider.transcriptionModel = createTranscriptionModel;
+
+  provider.languageModel = () => {
+    throw new NoSuchModelError({
+      modelId: 'unknown',
+      modelType: 'languageModel',
+      message: 'AssemblyAI does not provide language models',
+    });
+  };
+
+  provider.embeddingModel = (modelId: string) => {
+    throw new NoSuchModelError({ modelId, modelType: 'embeddingModel' });
+  };
+  provider.textEmbeddingModel = provider.embeddingModel;
+
+  provider.imageModel = (modelId: string) => {
+    throw new NoSuchModelError({ modelId, modelType: 'imageModel' });
+  };
+
+  return provider as AssemblyAIProvider;
+}
+
+/**
+Default AssemblyAI provider instance.
+ */
+export const assemblyai = createAssemblyAI();