@ai-sdk/openai 2.0.0-canary.2 → 2.0.0-canary.4

package/internal/dist/index.d.mts

@@ -1,4 +1,4 @@
-import { LanguageModelV2, EmbeddingModelV1, ImageModelV1 } from '@ai-sdk/provider';
+import { LanguageModelV2, EmbeddingModelV1, ImageModelV1, TranscriptionModelV1CallOptions, TranscriptionModelV1 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod';
 
@@ -244,6 +244,71 @@ declare class OpenAIImageModel implements ImageModelV1 {
     doGenerate({ prompt, n, size, aspectRatio, seed, providerOptions, headers, abortSignal, }: Parameters<ImageModelV1['doGenerate']>[0]): Promise<Awaited<ReturnType<ImageModelV1['doGenerate']>>>;
 }
 
+type OpenAITranscriptionModelId = 'whisper-1' | 'gpt-4o-mini-transcribe' | 'gpt-4o-transcribe' | (string & {});
+type OpenAITranscriptionModelOptions = {
+    /**
+     * Additional information to include in the transcription response.
+     */
+    include?: string[];
+    /**
+     * The language of the input audio in ISO-639-1 format.
+     */
+    language?: string;
+    /**
+     * An optional text to guide the model's style or continue a previous audio segment.
+     */
+    prompt?: string;
+    /**
+     * The sampling temperature, between 0 and 1.
+     * @default 0
+     */
+    temperature?: number;
+    /**
+     * The timestamp granularities to populate for this transcription.
+     * @default ['segment']
+     */
+    timestamp_granularities?: Array<'word' | 'segment'>;
+};
+
+declare const OpenAIProviderOptionsSchema: z.ZodObject<{
+    include: z.ZodOptional<z.ZodArray<z.ZodString, "many">>;
+    language: z.ZodOptional<z.ZodString>;
+    prompt: z.ZodOptional<z.ZodString>;
+    temperature: z.ZodDefault<z.ZodOptional<z.ZodNumber>>;
+    timestampGranularities: z.ZodDefault<z.ZodOptional<z.ZodArray<z.ZodEnum<["word", "segment"]>, "many">>>;
+}, "strip", z.ZodTypeAny, {
+    temperature: number;
+    timestampGranularities: ("word" | "segment")[];
+    prompt?: string | undefined;
+    include?: string[] | undefined;
+    language?: string | undefined;
+}, {
+    prompt?: string | undefined;
+    temperature?: number | undefined;
+    include?: string[] | undefined;
+    language?: string | undefined;
+    timestampGranularities?: ("word" | "segment")[] | undefined;
+}>;
+type OpenAITranscriptionCallOptions = Omit<TranscriptionModelV1CallOptions, 'providerOptions'> & {
+    providerOptions?: {
+        openai?: z.infer<typeof OpenAIProviderOptionsSchema>;
+    };
+};
+interface OpenAITranscriptionModelConfig extends OpenAIConfig {
+    _internal?: {
+        currentDate?: () => Date;
+    };
+}
+declare class OpenAITranscriptionModel implements TranscriptionModelV1 {
+    readonly modelId: OpenAITranscriptionModelId;
+    private readonly config;
+    readonly specificationVersion = "v1";
+    get provider(): string;
+    constructor(modelId: OpenAITranscriptionModelId, config: OpenAITranscriptionModelConfig);
+    private getArgs;
+    doGenerate(options: OpenAITranscriptionCallOptions): Promise<Awaited<ReturnType<TranscriptionModelV1['doGenerate']>>>;
+}
+
 type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024-09-12' | 'o1-preview' | 'o1-preview-2024-09-12' | 'o3-mini' | 'o3-mini-2025-01-31' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo-preview' | 'gpt-4-0125-preview' | 'gpt-4-1106-preview' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV2 {
@@ -287,4 +352,4 @@ declare const openaiResponsesProviderOptionsSchema: z.ZodObject<{
 }>;
 type OpenAIResponsesProviderOptions = z.infer<typeof openaiResponsesProviderOptionsSchema>;
 
-export { OpenAIChatLanguageModel, type OpenAIChatModelId, type OpenAIChatSettings, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionSettings, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingSettings, OpenAIImageModel, type OpenAIImageModelId, type OpenAIImageSettings, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, modelMaxImagesPerCall };
+export { OpenAIChatLanguageModel, type OpenAIChatModelId, type OpenAIChatSettings, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionSettings, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingSettings, OpenAIImageModel, type OpenAIImageModelId, type OpenAIImageSettings, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionModelOptions, modelMaxImagesPerCall };

package/internal/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { LanguageModelV2, EmbeddingModelV1, ImageModelV1 } from '@ai-sdk/provider';
+import { LanguageModelV2, EmbeddingModelV1, ImageModelV1, TranscriptionModelV1CallOptions, TranscriptionModelV1 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 import { z } from 'zod';
 
@@ -244,6 +244,71 @@ declare class OpenAIImageModel implements ImageModelV1 {
     doGenerate({ prompt, n, size, aspectRatio, seed, providerOptions, headers, abortSignal, }: Parameters<ImageModelV1['doGenerate']>[0]): Promise<Awaited<ReturnType<ImageModelV1['doGenerate']>>>;
 }
 
+type OpenAITranscriptionModelId = 'whisper-1' | 'gpt-4o-mini-transcribe' | 'gpt-4o-transcribe' | (string & {});
+type OpenAITranscriptionModelOptions = {
+    /**
+     * Additional information to include in the transcription response.
+     */
+    include?: string[];
+    /**
+     * The language of the input audio in ISO-639-1 format.
+     */
+    language?: string;
+    /**
+     * An optional text to guide the model's style or continue a previous audio segment.
+     */
+    prompt?: string;
+    /**
+     * The sampling temperature, between 0 and 1.
+     * @default 0
+     */
+    temperature?: number;
+    /**
+     * The timestamp granularities to populate for this transcription.
+     * @default ['segment']
+     */
+    timestamp_granularities?: Array<'word' | 'segment'>;
+};
+
+declare const OpenAIProviderOptionsSchema: z.ZodObject<{
+    include: z.ZodOptional<z.ZodArray<z.ZodString, "many">>;
+    language: z.ZodOptional<z.ZodString>;
+    prompt: z.ZodOptional<z.ZodString>;
+    temperature: z.ZodDefault<z.ZodOptional<z.ZodNumber>>;
+    timestampGranularities: z.ZodDefault<z.ZodOptional<z.ZodArray<z.ZodEnum<["word", "segment"]>, "many">>>;
+}, "strip", z.ZodTypeAny, {
+    temperature: number;
+    timestampGranularities: ("word" | "segment")[];
+    prompt?: string | undefined;
+    include?: string[] | undefined;
+    language?: string | undefined;
+}, {
+    prompt?: string | undefined;
+    temperature?: number | undefined;
+    include?: string[] | undefined;
+    language?: string | undefined;
+    timestampGranularities?: ("word" | "segment")[] | undefined;
+}>;
+type OpenAITranscriptionCallOptions = Omit<TranscriptionModelV1CallOptions, 'providerOptions'> & {
+    providerOptions?: {
+        openai?: z.infer<typeof OpenAIProviderOptionsSchema>;
+    };
+};
+interface OpenAITranscriptionModelConfig extends OpenAIConfig {
+    _internal?: {
+        currentDate?: () => Date;
+    };
+}
+declare class OpenAITranscriptionModel implements TranscriptionModelV1 {
+    readonly modelId: OpenAITranscriptionModelId;
+    private readonly config;
+    readonly specificationVersion = "v1";
+    get provider(): string;
+    constructor(modelId: OpenAITranscriptionModelId, config: OpenAITranscriptionModelConfig);
+    private getArgs;
+    doGenerate(options: OpenAITranscriptionCallOptions): Promise<Awaited<ReturnType<TranscriptionModelV1['doGenerate']>>>;
+}
+
 type OpenAIResponsesModelId = 'o1' | 'o1-2024-12-17' | 'o1-mini' | 'o1-mini-2024-09-12' | 'o1-preview' | 'o1-preview-2024-09-12' | 'o3-mini' | 'o3-mini-2025-01-31' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4-turbo' | 'gpt-4-turbo-2024-04-09' | 'gpt-4-turbo-preview' | 'gpt-4-0125-preview' | 'gpt-4-1106-preview' | 'gpt-4' | 'gpt-4-0613' | 'gpt-4.5-preview' | 'gpt-4.5-preview-2025-02-27' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'chatgpt-4o-latest' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV2 {
@@ -287,4 +352,4 @@ declare const openaiResponsesProviderOptionsSchema: z.ZodObject<{
 }>;
 type OpenAIResponsesProviderOptions = z.infer<typeof openaiResponsesProviderOptionsSchema>;
 
-export { OpenAIChatLanguageModel, type OpenAIChatModelId, type OpenAIChatSettings, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionSettings, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingSettings, OpenAIImageModel, type OpenAIImageModelId, type OpenAIImageSettings, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, modelMaxImagesPerCall };
+export { OpenAIChatLanguageModel, type OpenAIChatModelId, type OpenAIChatSettings, OpenAICompletionLanguageModel, type OpenAICompletionModelId, type OpenAICompletionSettings, OpenAIEmbeddingModel, type OpenAIEmbeddingModelId, type OpenAIEmbeddingSettings, OpenAIImageModel, type OpenAIImageModelId, type OpenAIImageSettings, OpenAIResponsesLanguageModel, type OpenAIResponsesProviderOptions, type OpenAITranscriptionCallOptions, OpenAITranscriptionModel, type OpenAITranscriptionModelId, type OpenAITranscriptionModelOptions, modelMaxImagesPerCall };