@ai-sdk/openai 4.0.58 → 4.0.59

package/dist/internal/index.d.ts

@@ -4,7 +4,7 @@ import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { InferSchema, WORKFLOW_SERIALIZE, WORKFLOW_DESERIALIZE, FetchFunction, WebSocketConstructor, EXPERIMENTAL_EMBEDDING_MODEL_MAX_INPUT_BYTES_PER_CALL } from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
 
-type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'o4-mini' | 'o4-mini-2025-04-16' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-audio-preview' | 'gpt-4o-audio-preview-2024-12-17' | 'gpt-4o-audio-preview-2025-06-03' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini-audio-preview' | 'gpt-4o-mini-audio-preview-2024-12-17' | 'gpt-4o-search-preview' | 'gpt-4o-search-preview-2025-03-11' | 'gpt-4o-mini-search-preview' | 'gpt-4o-mini-search-preview-2025-03-11' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo-16k' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5.1' | 'gpt-5.1-2025-11-13' | 'gpt-5.1-chat-latest' | 'gpt-5.2' | 'gpt-5.2-2025-12-11' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.3-chat-latest' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.5' | 'gpt-5.5-2026-04-23' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | (string & {});
+type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'o4-mini' | 'o4-mini-2025-04-16' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-audio-preview' | 'gpt-4o-audio-preview-2024-12-17' | 'gpt-4o-audio-preview-2025-06-03' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini-audio-preview' | 'gpt-4o-mini-audio-preview-2024-12-17' | 'gpt-4o-search-preview' | 'gpt-4o-search-preview-2025-03-11' | 'gpt-4o-mini-search-preview' | 'gpt-4o-mini-search-preview-2025-03-11' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo-16k' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5.1' | 'gpt-5.1-2025-11-13' | 'gpt-5.1-chat-latest' | 'gpt-5.2' | 'gpt-5.2-2025-12-11' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.3-chat-latest' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.5' | 'gpt-5.5-2026-04-23' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | 'gpt-6-astra' | (string & {});
 declare const openaiLanguageModelChatOptions: _ai_sdk_provider_utils.LazySchema<{
     logitBias?: Record<number, number> | undefined;
     logprobs?: number | boolean | undefined;
@@ -217,6 +217,13 @@ declare const openAITranscriptionModelOptions: _ai_sdk_provider_utils.LazySchema
     prompt?: string | undefined;
     temperature?: number | undefined;
     timestampGranularities?: ("word" | "segment")[] | undefined;
+    responseFormat?: "json" | "verbose_json" | "diarized_json" | undefined;
+    chunkingStrategy?: "auto" | {
+        type: "server_vad";
+        threshold?: number | undefined;
+        prefixPaddingMs?: number | undefined;
+        silenceDurationMs?: number | undefined;
+    } | undefined;
     streaming?: {
         delay?: "minimal" | "low" | "medium" | "high" | "xhigh" | undefined;
         include?: string[] | undefined;
@@ -1803,7 +1810,7 @@ declare const webSearch: (args?: Parameters<typeof webSearchToolFactory>[0]) =>
     }>;
 }, {}>;
 
-type OpenAIResponsesModelId = 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini' | 'gpt-4o' | 'gpt-5.1' | 'gpt-5.1-2025-11-13' | 'gpt-5.1-chat-latest' | 'gpt-5.1-codex-mini' | 'gpt-5.1-codex' | 'gpt-5.1-codex-max' | 'gpt-5.2' | 'gpt-5.2-2025-12-11' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.2-codex' | 'gpt-5.3-chat-latest' | 'gpt-5.3-codex' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.5' | 'gpt-5.5-2026-04-23' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | 'gpt-5-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-5-mini-2025-08-07' | 'gpt-5-mini' | 'gpt-5-nano-2025-08-07' | 'gpt-5-nano' | 'gpt-5-pro-2025-10-06' | 'gpt-5-pro' | 'gpt-5' | 'o1-2024-12-17' | 'o1' | 'o3-2025-04-16' | 'o3-mini-2025-01-31' | 'o3-mini' | 'o3' | 'o4-mini' | 'o4-mini-2025-04-16' | (string & {});
+type OpenAIResponsesModelId = 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini' | 'gpt-4o' | 'gpt-5.1' | 'gpt-5.1-2025-11-13' | 'gpt-5.1-chat-latest' | 'gpt-5.1-codex-mini' | 'gpt-5.1-codex' | 'gpt-5.1-codex-max' | 'gpt-5.2' | 'gpt-5.2-2025-12-11' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.2-codex' | 'gpt-5.3-chat-latest' | 'gpt-5.3-codex' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.5' | 'gpt-5.5-2026-04-23' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | 'gpt-6-astra' | 'gpt-5-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5-codex' | 'gpt-5-mini-2025-08-07' | 'gpt-5-mini' | 'gpt-5-nano-2025-08-07' | 'gpt-5-nano' | 'gpt-5-pro-2025-10-06' | 'gpt-5-pro' | 'gpt-5' | 'o1-2024-12-17' | 'o1' | 'o3-2025-04-16' | 'o3-mini-2025-01-31' | 'o3-mini' | 'o3' | 'o4-mini' | 'o4-mini-2025-04-16' | (string & {});
 
 declare class OpenAIResponsesLanguageModel implements LanguageModelV4 {
     readonly specificationVersion = "v4";

package/dist/internal/index.js

@@ -2424,18 +2424,28 @@ var openaiTranscriptionResponseSchema = lazySchema9(
         })
       ).nullish(),
       segments: z10.array(
-        z10.object({
-          id: z10.number(),
-          seek: z10.number(),
-          start: z10.number(),
-          end: z10.number(),
-          text: z10.string(),
-          tokens: z10.array(z10.number()),
-          temperature: z10.number(),
-          avg_logprob: z10.number(),
-          compression_ratio: z10.number(),
-          no_speech_prob: z10.number()
-        })
+        z10.union([
+          z10.object({
+            id: z10.number(),
+            seek: z10.number(),
+            start: z10.number(),
+            end: z10.number(),
+            text: z10.string(),
+            tokens: z10.array(z10.number()),
+            temperature: z10.number(),
+            avg_logprob: z10.number(),
+            compression_ratio: z10.number(),
+            no_speech_prob: z10.number()
+          }),
+          z10.object({
+            type: z10.literal("transcript.text.segment"),
+            id: z10.string(),
+            start: z10.number(),
+            end: z10.number(),
+            text: z10.string(),
+            speaker: z10.string()
+          })
+        ])
       ).nullish()
     })
   )
@@ -2472,6 +2482,22 @@ var openAITranscriptionModelOptions = lazySchema10(
        * @default ['segment']
        */
       timestampGranularities: z11.array(z11.enum(["word", "segment"])).default(["segment"]).optional(),
+      /**
+       * The format of the transcription response.
+       */
+      responseFormat: z11.enum(["json", "verbose_json", "diarized_json"]).optional(),
+      /**
+       * Controls how the audio is split into chunks before transcription.
+       */
+      chunkingStrategy: z11.union([
+        z11.literal("auto"),
+        z11.object({
+          type: z11.literal("server_vad"),
+          threshold: z11.number().min(0).max(1).optional(),
+          prefixPaddingMs: z11.number().int().min(0).optional(),
+          silenceDurationMs: z11.number().int().min(0).optional()
+        })
+      ]).optional(),
       /**
        * Options for streaming transcription models such as `gpt-realtime-whisper`.
        */
@@ -2575,6 +2601,7 @@ var OpenAITranscriptionModel = class _OpenAITranscriptionModel {
     mediaType,
     providerOptions
   }) {
+    var _a2, _b;
     const warnings = [];
     const openAIOptions = await parseProviderOptions5({
       provider: "openai",
@@ -2593,6 +2620,8 @@ var OpenAITranscriptionModel = class _OpenAITranscriptionModel {
     if (this.modelId === "whisper-1") {
       formData.append("response_format", "verbose_json");
     }
+    const isDiarizationModel = this.modelId === "gpt-4o-transcribe-diarize";
+    const chunkingStrategy = (_a2 = openAIOptions == null ? void 0 : openAIOptions.chunkingStrategy) != null ? _a2 : isDiarizationModel ? "auto" : void 0;
     if (openAIOptions) {
       const isGpt4oTranscribeModel = [
         "gpt-4o-transcribe",
@@ -2605,7 +2634,7 @@ var OpenAITranscriptionModel = class _OpenAITranscriptionModel {
         // https://platform.openai.com/docs/api-reference/audio/createTranscription#audio_createtranscription-response_format
         // prefer verbose_json to get segments for models that support it
         ...this.modelId !== "whisper-1" && {
-          response_format: isGpt4oTranscribeModel ? "json" : "verbose_json"
+          response_format: (_b = openAIOptions.responseFormat) != null ? _b : isDiarizationModel ? "diarized_json" : isGpt4oTranscribeModel ? "json" : "verbose_json"
         },
         temperature: openAIOptions.temperature,
         timestamp_granularities: openAIOptions.timestampGranularities
@@ -2621,6 +2650,25 @@ var OpenAITranscriptionModel = class _OpenAITranscriptionModel {
           }
         }
       }
+    } else if (isDiarizationModel) {
+      formData.append("response_format", "diarized_json");
+    }
+    if (chunkingStrategy != null) {
+      formData.append(
+        "chunking_strategy",
+        typeof chunkingStrategy === "string" ? chunkingStrategy : JSON.stringify({
+          type: chunkingStrategy.type,
+          ...chunkingStrategy.threshold != null && {
+            threshold: chunkingStrategy.threshold
+          },
+          ...chunkingStrategy.prefixPaddingMs != null && {
+            prefix_padding_ms: chunkingStrategy.prefixPaddingMs
+          },
+          ...chunkingStrategy.silenceDurationMs != null && {
+            silence_duration_ms: chunkingStrategy.silenceDurationMs
+          }
+        })
+      );
     }
     return {
       formData,
@@ -2628,7 +2676,7 @@ var OpenAITranscriptionModel = class _OpenAITranscriptionModel {
     };
   }
   async doGenerate(options) {
-    var _a2, _b, _c, _d, _e, _f, _g, _h, _i, _j;
+    var _a2, _b, _c, _d, _e, _f, _g, _h, _i, _j, _k;
     if (isRealtimeTranscriptionModelId(this.modelId)) {
       throw new UnsupportedFunctionalityError4({
         functionality: `non-streaming transcription with ${this.modelId}`
@@ -2655,25 +2703,42 @@ var OpenAITranscriptionModel = class _OpenAITranscriptionModel {
       fetch: this.config.fetch
     });
     const language = response.language != null && response.language in languageMap ? languageMap[response.language] : void 0;
+    const diarizedSegments = (_f = response.segments) == null ? void 0 : _f.flatMap(
+      (segment) => "speaker" in segment ? [
+        {
+          text: segment.text,
+          startSecond: segment.start,
+          endSecond: segment.end,
+          speaker: segment.speaker
+        }
+      ] : []
+    );
     return {
       text: response.text,
-      segments: (_i = (_h = (_f = response.segments) == null ? void 0 : _f.map((segment) => ({
+      segments: (_j = (_i = (_g = response.segments) == null ? void 0 : _g.map((segment) => ({
         text: segment.text,
         startSecond: segment.start,
         endSecond: segment.end
-      }))) != null ? _h : (_g = response.words) == null ? void 0 : _g.map((word) => ({
+      }))) != null ? _i : (_h = response.words) == null ? void 0 : _h.map((word) => ({
         text: word.word,
         startSecond: word.start,
         endSecond: word.end
-      }))) != null ? _i : [],
+      }))) != null ? _j : [],
       language,
-      durationInSeconds: (_j = response.duration) != null ? _j : void 0,
+      durationInSeconds: (_k = response.duration) != null ? _k : void 0,
       warnings,
       response: {
         timestamp: currentDate,
         modelId: this.modelId,
         headers: responseHeaders,
         body: rawResponse
+      },
+      ...diarizedSegments != null && diarizedSegments.length > 0 && {
+        providerMetadata: {
+          openai: {
+            segments: diarizedSegments
+          }
+        }
       }
     };
   }
@@ -5821,7 +5886,8 @@ var openaiResponsesReasoningModelIds = [
   "gpt-5.6",
   "gpt-5.6-luna",
   "gpt-5.6-sol",
-  "gpt-5.6-terra"
+  "gpt-5.6-terra",
+  "gpt-6-astra"
 ];
 var openaiResponsesModelIds = [
   "gpt-4.1",