@ai-sdk/google 4.0.101 → 4.0.102

package/src/transcription/google-transcription-model-options.ts

@@ -1,3 +1,8 @@
+import {
+  lazySchema,
+  zodSchema,
+  type InferSchema,
+} from '@ai-sdk/provider-utils';
 import { z } from 'zod/v4';
 
 export type GoogleTranscriptionModelId =
@@ -10,41 +15,45 @@ export type GoogleTranscriptionModelId =
  * live (`gemini-3.5-transcribe-live`) transcription. Maps onto Google's
  * `AudioTranscriptionConfig`.
  */
-export const googleTranscriptionModelOptions = z.object({
-  /**
-   * BCP-47 language codes providing hints about the languages present in the
-   * audio. If omitted or empty, defaults to automatic language detection.
-   */
-  languageCodes: z.array(z.string()).optional(),
+export const googleTranscriptionModelOptions = lazySchema(() =>
+  zodSchema(
+    z.object({
+      /**
+       * BCP-47 language codes providing hints about the languages present in the
+       * audio. If omitted or empty, defaults to automatic language detection.
+       */
+      languageCodes: z.array(z.string()).optional(),
 
-  /**
-   * Custom vocabulary phrases, which bias the speech recognition model
-   * toward recognizing specific terms.
-   */
-  customVocabulary: z.array(z.string()).optional(),
+      /**
+       * Custom vocabulary phrases, which bias the speech recognition model
+       * toward recognizing specific terms.
+       */
+      customVocabulary: z.array(z.string()).optional(),
 
-  /**
-   * Enables word-level timestamp generation.
-   */
-  wordTimestamp: z.boolean().optional(),
+      /**
+       * Enables word-level timestamp generation.
+       */
+      wordTimestamp: z.boolean().optional(),
 
-  /**
-   * Enables speaker diarization.
-   */
-  diarization: z.boolean().optional(),
+      /**
+       * Enables speaker diarization.
+       */
+      diarization: z.boolean().optional(),
 
-  /**
-   * Transcription output formatting mode.
-   *
-   * - `VERBATIM` (default): exact literal transcript preserving filler
-   *   words, repetitions, and false starts.
-   * - `SMART`: cleans up and structures the transcript in real time —
-   *   disfluency removal, inline self-corrections, structured formatting
-   *   (lists, numbers, dates, paragraph breaks), and grammar/casing polish.
-   */
-  mode: z.enum(['SMART', 'VERBATIM']).optional(),
-});
+      /**
+       * Transcription output formatting mode.
+       *
+       * - `VERBATIM` (default): exact literal transcript preserving filler
+       *   words, repetitions, and false starts.
+       * - `SMART`: cleans up and structures the transcript in real time —
+       *   disfluency removal, inline self-corrections, structured formatting
+       *   (lists, numbers, dates, paragraph breaks), and grammar/casing polish.
+       */
+      mode: z.enum(['SMART', 'VERBATIM']).optional(),
+    }),
+  ),
+);
 
-export type GoogleTranscriptionModelOptions = z.infer<
+export type GoogleTranscriptionModelOptions = InferSchema<
   typeof googleTranscriptionModelOptions
 >;

package/src/transcription/google-transcription-model.ts

@@ -7,6 +7,8 @@ import {
   type TranscriptionModelV4,
 } from '@ai-sdk/provider';
 import {
+  lazySchema,
+  zodSchema,
   combineHeaders,
   connectToWebSocket,
   convertToBase64,
@@ -684,33 +686,38 @@ function validateLiveInputAudioFormat(
   }
 }
 
-const googleInteractionsWordAnnotationSchema = z.object({
-  type: z.string().nullish(),
-  text: z.string().nullish(),
-  speaker: z.string().nullish(),
-  start_offset: z.string().nullish(),
-  end_offset: z.string().nullish(),
-});
-
-const googleInteractionsTranscriptionResponseSchema = z.object({
-  status: z.string().nullish(),
-  steps: z
-    .array(
-      z.object({
-        type: z.string().nullish(),
-        content: z
-          .array(
-            z.object({
-              type: z.string().nullish(),
-              text: z.string().nullish(),
-              annotations: z
-                .array(googleInteractionsWordAnnotationSchema)
-                .nullish(),
-            }),
-          )
-          .nullish(),
-      }),
-    )
-    .nullish(),
-  usage: z.record(z.string(), z.json()).nullish(),
-});
+const googleInteractionsWordAnnotationSchema = () =>
+  z.object({
+    type: z.string().nullish(),
+    text: z.string().nullish(),
+    speaker: z.string().nullish(),
+    start_offset: z.string().nullish(),
+    end_offset: z.string().nullish(),
+  });
+
+const googleInteractionsTranscriptionResponseSchema = lazySchema(() =>
+  zodSchema(
+    z.object({
+      status: z.string().nullish(),
+      steps: z
+        .array(
+          z.object({
+            type: z.string().nullish(),
+            content: z
+              .array(
+                z.object({
+                  type: z.string().nullish(),
+                  text: z.string().nullish(),
+                  annotations: z
+                    .array(googleInteractionsWordAnnotationSchema())
+                    .nullish(),
+                }),
+              )
+              .nullish(),
+          }),
+        )
+        .nullish(),
+      usage: z.record(z.string(), z.json()).nullish(),
+    }),
+  ),
+);