@ai-sdk/google 4.0.0-canary.74 → 4.0.0-canary.76

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @ai-sdk/google
 
+## 4.0.0-canary.76
+
+### Patch Changes
+
+- b563707: feat(provider/google): add Gemini text-to-speech (speech) model support
+
+## 4.0.0-canary.75
+
+### Patch Changes
+
+- 00a0f36: feat(google, google-vertex): added `gemini-embedding-2`, `deep-research-max-preview-04-2026` and `deep-research-preview-04-2026`
+
 ## 4.0.0-canary.74
 
 ### Patch Changes

package/dist/index.d.ts

@@ -1,6 +1,6 @@
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { InferSchema, FetchFunction } from '@ai-sdk/provider-utils';
-import { ProviderV4, LanguageModelV4, ImageModelV4, EmbeddingModelV4, Experimental_VideoModelV4, FilesV4 } from '@ai-sdk/provider';
+import { ProviderV4, LanguageModelV4, ImageModelV4, EmbeddingModelV4, Experimental_VideoModelV4, SpeechModelV4, FilesV4 } from '@ai-sdk/provider';
 
 declare const googleErrorDataSchema: _ai_sdk_provider_utils.LazySchema<{
     error: {
@@ -11,7 +11,7 @@ declare const googleErrorDataSchema: _ai_sdk_provider_utils.LazySchema<{
 }>;
 type GoogleErrorData = InferSchema<typeof googleErrorDataSchema>;
 
-type GoogleModelId = 'gemini-2.0-flash' | 'gemini-2.0-flash-001' | 'gemini-2.0-flash-lite' | 'gemini-2.0-flash-lite-001' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-2.5-flash-image' | 'gemini-2.5-flash-lite' | 'gemini-2.5-flash-preview-tts' | 'gemini-2.5-pro-preview-tts' | 'gemini-2.5-flash-native-audio-latest' | 'gemini-2.5-flash-native-audio-preview-09-2025' | 'gemini-2.5-flash-native-audio-preview-12-2025' | 'gemini-2.5-computer-use-preview-10-2025' | 'gemini-3-pro-preview' | 'gemini-3-pro-image-preview' | 'gemini-3-flash-preview' | 'gemini-3.1-pro-preview' | 'gemini-3.1-pro-preview-customtools' | 'gemini-3.1-flash-image-preview' | 'gemini-3.1-flash-lite-preview' | 'gemini-3.1-flash-tts-preview' | 'gemini-3.5-flash' | 'gemini-pro-latest' | 'gemini-flash-latest' | 'gemini-flash-lite-latest' | 'deep-research-pro-preview-12-2025' | 'nano-banana-pro-preview' | 'aqa' | 'gemini-robotics-er-1.5-preview' | 'gemma-3-1b-it' | 'gemma-3-4b-it' | 'gemma-3n-e4b-it' | 'gemma-3n-e2b-it' | 'gemma-3-12b-it' | 'gemma-3-27b-it' | (string & {});
+type GoogleModelId = 'gemini-2.0-flash' | 'gemini-2.0-flash-001' | 'gemini-2.0-flash-lite' | 'gemini-2.0-flash-lite-001' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-2.5-flash-image' | 'gemini-2.5-flash-lite' | 'gemini-2.5-flash-preview-tts' | 'gemini-2.5-pro-preview-tts' | 'gemini-2.5-flash-native-audio-latest' | 'gemini-2.5-flash-native-audio-preview-09-2025' | 'gemini-2.5-flash-native-audio-preview-12-2025' | 'gemini-2.5-computer-use-preview-10-2025' | 'gemini-3-pro-preview' | 'gemini-3-pro-image-preview' | 'gemini-3-flash-preview' | 'gemini-3.1-pro-preview' | 'gemini-3.1-pro-preview-customtools' | 'gemini-3.1-flash-image-preview' | 'gemini-3.1-flash-lite-preview' | 'gemini-3.1-flash-tts-preview' | 'gemini-3.5-flash' | 'gemini-pro-latest' | 'gemini-flash-latest' | 'gemini-flash-lite-latest' | 'deep-research-pro-preview-12-2025' | 'deep-research-max-preview-04-2026' | 'deep-research-preview-04-2026' | 'nano-banana-pro-preview' | 'aqa' | 'gemini-robotics-er-1.5-preview' | 'gemma-3-1b-it' | 'gemma-3-4b-it' | 'gemma-3n-e4b-it' | 'gemma-3n-e2b-it' | 'gemma-3-12b-it' | 'gemma-3-27b-it' | (string & {});
 declare const googleLanguageModelOptions: _ai_sdk_provider_utils.LazySchema<{
     responseModalities?: ("TEXT" | "IMAGE")[] | undefined;
     thinkingConfig?: {
@@ -231,7 +231,7 @@ declare const googleImageModelOptionsSchema: _ai_sdk_provider_utils.LazySchema<{
 }>;
 type GoogleImageModelOptions = InferSchema<typeof googleImageModelOptionsSchema>;
 
-type GoogleEmbeddingModelId = 'gemini-embedding-001' | 'gemini-embedding-2-preview' | (string & {});
+type GoogleEmbeddingModelId = 'gemini-embedding-001' | 'gemini-embedding-2' | 'gemini-embedding-2-preview' | (string & {});
 declare const googleEmbeddingModelOptions: _ai_sdk_provider_utils.LazySchema<{
     outputDimensionality?: number | undefined;
     taskType?: "SEMANTIC_SIMILARITY" | "CLASSIFICATION" | "CLUSTERING" | "RETRIEVAL_DOCUMENT" | "RETRIEVAL_QUERY" | "QUESTION_ANSWERING" | "FACT_VERIFICATION" | "CODE_RETRIEVAL_QUERY" | undefined;
@@ -265,6 +265,21 @@ type GoogleVideoModelOptions = {
 
 type GoogleVideoModelId = 'veo-3.1-fast-generate-preview' | 'veo-3.1-generate-preview' | 'veo-3.1-generate' | 'veo-3.1-lite-generate-preview' | 'veo-3.0-generate-001' | 'veo-3.0-fast-generate-001' | 'veo-2.0-generate-001' | (string & {});
 
+type GoogleSpeechModelId = 'gemini-2.5-flash-preview-tts' | 'gemini-2.5-pro-preview-tts' | 'gemini-3.1-flash-tts-preview' | (string & {});
+declare const googleSpeechProviderOptionsSchema: _ai_sdk_provider_utils.LazySchema<{
+    multiSpeakerVoiceConfig?: {
+        speakerVoiceConfigs: {
+            speaker: string;
+            voiceConfig: {
+                prebuiltVoiceConfig: {
+                    voiceName: string;
+                };
+            };
+        }[];
+    } | undefined;
+}>;
+type GoogleSpeechModelOptions = InferSchema<typeof googleSpeechProviderOptionsSchema>;
+
 type GoogleFilesUploadOptions = {
     displayName?: string | null;
     pollIntervalMs?: number | null;
@@ -517,6 +532,14 @@ interface GoogleProvider extends ProviderV4 {
      * Creates a model for video generation.
      */
     videoModel(modelId: GoogleVideoModelId): Experimental_VideoModelV4;
+    /**
+     * Creates a model for speech generation (text-to-speech).
+     */
+    speech(modelId: GoogleSpeechModelId): SpeechModelV4;
+    /**
+     * Creates a model for speech generation (text-to-speech).
+     */
+    speechModel(modelId: GoogleSpeechModelId): SpeechModelV4;
     files(): FilesV4;
     /**
      * Creates a language model targeting the Gemini Interactions API
@@ -574,4 +597,4 @@ declare const google: GoogleProvider;
 
 declare const VERSION: string;
 
-export { type GoogleEmbeddingModelOptions, type GoogleErrorData, type GoogleFilesUploadOptions, type GoogleEmbeddingModelOptions as GoogleGenerativeAIEmbeddingProviderOptions, type GoogleImageModelOptions as GoogleGenerativeAIImageProviderOptions, type GoogleProvider as GoogleGenerativeAIProvider, type GoogleProviderMetadata as GoogleGenerativeAIProviderMetadata, type GoogleLanguageModelOptions as GoogleGenerativeAIProviderOptions, type GoogleProviderSettings as GoogleGenerativeAIProviderSettings, type GoogleVideoModelId as GoogleGenerativeAIVideoModelId, type GoogleVideoModelOptions as GoogleGenerativeAIVideoProviderOptions, type GoogleImageModelOptions, type GoogleInteractionsAgentName, type GoogleInteractionsModelId, type GoogleInteractionsProviderMetadata, type GoogleLanguageModelInteractionsOptions, type GoogleLanguageModelOptions, type GoogleProvider, type GoogleProviderMetadata, type GoogleProviderSettings, type GoogleVideoModelId, type GoogleVideoModelOptions, VERSION, createGoogle, createGoogle as createGoogleGenerativeAI, google };
+export { type GoogleEmbeddingModelOptions, type GoogleErrorData, type GoogleFilesUploadOptions, type GoogleEmbeddingModelOptions as GoogleGenerativeAIEmbeddingProviderOptions, type GoogleImageModelOptions as GoogleGenerativeAIImageProviderOptions, type GoogleProvider as GoogleGenerativeAIProvider, type GoogleProviderMetadata as GoogleGenerativeAIProviderMetadata, type GoogleLanguageModelOptions as GoogleGenerativeAIProviderOptions, type GoogleProviderSettings as GoogleGenerativeAIProviderSettings, type GoogleVideoModelId as GoogleGenerativeAIVideoModelId, type GoogleVideoModelOptions as GoogleGenerativeAIVideoProviderOptions, type GoogleImageModelOptions, type GoogleInteractionsAgentName, type GoogleInteractionsModelId, type GoogleInteractionsProviderMetadata, type GoogleLanguageModelInteractionsOptions, type GoogleLanguageModelOptions, type GoogleProvider, type GoogleProviderMetadata, type GoogleProviderSettings, type GoogleSpeechModelId, type GoogleSpeechModelOptions, type GoogleVideoModelId, type GoogleVideoModelOptions, VERSION, createGoogle, createGoogle as createGoogleGenerativeAI, google };