PackageTrack

npm · #4234

@ai-sdk/google

4.0.54vercel/ai ↗

Release timeline

636 releases since 2024
20252026

Releases

  1. 4.0.5426 Aug 2026
    Release notes

    Patch Changes

    • 1f7835c: feat (provider/google, provider/google-vertex): Gemini 3.5 Transcribe support — unary transcription (gemini-3.5-transcribe) via generateContent with language detection, speaker diarization, word timestamps, and custom vocabulary, plus streaming transcription (gemini-3.5-transcribe-live) over the Live API WebSocket with mode: 'VERBATIM' | 'SMART' transcription formatting
    Open source →
  2. 4.0.5326 Aug 2026
    Release notes

    Patch Changes

    Open source →
  3. 4.0.5125 Aug 2026
    Release notes

    Patch Changes

    Open source →
  4. 4.0.5022 Aug 2026
    Release notes

    Patch Changes

    Open source →
  5. 4.0.4921 Aug 2026
    Release notes

    Patch Changes

    • f607a12: chore(google): drop support for Imagen models and their integration following API shutdown
    Open source →
  6. 4.0.4820 Aug 2026
    Release notes

    Patch Changes

    • 6c5a1ed: Inline local JSON Schema references in Google tool and structured-output schemas.
    Open source →
  7. 4.0.4719 Aug 2026
    Release notes

    Patch Changes

    Open source →
    Additional notes

    Patch Changes

    • e6087c9: fix: handle empty string tool call IDs
    • Updated dependencies [e6087c9]
    Open source →
  8. 4.0.4619 Aug 2026
    Release notes

    Patch Changes

    • f69920a: fix(google): use low as the minimum reasoning level for full Gemini Flash 3.7 and later
    Open source →
  9. 4.0.4518 Aug 2026
    Release notes

    Patch Changes

    • bb0cf2e: fix(google): coerce minimal reasoning to low for Gemini 3.7 Flash
    Open source →
  10. 4.0.4413 Aug 2026
    Release notes2 sources agree

    Patch Changes

    • 16650e9: feat(google): add gemini-3.7-flash model
    Open source →
    Additional notes

    Patch Changes

    Open source →
  11. 4.0.4312 Aug 2026
    Release notes

    Patch Changes

    Open source →
    Additional notes

    Patch Changes

    • a062795: fix(openai): support built-in and provider-defined tools in the Responses allowedTools option

      allowedTools emitted every allow-list entry as { type: 'function', name }, but OpenAI identifies built-in tools by type. Allow-listing a declared provider-defined tool (web search, image generation, MCP, custom, ...) therefore failed with Tool choice '<name>' not found in 'tools' parameter. Entries are now derived from the declared tool, including the MCP server label and custom tool name.

      Tools that OpenAI cannot allow-list (the tool search tool, deferred tools, and namespaced tools) are dropped from the allow-list with a warning, and an error is thrown if that would leave the allow-list empty rather than silently sending an unrestricted request.

      Ambiguous names are now reported instead of resolved silently. A name that matches both a declared tool and another tool's provider tool name resolves to the declared tool and warns; a provider tool name shared by several tools in the same request (two MCP servers, for example) is dropped with a warning. A name that matches no declared tool keeps its existing behavior and is now warned about.

    Open source →
    Additional notes

    Patch Changes

    • 8e90283: Preserve forced tool calls when strict function tools are configured.
    Open source →
  12. 4.0.4211 Aug 2026
    Release notes

    Patch Changes

    • b6fff2e: feat(provider/openai): support explicit Responses compaction triggers
    Open source →
    Additional notes

    Patch Changes

    Open source →
  13. 4.0.4111 Aug 2026
    Release notes

    Patch Changes

    • da78d58: fix(google): convert enum values to the Gemini schema format
    • 8a2482d: Preserve Google API error details in APICallError.data.
    Open source →
  14. 4.0.4010 Aug 2026
    Release notes

    Patch Changes

    • 1ffa1d2: feat(xai): speech timestamps, pronunciation replacements, provider metadata, and error parsing

      • Add withTimestamps and replace provider options for text to speech. With withTimestamps, the JSON envelope is decoded and the audio returned as usual, while duration, content type, and character-level alignment are exposed via providerMetadata.xai.
      • Return providerMetadata.xai.traceId (from the x-trace-id response header) on every speech response.
      • Parse the text to speech error shape ({"error":"..."}) so APICallError messages carry xAI's real error detail instead of the HTTP reason phrase.
    Open source →
    Additional notes

    Patch Changes

    Open source →
  15. 4.0.397 Aug 2026
    Release notes

    Patch Changes

    • 4579b08: Preserve Anthropic server-tool caller metadata in multi-turn conversations.
    Open source →
    Additional notes

    Patch Changes

    • 646c86e: fix(provider/xai): report video moderation blocks and missing URLs as an error status instead of throwing
    Open source →
    Additional notes

    Patch Changes

    Open source →
  16. 4.0.387 Aug 2026
    Release notes

    Patch Changes

    • 484293f: feat(xai): support the priority service tier on chat and responses
    Open source →
    Additional notes

    Patch Changes

    Open source →
  17. 4.0.377 Aug 2026
    Release notes

    Patch Changes

    • a4d386d: feat(xai): add the Grok 4.6 model IDs and support its xhigh reasoning effort
    Open source →
    Additional notes

    Patch Changes

    • bbd9b31: chore: rename *TranslationModel and its related types to *SpeechTranslationModel for consistency
    Open source →
  18. 4.0.366 Aug 2026
    Release notes

    Patch Changes

    Open source →
  19. 4.0.356 Aug 2026
    Release notes

    Patch Changes

    Open source →
  20. 4.0.344 Aug 2026
    Release notes

    Patch Changes

    Open source →
  21. 4.0.334 Aug 2026
    Release notes

    Patch Changes

    Open source →
  22. 4.0.323 Aug 2026
    Release notes

    Patch Changes

    • 79e133c: async APIs for generateVideo (poll, webhook)

      Adds an asynchronous start/status flow to the experimental video model interface (VideoModelV4): models may now implement doStart, doStatus, and handleWebhookOption instead of (or in addition to) doGenerate, and experimental_generateVideo accepts poll and webhook options to orchestrate completion via polling or webhooks. Polling configuration can use a custom delay implementation for durable workflow compatibility.

    • Updated dependencies [79e133c]

    Open source →
  23. 4.0.3131 Jul 2026
    Release notes

    Patch Changes

    • 5fc7da5: chore: centralize empty language model usage creation in provider utilities.
    • Updated dependencies [5fc7da5]
    • Updated dependencies [93b2acd]
    Open source →
  24. 4.0.3031 Jul 2026
    Release notes

    Patch Changes

    Open source →
  25. 4.0.2930 Jul 2026
    Release notes

    Patch Changes

    • d8210b6: chore: centralize record type guards in provider-utils
    • Updated dependencies [d8210b6]
    • Updated dependencies [b192878]
    Open source →
  26. 4.0.2829 Jul 2026
    Release notes

    Patch Changes

    • Updated dependencies [1659cd5]
    • Updated dependencies [6a5bdff]
    Open source →
  27. 4.0.2728 Jul 2026
    Release notes

    Patch Changes

    • d2d9324: Forward topK through Google Interactions requests and warn when unsupported frequency or presence penalties are provided.
    • 8bedb2c: Allow fetch to derive the content length for Google file upload request bodies.
    Open source →
  28. 4.0.2628 Jul 2026
    Release notes

    Patch Changes

    • c49380c: feat: add experimental streaming speech translation models (openai.translation('gpt-realtime-translate') over the OpenAI Realtime translations WebSocket and google.translation('gemini-3.5-live-translate-preview') over the Gemini Live API). connectToWebSocket in @ai-sdk/provider-utils now passes close code and reason to onClose (additive, optional parameter).
    • Updated dependencies [0c464d9]
    • Updated dependencies [c49380c]
    Open source →
  29. 4.0.2527 Jul 2026
    Release notes

    Patch Changes

    Open source →
  30. 4.0.2424 Jul 2026
    Release notes

    Patch Changes

    • c57a353: fix(google): omit unsupported function call IDs
    Open source →
  31. 4.0.2323 Jul 2026
    Release notes

    Patch Changes

    • f126649: feat(provider/google): default unknown Gemini model IDs to the newest supported capabilities
    Open source →
  32. 4.0.2222 Jul 2026
    Release notes

    Patch Changes

    • 66b7151: fix(provider/google): preserve Gemini Live lifecycle events
    • 5e5453c: Avoid missing thought-signature warnings and skip-validator injection for valid unsigned Gemini 3 parallel function calls in the same model response.
    Open source →
  33. 4.0.2121 Jul 2026
    Release notes

    Patch Changes

    • 7c16f21: feat(google): add gemini-3.6-flash and gemini-3.5-flash-lite models
    Open source →
  34. 4.0.2021 Jul 2026
    Release notes

    Patch Changes

    • Updated dependencies [02ffdcb]
    • Updated dependencies [76cb673]
    Open source →
  35. 4.0.1920 Jul 2026
    Release notes

    Patch Changes

    • a70b027: fix(provider/google): associate multiple code execution results with their tool call
    • a3ce307: fix(provider/google): surface Gemini responseId as response-metadata (stream) and response.id (generate)
    Open source →
  36. 4.0.1817 Jul 2026
    Release notes

    Patch Changes

    Open source →
  37. 4.0.1715 Jul 2026
    Release notes

    Patch Changes

    • 5b4a299: fix(provider/google): forward Vertex-only imageConfig options (personGeneration, prominentPeople, imageOutputOptions)
    Open source →
  38. 4.0.1614 Jul 2026
    Release notes

    Patch Changes

    • 662ddfc: Allow google.interactions agent requests to include supported tools, including file_search.
    Open source →
  39. 4.0.1514 Jul 2026
    Release notes

    Patch Changes

    Open source →
  40. 4.0.1413 Jul 2026
    Release notes

    Patch Changes

    • 4be62c1: fix(provider-utils): validate provider-response URLs in getFromApi

      getFromApi now has a validateUrl flag. It is optional so existing callers keep compiling (omitting it behaves like false, i.e. no validation), but all AI SDK provider packages set it explicitly at every call site so each one makes a visible trust decision. When true, the URL is routed through fetchWithValidatedRedirects — the same guard used by downloadBlob — which rejects private/loopback/link-local targets, re-validates every redirect hop, strips proxy/metadata/cookie request headers, and drops all caller headers except the user-agent on cross-origin redirects (custom API-key headers must not follow a redirect off-origin any more than Authorization may); blocked URLs throw DownloadError. It is enabled at the image/video/audio download and polling call sites where the URL comes from a provider response body; URLs built from developer-configured endpoints pass validateUrl: false and are unaffected.

      A new optional credentialedOrigin withholds caller headers unless the URL is same-origin with it, so the API key is not sent to a response-supplied host on a different origin.

      A new optional trustedOrigin exempts URLs (and redirect hops) that are same-origin with the developer-configured provider endpoint from target validation, so self-hosted and localhost deployments whose response URLs point back at the configured host keep working; all other hops are still validated.

      Also closes range gaps in validateDownloadUrl (IPv4 224.0.0.0/4 multicast and the TEST-NET documentation ranges 192.0.2.0/24, 198.51.100.0/24, 203.0.113.0/24; IPv6 documentation ranges 2001:db8::/32 and 3fff::/20), and follows only the fetch-spec redirect status codes (301/302/303/307/308) — a Location header on any other status is not followed. This guard performs string/literal checks only and does not resolve DNS; hostnames that resolve to private addresses and DNS rebinding remain out of scope and must be constrained at the network layer (or by injecting a Node fetch that pins the resolved IP at connect time) for server deployments handling untrusted URLs. See contributing/secure-url-handling.md.

    • Updated dependencies [4be62c1]

    • Updated dependencies [7805e4a]

    • Updated dependencies [cd12954]

    Open source →
  41. 4.0.1210 Jul 2026
    Release notes

    Patch Changes

    • e40118c: Forward text file references as documents when using the Google Interactions API.
    Open source →
  42. 4.0.119 Jul 2026
    Release notes

    Patch Changes

    • 17d66c5: Fix Google tool result conversion to send file data as inline data instead of JSON text on the legacy tool-result path.
    • 96d40bc: Expand standalone Google threshold provider options into safety settings.
    • 0f93c57: feat (video): support video (not just image) reference inputs in inputReferences for reference-to-video generation
    • Updated dependencies [0f93c57]
    Open source →
  43. 4.0.108 Jul 2026
    Release notes

    Patch Changes

    Open source →
  44. 4.0.97 Jul 2026
    Release notes

    Patch Changes

    • 7401c2c: Pass documented Gemini external HTTPS file URLs through without downloading them.
    Open source →
  45. 4.0.82 Jul 2026
    Release notes

    Patch Changes

    • 5c5c0f5: Add experimental streaming transcription support for transcription models, including OpenAI gpt-realtime-whisper and xAI WebSocket STT.
    • Updated dependencies [5c5c0f5]
    Open source →
  46. 4.0.72 Jul 2026
    Release notes

    Patch Changes

    • c6f5e62: Prevent prototype pollution when synchronously parsing provider JSON inputs and expose secureJsonParse from provider-utils.
    • bd8d172: Fix Google embedding batch size to respect the Gemini API limit of 100 requests per batch.
    • Updated dependencies [c6f5e62]
    Open source →
  47. 4.0.62 Jul 2026
    Release notes

    Patch Changes

    • d20f0dc: Add vertex.interactions() for the Gemini Interactions API on Vertex AI. Targets the location-scoped .../locations/{region}/interactions resource using the existing Vertex OAuth credentials, enabling multimodal-output models such as gemini-omni-flash-preview (video output) through Vertex. The GoogleInteractionsLanguageModel is now exported from @ai-sdk/google/internal for provider reuse.
    Open source →
  48. 4.0.51 Jul 2026
    Release notes

    Patch Changes

    Open source →
  49. 4.0.41 Jul 2026
    Release notes

    Patch Changes

    • dc1eb8d: Support Gemini Interactions video output. Parse video output blocks from the Google Interactions API into file parts (buffered and streaming), and surface the per-modality output token breakdown via providerMetadata.google.outputTokensByModality.
    Open source →
  50. 4.0.330 Jun 2026
    Release notes

    Patch Changes

    • 0274f34: feat (video): add first-class frameImages and inputReferences call options for video generation
    • Updated dependencies [0274f34]
    Open source →
  51. 4.0.227 Jun 2026
    Release notes

    Patch Changes

    Open source →
  52. 4.0.127 Jun 2026
    Release notes

    Patch Changes

    • ba6d510: chore: fix deprecated use of zod .passthrough()
    Open source →
  53. 4.0.025 Jun 2026
    Release notes

    Major Changes

    • a3757d7: chore(provider/google): remove useless GenerativeAI affix from types and classes for consistency

    • f7d4f01: feat(provider): add support for reasoning-file type for files that are part of reasoning

    • ef992f8: Remove CommonJS exports from all packages. All packages are now ESM-only ("type": "module"). Consumers using require() must switch to ESM import syntax.

    • c29a26f: feat(provider): add support for provider references and uploading files as supported per provider

    • 3887c70: feat(provider): add new top-level reasoning parameter to spec and support it in generateText and streamText

    • 8359612: Start v7 pre-release

    • 04e9009: chore: make provider implementations code patterns more consistent, including renaming certain exported symbols

      For all externally exported symbols that were renamed, the old names continue to work via deprecated aliases.

    Patch Changes

    • 7f04802: feat(provider/google): add support for managed agents in the Interactions API

    • 38fc777: Add AI Gateway hint to provider READMEs

    • b71c0d7: feat(provider/google): support Google search grounding when using generateImage with Gemini

    • 6190649: chore(provider/google): remove obsolete Google image model

    • 55db546: fix(provider/google): fix Gemini service tier enum after upstream update

    • 9a0a618: fix(google): fix serviceTier to be correctly formatted for Vertex API

    • 00a0f36: feat(google, google-vertex): added gemini-embedding-2, deep-research-max-preview-04-2026 and deep-research-preview-04-2026

    • 9715ec7: feat(provider/google): add support for service tier parameter

    • 41da50c: fix(provider/google): support functionCall.id when returned by Gemini API and provide matching functionResponse.id

    • add4326: fix(provider/google): correct JSDoc for multimodal embedding content option

    • a8d70b6: fix(google): auto-inject skip_thought_signature_validator for Gemini 3 tool-call replays without a signature

    • 947cdab: Add Google realtime Live Translation provider options for gemini-3.5-live-translate-preview.

    • 4e825f3: feat(google): update Interactions API implementation to cater for upstream breaking changes coming May 26

    • b563707: feat(provider/google): add Gemini text-to-speech (speech) model support

    • a05109d: feat(provider/google): preserve per-modality token details in usage data

    • cfca634: fix(google): emit Vertex no-args streaming tool calls and preserve thoughtSignature

      Vertex emits a no-args function call as a single chunk shaped { functionCall: { name: 'X' } } with no args, no partialArgs, and no willContinue. The streaming parser had no branch for this shape, so the call was dropped along with any thoughtSignature it carried. For Gemini 3 thinking models this caused the next multi-turn step to 400 with missing thought_signature. The unary (doGenerate) path had the same drop.

      Both paths now emit the call as a complete tool call with '{}' input and propagate thoughtSignature provider metadata.

      Fixes #14847.

    • c9c4661: fix(provider/google): preserve groundingMetadata and urlContextMetadata when they arrive in a stream chunk before the finishReason chunk

    • 045d2e8: fix(google): read serviceTier from usageMetadata.serviceTier in both generate and stream paths

      The previous implementation read serviceTier from the x-gemini-service-tier response header, which is only populated on non-streaming responses. Gemini streaming includes the value in usageMetadata.serviceTier on every chunk, so providerMetadata.google.serviceTier was always null for streams. Read from usageMetadata for both paths instead.

    • 19b95f9: fix(google): use VALIDATED function calling mode when any tool has strict:true

    • 2ce3c65: feat(provider/google-vertex): add Gemini text-to-speech (speech) model support

    • 5878b40: fix(google): prevent prototype pollution when streaming tool args

    • 46d1149: chore(provider-utils,google): fix grammar errors in error and warning messages

    • 6a26901: feat(google): add fileData support to embedding model

    • 01fa606: feat(provider/google): support combining built-in tools with function calling on Gemini 3

    • 5036db8: feat(google-vertex): add support for streaming tool arguments input

    • 9f0e36c: trigger release for all packages after provenance setup

    • a2609df: fix(google): fix streaming tool call args

    • ab43029: feat(provider/google): support multimodal content parts in embedding provider options

    • 82288b0: feat(provider/google): add gemini-embedding-2-preview and fix multimodal embedding support with embedMany

    • b04e23e: feat(provider/google): add support for the Gemini Interactions API

    • 58a2ad7: fix: more precise default message for tool execution denial

    • e59176c: chore(google): update v3 specs to v4

    • ebbb0f2: fix(provider/google): fix lack of image consistency when using Interactions API in stateless mode

    • aeda373: fix: only send provider credentials to same-origin response-supplied URLs

      Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as polling_url, urls.get, result_url, result.sample, or video.uri) and reused the authenticated headers — or appended ?key=<API_KEY> — on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.

      A new isSameOrigin helper is added to @ai-sdk/provider-utils, and the affected fetches in @ai-sdk/black-forest-labs, @ai-sdk/fireworks, @ai-sdk/replicate, @ai-sdk/gladia, @ai-sdk/fal, and @ai-sdk/google now attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.

    • 7fc6bd6: Raise minimum supported Node.js version to 22. Supported versions: 22, 24, and 26.

    • 0c4c275: trigger initial canary release

    • bdb9ea1: chore(google): remove now obsolete Interactions API Api-Revision header

    • db394ab: feat(provider/google): support cancelling long-running Interactions API agents via AbortSignal, and process their intermittent stream

    • ce769dd: feat(provider): add experimental Realtime API support for voice conversations

      Adds first-class support for realtime (speech-to-speech) APIs:

      • Experimental_RealtimeModelV4 spec in @ai-sdk/provider with normalized event types and factory
      • OpenAI, Google, and xAI realtime provider implementations
      • openai.experimental_realtime() / google.experimental_realtime() / xai.experimental_realtime() work in both server and browser
      • .getToken() static method on each provider for server-side ephemeral token creation
      • experimental_getRealtimeToolDefinitions helper for provider session tool definitions
      • experimental_useRealtime hook in @ai-sdk/react returning UIMessage[] (aligned with useChat), with onToolCall and addToolOutput for client-driven tool execution
      • inputAudioTranscription session config for showing transcribed user audio messages when supported by the provider

    • 5b7e7c2: fix(google-vertex): don't send streamFunctionCallArguments for unary API calls and change default to false

    • 2edd14e: fix(provider/google): correctly mark reasoning files as such and fix related multi-turn errors

    • 9bd6512: feat(provider): change file part data property to be tagged with a type and remove the image part type

    • 258c093: chore: ensure consistent import handling and avoid import duplicates or cycles

    • 546cefe: feat(provider/google): add gemini-3.5-flash

    • 5463d0d: feat(provider): align tool result output content file part types with top-level message file part types

    • 55f0938: chore(provider/google): update available models

    • b8396f0: trigger initial beta release

    • 84f36e0: fix(google): omit passing includeServerSideToolInvocations for Vertex tool_config

    • 90e2d8a: chore: fix unused vars not being flagged by our lint tooling

    • 4dac142: feat(google): add new finishMessage field in providerMetadata

    • aeea161: feat(google): read serviceTier from x-gemini-service-tier response header in Gemini API and use PayGo for Vertex

    • 18c1970: feat(provider/google): Add multimodal tool-result support for Google function responses.

      Tool results with output.type = 'content' now map media parts into functionResponse.parts for Google models, including image-data, file-data, and base64 data: URLs in URL-style content parts. Remote HTTP(S) URLs in URL-style tool-result parts are not supported.

    • b3976a2: Add workflow serialization support to all provider models.

      @ai-sdk/provider-utils: New serializeModel() helper that extracts only serializable properties from a model instance, filtering out functions and objects containing functions. Third-party provider authors can use this to add workflow support to their own models.

      All providers: headers is now optional in provider config types. This is non-breaking — existing code that passes headers continues to work. Custom provider implementations that construct model configs manually can now omit headers, which is useful when models are deserialized from a workflow step boundary where auth is provided separately.

      All provider model classes now include WORKFLOW_SERIALIZE and WORKFLOW_DESERIALIZE static methods, enabling them to cross workflow step boundaries without serialization errors.

    • ff5eba1: feat: roll image-* tool output types into their equivalent file-* types

    Open source →
  54. 4.0.0-canary.8112 Jun 2026pre-release
    Release notes

    Patch Changes

    • 5878b40: fix(google): prevent prototype pollution when streaming tool args

    • aeda373: fix: only send provider credentials to same-origin response-supplied URLs

      Several provider clients followed a URL taken from the provider's API response (a polling/status URL or a final media URL such as polling_url, urls.get, result_url, result.sample, or video.uri) and reused the authenticated headers — or appended ?key=<API_KEY> — on that request. Because the host of the response-supplied URL was never validated, the long-lived API key was sent to whatever host the response named (a CDN in the benign case, or an attacker-chosen host if the provider response was tampered with), allowing credential exfiltration.

      A new isSameOrigin helper is added to @ai-sdk/provider-utils, and the affected fetches in @ai-sdk/black-forest-labs, @ai-sdk/fireworks, @ai-sdk/replicate, @ai-sdk/gladia, @ai-sdk/fal, and @ai-sdk/google now attach credentials only when the followed URL is same-origin with the provider's configured API origin. Requests to a foreign origin are made without the credential.

    • Updated dependencies [aeda373]

    • Updated dependencies [375fdd7]

    • Updated dependencies [b4507d5]

    Open source →
  55. 4.0.0-canary.8011 Jun 2026pre-release
    Release notes

    Patch Changes

    Open source →
  56. 4.0.0-canary.795 Jun 2026pre-release
    Release notes

    Patch Changes

    • ce769dd: feat(provider): add experimental Realtime API support for voice conversations

      Adds first-class support for realtime (speech-to-speech) APIs:

      • Experimental_RealtimeModelV4 spec in @ai-sdk/provider with normalized event types and factory
      • OpenAI, Google, and xAI realtime provider implementations
      • openai.experimental_realtime() / google.experimental_realtime() / xai.experimental_realtime() work in both server and browser
      • .getToken() static method on each provider for server-side ephemeral token creation
      • experimental_getRealtimeToolDefinitions helper for provider session tool definitions
      • experimental_useRealtime hook in @ai-sdk/react returning UIMessage[] (aligned with useChat), with onToolCall and addToolOutput for client-driven tool execution
      • inputAudioTranscription session config for showing transcribed user audio messages when supported by the provider

    • Updated dependencies [ce769dd]

    Open source →
  57. 4.0.0-canary.784 Jun 2026pre-release
    Release notes

    Patch Changes

    • 2ce3c65: feat(provider/google-vertex): add Gemini text-to-speech (speech) model support
    Open source →
  58. 4.0.0-canary.774 Jun 2026pre-release
    Release notes

    Patch Changes

    • Updated dependencies [ee798eb]
    • Updated dependencies [daf6637]
    Open source →
  59. 4.0.0-canary.762 Jun 2026pre-release
    Release notes

    Patch Changes

    • b563707: feat(provider/google): add Gemini text-to-speech (speech) model support
    Open source →
  60. 4.0.0-canary.7530 May 2026pre-release
    Release notes

    Patch Changes

    • 00a0f36: feat(google, google-vertex): added gemini-embedding-2, deep-research-max-preview-04-2026 and deep-research-preview-04-2026
    Open source →