gemini_live 2026.11.19
gemini_live: ^2026.11.19 copied to clipboard
A Flutter package for the Gemini Live API, enabling real-time, multimodal conversations with Google's Gemini models.
2026.11.19 #
Added & Fixed (Upstream Parity with js-genai 3.6.1 & python-genai 3.6.1) #
- Gemini 4 Neon Model Identifier (
InteractionModels.gemini4Neon):- Added
InteractionModels.gemini4Neon('gemini-4-neon') for frontier-level intelligence with fast end-to-end task completion across complex software engineering, analytical, and science workflows.
- Added
- Public File Processing Metadata on
Part&FunctionResponsePart(DocumentMetadata,SpreadsheetMetadata,AudioMetadata,VideoMetadata.contentLayers):- Added
DocumentMetadata(DocumentMetadataContentLayer:PAGE_IMAGE,PAGE_TEXT),SpreadsheetMetadata(SpreadsheetMetadataContentLayer:DATA,FORMULAS,VISUAL),AudioMetadata, andVideoMetadata.contentLayers(VideoMetadataContentLayer:FRAMES,AUDIO,TRANSCRIPT). - Wired
documentMetadata,spreadsheetMetadata, andaudioMetadataonPart, andmediaResolution,videoMetadata,documentMetadata,spreadsheetMetadata, andaudioMetadataonFunctionResponsePart(includingfromBytesandfromUri).
- Added
- Live Interactions Auth Tokens, Wire Events & Deferred MCP Tool Loading:
- Added
AuthTokensService.createForInteraction()(POST /{api_version}/interactions/{id}/auth_tokens) andAuthTokensService.deleteForInteraction()(DELETE /{api_version}/interactions/{id}/auth_tokens/{token}), along withInteractionAuthTokenandInteractionAuthTokenCreateParams. - Added Live Interactions & World Simulation event models (
CreateInteractionEvent,ConnectInteractionEvent,CompleteInteractionEvent,CancelInteractionEvent,DisconnectEvent,LiveInteractionCreatedEvent,InteractionConnectedEvent,LiveInteractionCompletedEvent,InteractionCancelledEvent,WorldPromptContent,WorldReferenceImage,WorldSetupEvent,UserActionType,UserActionKey,UserActionInput). - Added
McpServer.deferLoading(defer_loading/deferLoading) for deferred MCP tool loading.
- Added
- SDK Client Telemetry Alignment (
3.6.1):- Updated
google-genai-sdktelemetry headers acrossApiClient,LiveService, andLiveMusicServiceto3.6.1.
- Updated
2026.11.16 #
Added & Fixed (Upstream Parity with js-genai & python-genai) #
- Interactions Static Media Processing Options (
StaticMediaProcessing,AudioStaticMediaProcessing,DocumentStaticMediaProcessing):- Added
StaticMediaProcessing(VideoContentLayer),AudioStaticMediaProcessing,DocumentStaticMediaProcessing,PageProcessingOptions(PageContentLayer:page_image,page_text), andSpreadsheetProcessingOptions(SpreadsheetContentLayer:visual,data,formulas) for configuring video, audio, paginated document, and spreadsheet extraction in the Interactions API.
- Added
- Interactions Dynamic Tool Search & Deferred Function Loading (
ToolSearch,InteractionFunction):- Added
ToolSearch(ToolSearchExecution.server/client),InteractionFunction,ToolSearchCallArguments,ToolSearchCallStep,ToolSearchResultStep,ToolSearchCallDelta, andToolSearchResultDelta, plusdeferLoadingandshortDescriptionsupport onFunctionDeclaration.
- Added
FunctionResponsePart.fromUriMIME Inference & Gemini Files API URIs:- Updated
FunctionResponsePart.fromUri()(inferMimeType,isFilesApiUri) to automatically infer MIME types from file extensions whenmimeTypeis omitted, leavemimeTypeunset for Gemini Files API URIs (https://generativelanguage.googleapis.com/.../files/...) so the server uses uploaded file metadata, validate unknown non-Files-API URIs, and forwarddisplayName.
- Updated
- Header Case-Variant Collapsing & SSE / JSON Stream Parsing Fixes (
ApiClient,RawJsonLineBuffer):- Added
ApiClient.collapseHeaderCaseVariants()andApiClient.appendLibraryVersionHeaders()and updatedApiClient.buildRequestHeaders()andLiveService.connect()to merge case variants ofUser-Agentandx-goog-api-clientwithout emitting duplicate headers. - Added
ApiClient.splitSseLines()(splitting strictly on CR, LF, and CRLF while preservingU+2028,U+2029, andU+0085inside JSON strings and handling split CRLF chunks) andRawJsonLineBuffer(ignoring{/}inside quoted JSON strings).
- Added
- Recursive Union JSON Schema
$defs/$refResolution (JsonSchemaTransformer.processSchema) &v1betaModel Docs:- Added
JsonSchemaTransformer.processSchema()to expand$defs/$refper recursion path without clobbering sharedanyOfunion branches while terminating cyclic back-edges as{}. - Documented
v1betarequirement for-latestaliases (gemini-flash-latest,gemini-flash-lite-latest,gemini-pro-latest) and-previewmodels.
- Added
2026.11.13 #
Added & Fixed (Upstream Parity with js-genai 3.3.0 & python-genai 3.3.0) #
- Gemini 4 Hydrogen & Full Interactions Model Catalog (
InteractionModels.gemini4Hydrogen):- Added
InteractionModels.gemini4Hydrogen('gemini-4-hydrogen') for fast, dependable frontier execution across coding, agentic workflows, and multimodal knowledge work, along with the full upstream Interactions model constants (gemma-4-26b-a4b-it,gemma-4-31b-it,gemini-flash-latest,gemini-flash-lite-latest,gemini-pro-latest,gemini-3.7-flash,gemini-3.6-flash,gemini-3.5-flash,gemini-3.5-flash-lite,gemini-3.8-flash-tts,gemini-3.8-flash-lite-tts,gemini-3.5-transcribe,gemini-nano-banana-2.1,gemini-robotics-er-2-preview,gemini-robotics-er-1.6-preview,lyria-3.5,lyria-3-clip-preview, andlyria-3-pro-preview).
- Added
- Default UTF-8 HTTP & Streaming SSE Response Decoding (
ApiClient):- Added
ApiClient.resolveResponseEncoding(),ApiClient.decodeResponseBody(), andApiClient.decodeSseJsonStream()so JSON, error-envelope, andtext/event-streamresponses without an explicitContent-Typecharsetparameter decode as UTF-8 by default (instead ofpackage:http'sISO-8859-1/latin1fallback) while preserving explicit server charsets and reassembling multi-byte UTF-8 sequences split across stream chunks.
- Added
- Environment Variable API Key & Debug Flag Resolution (
GEMINI_API_KEY,GOOGLE_API_KEY,GOOGLE_GENAI_DEBUG):- Added
ApiClient.resolveDefaultApiKey()(GEMINI_API_KEYwith fallback toGOOGLE_API_KEY) and optionalapiKeyparameter support onGoogleGenAIandApiClient, plusApiClient.isDebugEnabled()recognizing'true','1','yes', and'on'inGOOGLE_GENAI_DEBUG.
- Added
- SDK Client Telemetry Alignment (
3.3.0):- Updated
google-genai-sdktelemetry headers acrossApiClient,LiveService, andLiveMusicServiceto3.3.0.
- Updated
2026.11.12 #
Added & Fixed (Upstream Parity with js-genai 3.2.0 & python-genai 3.2.0) #
- Live API Proactive Video (
ProactivityConfig.proactiveVideo):- Added
proactiveVideo(proactive_video/proactiveVideo) toProactivityConfigfor triggering model generation on incoming Live video frames whenproactiveAudiois enabled, and ensuredLiveClientSetup.toJson()serializes nestedproactivitymaps directly.
- Added
- Extra-High Thinking Effort (
ThinkingLevel.XHIGH):- Added
ThinkingLevel.XHIGH('XHIGH') and updatedThinkingConfig.fromJson()to normalize bothsnake_case/camelCasekeys and lowercase'xhigh'wire values across Gemini API and Interactions API payloads.
- Added
- Decisions API (
DecisionsService/genAI.decisions.create):- Added
DecisionsService(POST /{api_version}/decisions) onGoogleGenAI.decisions, along withCreateDecisionRequest,CreateDecisionResponse,DecisionQuestion(NoulQuestion,ChoiceQuestion,ScoreQuestion),DecisionAnswer(NoulAnswer,ChoiceAnswer,ScoreAnswer),NoulCriteria,DecisionPromptFeedback, andDecisionBlockReason.
- Added
- Interactions Model/Agent Identifiers,
EnvironmentMode, & SDK Telemetry (3.2.0):- Added
InteractionModels(gemini-4-carbon,gemini-omni-1.2-flash, etc.),InteractionAgents(antigravity-preview-09-2026, etc.), andEnvironmentMode(on_demand,self_hosted). - Updated
google-genai-sdktelemetry headers to3.2.0, refreshed Dartdoc descriptions forFinishReason,MediaProcessing,MediaResolution, andModality, and updated Gemini API documentation links fromai.google.devtoaistudio.google.com.
- Added
2026.11.8 #
Added & Fixed (Upstream Parity with js-genai & python-genai) #
- Expanded
FinishReason&ReinforcementTuningThinkingLevelEnums:- Added
MISSING_THOUGHT_SIGNATURE,ESCALATION,PUP_LIMITED_DISABLED, andMODEL_ARMORtoFinishReason. - Added
ReinforcementTuningThinkingLevel(REINFORCEMENT_TUNING_THINKING_LEVEL_UNSPECIFIED,MINIMAL,LOW,MEDIUM,HIGH).
- Added
- Typed 4XX/5XX HTTP API Error Responses (
ApiError,GoogleGenAiError,ApiClientError,ApiServerError):- Added
ApiError(code,message,status,details),GoogleGenAiError,ApiClientError(thrown on 4XX HTTP responses), andApiServerError(thrown on 5XX HTTP responses) inApiClient, surfacing structured backend error messages while preservingAPI Error: <statusCode> <body>string formatting.
- Added
- Multimodal
CodeExecutionResult& Office/OpenDocument MIME Types (DocumentMimeTypes):- Extended
CodeExecutionResultwith multimodalcontent(List<Content>?),resultunion getter/constructor parameter (StringorList<Content>),isError,signature, andcall_idJSON alias support. - Added
DocumentMimeTypesconstants andDocumentMimeTypes.isSupported()covering PDF, CSV, Microsoft Office (.pptx,.ppt,.docx,.doc,.dotx,.xlsx,.xls), and OpenDocument (.odp,.odt,.ods) MIME types. - Extended
UsageMetadata.fromJson()to normalize snake_casetraffic_typeandservice_tierfields.
- Extended
- Curated History AFC Exchange Trimming (
GeminiLiveTranscriptExporter.extractCuratedHistory):- Added
GeminiLiveTranscriptExporter.extractCuratedHistory()andvalidateContent(), dropping the entire automatic function calling (AFC) exchange from curated chat history when the final model turn is invalid while preserving unanswered spent-budget function calls.
- Added
2026.11.6 #
Added & Fixed (Upstream Parity with js-genai 3.0.0 & python-genai 3.0.0) #
- Voice-Driven Editing & Transcription (
AudioTranscriptionConfig.sourceText,SmartTranscriptionMode):- Added
sourceText,wordTimestamp, anddiarizationtoAudioTranscriptionConfigwith snake_case (source_text,word_timestamp) and camelCase (sourceText,wordTimestamp) JSON serialization support. - Added
SmartTranscriptionMode(type: 'smart',sourceText) for voice-driven text editing and replacement in smart transcription mode.
- Added
- Finish Reason Enum &
MALFORMED_RESPONSE(FinishReason):- Added
FinishReasonenum includingCONTINUATIONandMALFORMED_RESPONSEaligned with upstreamjs-genai3.0.0 andpython-genai3.0.0.
- Added
- Pre-Setup WebSocket Close & Error Rejection (
LiveService.connect,LiveMusicService.connect):- Fixed
LiveService.connect()andLiveMusicService.connect()to immediately reject with aStateError(Live connection closed before setup completed (code <code>): <reason>) when the WebSocket closes beforesetupCompletearrives instead of waiting for setup timeout, while still invoking useronErrorandonClosecallbacks and closing the underlying socket on setup failure.
- Fixed
- API Version Environment Variable &
{api_version}Path Placeholder (ApiClient):- Added
ApiClient.resolveDefaultApiVersion(),ApiClient.setDefaultGoogleAiApiVersion(), andGOOGLE_GENAI_API_VERSIONenvironment variable support (beta->v1beta, or verbatim version string when no explicitapiVersionis passed in code). - Added
ApiClient.resolveApiVersionInPath()and{api_version}path placeholder substitution inApiClientfor versioned upload and resource paths. - Verified
AuthTokensServicefieldMaskgeneration keeps repeated/array fields (tools,safetySettings,generationConfig.response_modalities) bare without array indices.
- Added
- SDK Client Header Version & Documentation Links (
3.0.0):- Updated default
User-Agentandx-goog-api-clientSDK version headers acrossLiveService,LiveMusicService, andApiClienttogoogle-genai-sdk/3.0.0. - Updated
codegen_instructions.mdreference links fromai.google.devtoaistudio.google.com/docs.
- Updated default
2026.11.1 #
Added (Upstream Parity with js-genai 2.32.0 & python-genai 2.34.0) #
- Automatic Continuation Deadline, Timeout & Multi-Hop Usage Aggregation (
UsageMetadata.merge,CallDeadline,ContinuationTimeoutError):- Added
UsageMetadata.merge(UsageMetadata other)to sum cumulative token fields (promptTokenCount,responseTokenCount,cachedContentTokenCount,toolUsePromptTokenCount,thoughtsTokenCount,totalTokenCount) and per-modalityModalityTokenCountlists across continuation hops while preservinginitialPromptTokenCountfrom the first hop. - Added
CallDeadline(timeoutMs,bounded,remainingMs(),expired(),hopTimeoutMs(),check()) andContinuationTimeoutErrorto bound wall-clock execution across multi-hop continuation turns.
- Added
- Speech Transcription Model Identifier (
LiveModels.gemini35Transcribe):- Added
LiveModels.gemini35Transcribe('gemini-3.5-transcribe') aligned with upstream speech transcription model support.
- Added
- SDK Client Header Version Alignment (
2.34.0):- Updated default
User-Agentandx-goog-api-clientSDK version headers acrossLiveService,LiveMusicService, andApiClienttogoogle-genai-sdk/2.34.0.
- Updated default
2026.10.29 #
Added (Upstream Parity with js-genai & python-genai) #
- Video Understanding in Tool Responses (
FunctionResponsePart.mediaProcessing):- Added
mediaProcessing(MediaProcessing.STATIC/MediaProcessing.AGENTIC) toFunctionResponsePartand its.fromBytes()/.fromUri()factories. - Added snake_case (
media_processing) and camelCase (mediaProcessing) deserialization support acrossFunctionResponsePart.fromJson()andPart.fromJson().
- Added
- Long Decode Continuation & Interaction Status (
REQUIRES_CONTINUATION,continuationToken,continuationIds):- Added
InteractionStatus.REQUIRES_CONTINUATIONtoInteractionStatuswith case-insensitive deserialization (requires_continuation/REQUIRES_CONTINUATION). - Added
continuationToken,continuationIds, andrequiresContinuationtoLiveServerContentandGeminiLiveSessionController. - Added
ContinuationInterruptedErrorto preserve partial progress,continuationToken,interactionId, andcontinuationIdsacross multi-hop continuation boundaries.
- Added
- Interaction Usage Metadata Aliases:
- Extended
UsageMetadata.fromJson()andModalityTokenCount.fromJson()to supportinitial_input_tokens(initialInputTokens),total_input_tokens,total_output_tokens,total_cached_tokens,total_tool_use_tokens,total_thought_tokens,total_tokens, and*_tokens_by_modality(tokensand lowercase modality names).
- Extended
- Per-Request Header Isolation,
GenAICredentials,X-Server-Timeout, & SDK Headers:- Added
GenAICredentialsfor dynamic bearer token (Authorization: Bearer ...) and quota project (x-goog-user-project) resolution acrossGoogleGenAI,LiveService, andApiClient. - Added
ApiClient.populateServerTimeoutHeader()(X-Server-Timeoutin whole seconds rounded up fromHttpOptions.timeout) and ensured per-request headers never mutate client default headers. - Aligned
ApiClient.buildRequestHeaders()to include defaultUser-Agentandx-goog-api-clientSDK headers (google-genai-sdk/2.33.0 dart/<version>) while preserving caller-supplied overrides. - Added
LiveService.supportsHeadersmatchingWebSocketFactory.supportsHeadersin@google/genai, and supportedHttpOptions(baseUrl,apiVersion,headers,timeout,extraBody,retryOptions) onLiveConnectConfigandLiveConnectParameters.
- Added
Added (Pre-Built Widgets, Foldable/Adaptive UI & Developer Utilities) #
- Foldable & Adaptive Responsive Layouts (
GeminiLiveViewportInfo,GeminiLiveAdaptiveSplitView):- Added
GeminiLiveViewportInfo(GeminiLiveSizeClass,GeminiLiveFoldPosture) detectingDisplayFeaturefoldable hinges (book,tabletop), ultra-narrow screens (< 360px), and tablet/desktop breakpoints. - Added
GeminiLiveAdaptiveSplitViewand adaptedGeminiLiveTranslateSplitView,GeminiLiveChatView,GeminiLiveControlBar,GeminiLiveMusicControlDeck,GeminiLiveLogOverlay, and all 4 bottom sheets (GeminiLiveVoiceSelectorSheet,GeminiLiveVoiceStudioSheet,GeminiLiveSessionInfoSheet,GeminiLiveContextConfigSheet) for foldable hinges and compact viewports.
- Added
- Universal In-App WebSocket & Diagnostic Log Overlay (
GeminiLiveLogOverlay,GeminiLiveLogConsole):- Added
GeminiLiveLogController,GeminiLiveLogOverlay,GeminiLiveLogConsole, and.withGeminiLiveLogOverlay()widget extension to attach a draggable floating log button and filterable diagnostic console to any widget.
- Added
- Additional Widgets & Developer Utilities:
- Added
GeminiLiveMusicControlDeck,GeminiLiveReconnectBanner,GeminiLiveVoiceStudioSheet, andGeminiLiveSessionInfoSheet/GeminiLiveSessionInfoBadge. - Added
GeminiLiveFunctionTool&GeminiLiveToolRegistry(inline tool declaration & auto-execution),GeminiLiveTranscriptExporter(HistoryConfig, Markdown, JSON, WebVTT, SRT),GeminiLiveFrameRateLimiter(camera frame throttling), andGeminiLiveAudioUtils(PCM16 resampling, stereo/mono conversion, silence detection, WAV header parsing).
- Added
Refactored & Example App #
- Removed unused
web_socket_clientdependency and standardized WebSocket handshake viaWebSocketChannel.ready. - Added 4-language (
en,ko,ja,zh) runtime localization, global log overlay integration, and MG16XU hardware mixer strips across all 13 example screens. - Applied Effective Dart documentation guidelines across public API classes and methods.
2026.10.23 #
Added (Upstream Parity with js-genai 2.31.0 & python-genai 2.33.0) #
LiveConnectConfig& SessionlabelsSupport:- Added
LiveConnectConfigcombiningGenerationConfigparameters and all Live session setup fields (systemInstruction,tools,realtimeInputConfig,sessionResumption,contextWindowCompression,inputAudioTranscription,outputAudioTranscription,proactivity,explicitVadSignal,avatarConfig,safetySettings,historyConfig,translationConfig,generationConfig,labels). - Supported passing
configas either aLiveConnectConfig,GenerationConfig, orMap<String, dynamic>in bothLiveConnectParametersandLiveConnectConstraints(AuthTokensService), mappinglabelsdirectly tosetup.labels(bidiGenerateContentSetup.labels).
- Added
CallableTool&CallableToolConfigSupport:- Added
CallableToolandCallableToolConfigwith automatic asynchronous tool declaration resolution viaLiveService.buildSetupMessageAsync()andLiveService.connect().
- Added
- Async Session Stream & Turn Iteration (
LiveSession.receive()&sessionId):- Added
LiveSession.sessionId(alias forsetupComplete?.sessionId),LiveSession.messages, and turn-scopedLiveSession.receive()(yielding server messages untilserverContent.turnComplete == true, matchingAsyncSession.session_idandAsyncSession.receive()inpython-genai). - Added
LiveMusicSession.messagesandLiveMusicSession.receive()onLiveMusicSession.
- Added
- Realtime Input & Live Music Parameter Classes:
- Added
LiveSendRealtimeInputParameters.media,LiveMusicSetWeightedPromptsParameters, andLiveMusicSetConfigParameters, and widenedLiveMusicSession.setWeightedPrompts()andLiveMusicSession.setMusicGenerationConfig()to accept typed parameter objects or maps. - Updated
SlidingWindow.targetTokensandContextWindowCompressionConfig.triggerTokensto accept bothintandStringtoken counts. - Added
GeminiLiveVoice.idandGeminiLiveVoice.characterDescriptionconvenience getters.
- Added
- Default Coding System Prompt (
codegen_instructions.md) &tContentAlignment:- Ported upstream
codegen_instructions.md(# Gemini Live API Coding Guidelines) to the repository root and synchronizedAGENTS.md,GEMINI.md,CLAUDE.md, andCODEX.md. - Aligned
GeminiLiveChatView.defaultSystemInstructionwith upstreamtContent(role: 'user') and unifiedsystemInstructionunion parsing. - Bumped internal SDK client version header to
2.33.0acrossLiveServiceandLiveMusicService.
- Ported upstream
2026.10.22 #
Added (Upstream Parity with js-genai 2.30.0+ & python-genai 2.32.0) #
- In-Session Context Updates (
sendContextUpdate):- Added
LiveClientContextUpdate,LiveClientContextUpdateTools, andLiveClientMessage.contextUpdateto dynamically updatesystemInstructionandtoolsmid-session in order with session inputs without reconnecting. - Added
LiveSession.sendContextUpdate()andGeminiLiveSessionController.sendContextUpdate(), supportingtools: const <Tool>[]to clear all previously registered tools.
- Added
- Voice Design Base Voice (
PromptedVoice.baseVoice):- Added
baseVoicetoPromptedVoiceandCreateVoiceRequest.prompted()to adapt an existing voice persona with a natural-language style prompt.
- Added
- Multimodal Tool Response & Binary Helpers:
- Added
FunctionResponsePart.fromBytes(),FunctionResponsePart.fromUri(),FunctionResponseBlob.fromBytes(),VoiceAudioData.fromBytes(), andBlob.fromBytes()(with.bytesgetters). - Automatic recursive base64 encoding for raw
Uint8Listvalues insideLiveClientToolResponse.toJson(). - Added snake_case (
inline_data,file_data,mime_type, etc.) and raw byte array (List<int>) deserialization support toPart.fromJson()andBlob.fromJson().
- Added
- Full Runtime & Union Parameter Parity (
tModel,tContents,tLiveSpeechConfig):- Added
LiveService.normalizeModelName()matching upstreamtModelvalidation (rejecting empty model strings or../?/&, and preservingmodels/andtunedModels/prefixes) acrossLiveServiceandLiveMusicService. - Added top-level generation parameters (
responseModalities,temperature,topP,topK,maxOutputTokens,mediaResolution,seed,speechConfigacceptingSpeechConfigor voice nameString,thinkingConfig, andenableAffectiveDialog) directly onLiveConnectParameters. - Enforced upstream
multiSpeakerVoiceConfigrejection (UnsupportedError) inLiveService.buildSetupMessage(). - Widened
LiveSession.sendClientContent()(turnsunion acceptingString,Part,Content,Map, orListwith automaticPartaccumulation into a single userContentturn, mixedContent/Partrejection, and unwrappedfunctionCall/functionResponsepart rejection). - Widened
LiveSession.sendRealtimeInput()(media,audio,videoacceptingBloborMap, andactivityStart/activityEndacceptingtrue,{}, orActivityStart/ActivityEnd) andLiveSession.sendToolResponse()(accepting singleFunctionResponse,Map, orList). - Added enterprise tool validation (
retrieval,enterpriseWebSearch,exaAiSearch,parallelAiSearch) and automaticmcp_used/unknownclient header injection whenTool.mcpServersis present. - Bumped internal SDK client version header to
2.32.0acrossLiveServiceandLiveMusicService.
- Added
Added (New Pre-Built Widgets & Controller Enhancements) #
GeminiLiveThinkingIndicator:- System-styled status pill and collapsible reasoning drawer for
gemini-3.8-live-extended-thinking(Part(thought: true)), with.fromController()factory and built-in integration inGeminiLiveChatView(showThinkingIndicator,thinkingIndicatorBuilder).
- System-styled status pill and collapsible reasoning drawer for
GeminiLiveContextConfigSheet,GeminiLiveContextBadge, &GeminiLiveContextPreset:- Interactive Material 3 bottom sheet (
.show()) and summary badge for switching persona presets, editingsystemInstruction, and toggling or clearing session tools mid-call viasendContextUpdate.
- Interactive Material 3 bottom sheet (
GeminiLiveSessionControllerEnhancements:- Added Extended Thinking state tracking (
isThinking,latestThought,thoughts). - Added live context state tracking (
activeSystemInstruction,activeTools).
- Added Extended Thinking state tracking (
Documentation & Examples #
- Updated
live_api,math_tutor, andfunction_callingexample demos to showcasesendContextUpdateand upstream union parameters. - Applied Effective Dart documentation guidelines across public Live API classes and widgets.
- Updated and synchronized all AI Agent Skills (
skills/,.agents/,.claude/,.codex/,.gemini/,.hermes/,.pi/).
2026.10.6 #
Added (Upstream Parity with js-genai 2.30.0 & python-genai 2.31.0) #
- Word-Level Transcription & Timestamps:
- Added
WordInfo(word,startOffset,endOffset) and extendedTranscriptionwithwords,startOffset, andendOffsetfields. - Added
interimTranscriptTimestampEnabledtoRealtimeInputConfig.
- Added
- Token Usage Metadata & Accounting:
- Added
initialPromptTokenCounttoUsageMetadataand exposedinitialPromptTokensandtoolUsePromptTokensonGeminiTokenUsageTracker. - Added wire-format fallback deserialization for
candidatesTokenCount/candidatesTokensDetailsonUsageMetadataandtypeonVoiceActivity.
- Added
- Live Grounding & Remote MCP Tool Models:
- Added
SearchTypes,WebSearch, andImageSearchmodels andGoogleSearch.searchTypes. - Added
AuthConfig(apiKey,authType) andGoogleMaps.authConfig/GoogleMaps.enableWidget. - Added typed
McpServerandStreamableHttpTransportmodels along withTool.fromMcpServersandTool.typedMcpServers.
- Added
- Full Live Setup Constraints on Ephemeral Tokens (
LiveConnectConstraints):- Expanded
LiveConnectConstraintsandAuthTokensService.create()to support lockingsystemInstruction,tools,realtimeInputConfig,sessionResumption,contextWindowCompression,inputAudioTranscription,outputAudioTranscription,proactivity,avatarConfig,safetySettings,historyConfig, andtranslationConfiginsidebidiGenerateContentSetup.
- Expanded
- Bumped internal SDK client version header to
2.30.0acrossLiveServiceandLiveMusicService.
Added (Widgets, Utilities & Controller Enhancements) #
- New Pre-Built Widgets:
GeminiLiveToolActivityChip: Animated status pill that automatically appears while the model executesLiveServerToolCallfunctions, with customlabelBuilderandleadingIconsupport.GeminiLiveAudioRouteButton: Hardware audio route switcher (speaker,earpiece,bluetooth,wiredHeadset) with 2-route quick toggle and 3+ route bottom sheet selector.GeminiLiveTranslateSplitView: Dual-pane real-time speech-to-speech interpreter view forgemini-3.5-live-translate-preview, including 180-degreefaceToFaceModerotation for across-the-table conversations.
- New Audio & Reconnection Utilities:
GeminiLivePcmChunker: Streams irregular microphone buffers into fixed-duration (e.g., 100ms / 3,200-byte) 16-bit aligned PCM frames.GeminiLiveAudioBuffer: Accumulates 16-bit PCM chunks with optionalmaxDurationrolling cap, duration calculation, and instant WAV export (toWavBytes()).GeminiLiveReconnectPolicy: Exponential backoff with random jitter and retryable WebSocket close code evaluation (1006,1011,1012,1013).
GeminiLiveSessionControllerEnhancements:- Automatic session resumption handle (
resumptionHandle) tracking and injection on reconnect. - Optional automatic reconnection (
reconnectPolicy) onGoAwaynotices and retryable disconnects. - Real-time tool execution state tracking (
activeToolCalls,isExecutingTool) forLiveServerToolCallandLiveServerToolCallCancellation. - Optional model turn PCM recording (
recordModelAudio) and WAV export (exportLastModelTurnWav()), plussendAudioStreamEnd().
- Automatic session resumption handle (
Fixed & Refactored #
- Fixed
GeminiLiveMicButtonandCupertinoGeminiLiveMicButtonignoring customactiveIconandinactiveIconwidget parameters. - Fixed
GeminiLiveChatView.didUpdateWidgetto properly rebind listeners when swappingcontroller, and guarded emptyLiveTranscriptItem.textindexing. - Added auto-dismiss timer (
displayDuration,onDismissed) and customiconwidget support toGeminiLiveBargeInBanner. - Fixed
GeminiLiveUsageBadgecustombackgroundColorandborderColoroverride precedence. - Fixed
GeminiLiveSessionController.dispose()so externally injectedGeminiTokenUsageTrackerinstances are not prematurely disposed. - Added
GeminiLiveLogger.removeListener()andclearListeners()to prevent listener leaks. - Modularized
lib/src/model/models.dartinto domain-specific part files underlib/src/model/models/. - Refactored all example app demos into a layered MVVM architecture (
data/services,ui/view_models,ui/widgets).
2026.10.5 #
Added #
LiveModels.gemini35LiveTranslatePreview(gemini-3.5-live-translate-preview) for speech-to-speech translation.SpeechAnnotationmodel and serialization for voice synthesis metadata (js-genai 2.27.0 sync).GoogleGenAI.musicgetter that exposes the Realtime Music service directly.- Type-Safe Voice Personas (
GeminiLiveVoice):- Added enhanced enum
GeminiLiveVoicecovering Google's 30 official prebuilt voices (puck,charon,kore,fenrir,aoede,leda,orus,zephyr, etc.) with compile-time safety, tone styles, and pitch/gender metadata. - Added
SpeechConfig.fromLiveVoice(GeminiLiveVoice voice, {String? languageCode})and extendedSpeechConfig.fromVoice(Object voice)to accept both enums and custom strings. - Added
liveVoicegetter acrossSpeechConfig,VoiceConfig, andPrebuiltVoiceConfigfor typed inspection and JSON round-trip deserialization. - Integrated
GeminiLiveVoicewithGeminiLiveVoiceSelectorSheet(.showLiveVoice,onLiveVoiceSelected,.allLiveVoices30-voice catalog) andGeminiVoiceOption.fromLiveVoice. - Synchronized
GeminiLiveVoiceandSpeechConfig.fromLiveVoiceinpackage:gemini_live/compat/firebase_ai.dart.
- Added enhanced enum
- Live/music service SDK version header bumped to js-genai
2.27.0.
Deprecated #
- Model constants that were misfiled as Live models during the js-genai 2.27.0 sync. Upstream added them to the Interactions
Modelenum, not the Live API. They will be removed in a future release.LiveModels.geminiOmni11Flash,LiveModels.geminiOmniFlashPreview(Gemini Omni is a video generation model).LiveModels.gemini38FlashTts,LiveModels.gemini38FlashLiteTts,LiveModels.gemini31FlashTtsPreview(TTS models).LiveMusicModels.lyria35,LiveMusicModels.lyria3ClipPreview,LiveMusicModels.lyria3ProPreview(not Realtime Music models; useLiveMusicModels.lyriaRealtimeExp).
Example App #
- Live Music Studio demo for Lyria RealTime, with Prompt DJ crossfader, tag bank, and auto-reset context.
- Pioneer-style Pro DJ Console and AI Studio Prompt DJ 4x4 rotary MIDI Box demos.
- Web Audio API real-time PCM streamer for Flutter Web playback.
- Removed non-realtime Lyria 3.x models from the Live Music Studio model picker.
Documentation #
- README (EN/KR/JP/ZH): AI Agents guide, Supported Models tables, Voice Quick Start (mic + playback + platform permissions), API key security note, and fixed widget snippets that did not compile.
- Agent Skills synchronized across Claude Code, Gemini CLI / Antigravity, Codex, and the open Agent Skills paths. Fixed snippets that did not compile, added mic/playback wiring, setup, and "Do NOT" guardrails.
doc/advanced_configuration.md: fixed the function calling example.
2026.10.4 #
Added (Upstream Parity with js-genai & python-genai) #
- Live Music API (
ai.live.music/LiveMusicService):- Full bidirectional WebSocket streaming client for Gemini Realtime Music generation (
models/lyria-realtime-exp) viaBidiGenerateMusic. - Accessible via
genAI.live.musicorliveService.music. - Added session controls:
setWeightedPrompts(),setMusicGenerationConfig(),play(),pause(),stop(),resetContext(). - Added full models and enums:
Scale,MusicGenerationMode,LiveMusicPlaybackControl,WeightedPrompt,LiveMusicGenerationConfig,LiveMusicClientMessage,LiveMusicServerMessage,AudioChunk(withbyteshelper getter),LiveMusicFilteredPrompt.
- Full bidirectional WebSocket streaming client for Gemini Realtime Music generation (
- Ephemeral Authentication Tokens Service (
genAI.authTokens/AuthTokensService):- Implemented
AuthTokensServicefor issuing secure, short-lived client-side session tokens (POST /v1alpha/authTokens). - Supports
liveConnectConstraints(locking model andGenerationConfig) and automatedfieldMaskgeneration withlockAdditionalFields. - Handles dual camelCase/snake_case JSON mapping for
AuthTokenresponses.
- Implemented
- Top-level
translationConfigonLiveConnectParameters:- Directly pass
TranslationConfigonLiveConnectParametersfor seamless realtime bidirectional translation without nesting inGenerationConfig.
- Directly pass
- Audio Transcription
languageCodesSupport:- Removed outdated restriction prohibiting
languageCodesinAudioTranscriptionConfig, aligning with upstream Gemini API support for transcription languages.
- Removed outdated restriction prohibiting
2026.10.3 #
Changed & Improved (Design & Aesthetics) #
- Native Non-AI UI Overhaul across all Pre-built Widgets:
GeminiLiveCaptionBubble:- Replaced garish neon-colored badges with sleek, native frosted glass (
enableBlur: truewithBackdropFilterandImageFilter.blur). - Added subtle neutral speaker chips (
showSpeakerTag: true/false), elegant subtitle typography, and smooth breathing indicator dot (_PulsingDot900ms ease-in-out).
- Replaced garish neon-colored badges with sleek, native frosted glass (
GeminiLiveWaveform:- Replaced mechanical rectangular bars with organic capsule pills (
borderRadiusdefaulting tobarWidth / 2). - Added
enableIdleBreathing: truewith organic sinusoidal micro-motion when idle, mimicking professional native audio recording equipment.
- Replaced mechanical rectangular bars with organic capsule pills (
GeminiLiveStatusBadge:- Swapped out raw color-outline boxes for refined neutral surface containers with 0.5px borders.
- Upgraded pulse dot to a modern halo ripple ring effect (
_PulseDot) and softened semantic palette.
GeminiLiveMicButton:- Replaced generic BoxShadow blur glow with crisp, expanding concentric acoustic ripple rings and neutral dark/light tactile surface layers.
GeminiLiveVoiceIndicator:- Upgraded from simple single sine to organic dual-harmonic motion with bell-curve center envelopes and pill capsules.
GeminiLiveUsageBadge&GeminiLiveUsageDetailsDialog:- Removed arcade-like neon cyan/amber accents in favor of clean, professional SaaS observability dark/light surface aesthetics.
2026.10.2 #
Added #
- GeminiLiveSessionController (
LiveSessionController):- All-in-one Flutter
ChangeNotifierstate manager for handling Live API WebSocket connections, lifecycle (disconnected,connecting,connected,error), message streams, and errors. - Integrated real-time transcript timeline tracking (
LiveTranscriptItem) for user input, interim speech, and model output with speaker attribution and style metadata. - Seamless barge-in interruption handling via
onInterruptedcallback. - Built-in token usage tracking integration (
TokenUsageTracker) and audio stream helpers (feedAudioPcm,sendText).
- All-in-one Flutter
- GeminiLiveWaveform Widget:
- Real-time animated audio visualizer supporting continuous amplitude stream/normalized levels or raw 16-bit PCM byte streams.
- Configurable bar count, wave style (
barsvssine), animated idle breathing, and gradient styling.
- GeminiLiveCaptionBubble Widget:
- Live subtitle/caption bubble widget for streaming speech-to-text transcripts with animated streaming dot indicator.
- Displays speaker badge, emotional/style tone indicators, and auto-dismiss after inactivity.
- GeminiLiveAudioUtils:
- Production-grade PCM audio analysis helper: RMS amplitude, peak amplitude, decibels (dBFS), and logarithmic visual scaling for audio meters.
2026.10.1 #
Added #
- LiveClientSetup & GenerationConfig Metadata Labels:
- Added
labels(Map<String, String>?) toLiveConnectParameters,LiveClientSetup, andGenerationConfig. - Enables user-defined metadata labels for tracking, attribution, and aggregator safety identifiers (e.g.
safety_identifier) adhering to unified Cloud label formatting.
- Added
- Speech Synthesis Metadata (
SpeechMetadata):- Added
SpeechMetadatadata model withspeakerandstylefields. - Added
Part.speechMetadata(speech_metadata) to control per-part multi-speaker allocation and vocal styles (e.g. "whispering", "excited, fast-paced") during speech synthesis and Live conversations.
- Added
- Gemini 3.8 Flash TTS Canonical Model Identifiers:
- Added canonical TTS model constants to
LiveModels:LiveModels.gemini38FlashTts('gemini-3.8-flash-tts'): High-fidelity Gemini 3.8 Flash text-to-speech model.LiveModels.gemini38FlashLiteTts('gemini-3.8-flash-lite-tts'): Ultra-low-latency lightweight Gemini 3.8 Flash text-to-speech model.
- Added canonical TTS model constants to
- Voice Resource Sample Audio:
- Added
sampleAudio(VoiceAudioData?) toVoiceResourceandCreateVoiceRequest(sample_audio), providing audio payload reference for newly designed and replicated voice assets.
- Added
- Upstream Sync with
js-genai2.25.0 &python-genai2.26.0:- Bumped internal SDK client user-agent to
google-genai-sdk/2.25.0. - Regenerated serialization code and updated unit test suites.
- Bumped internal SDK client user-agent to
2026.9.20 #
Added #
- Gemini Voices API Integration & Support:
- Added
GeminiVoicesService(accessible viagenAI.voicesor standalone) for managing custom and prebuilt system voice catalog resources (listVoices,createVoice,getVoice,deleteVoice). - Added
VoiceResourcemodel supporting custom Google-managed voices, client-managed replication keys, and prebuilt catalog voices. - Added
CreateVoiceRequestsupporting natural-language prompted voices (CreateVoiceRequest.prompted) and audio-cloned replicated voices (CreateVoiceRequest.replicated). - Added
VoiceType(replicated,prompted,prebuilt),VoicePitch(low,medium,high),PromptedVoice,ReplicatedVoice,VoiceAudioData,ListVoicesResponse, andDeleteVoiceResponsedata models.
- Added
- VoiceConfig & SpeechConfig Enhancements:
- Added
VoiceConfig.voicestring property to directly pass custom voice IDs (voice_...), replication keys (voicekey_...), or prebuilt voice names directly into speech synthesis. - Added
VoiceConfig.promptedVoiceConfigsupport for natural-language designed voices. - Added ergonomic constructors:
VoiceConfig.fromVoiceName(String name)andVoiceConfig.fromVoiceId(String id). - Added
SpeechConfig.voiceproperty andSpeechConfig.fromVoice(String voiceNameOrId, {String? languageCode})convenience factory.
- Added
- Upstream Sync & Documentation:
- Synced with upstream
js-genaiandpython-genaidiscovery doc and Voices API resource updates. - Updated
AudioTranscriptionConfig.languageCodesdocumentation reflecting current upstream preference over deprecatedlanguageHints/languageAuto.
- Synced with upstream
2026.9.19 #
Added #
- Real-time Token Usage & Cost Tracking:
- Added
GeminiTokenUsageTracker: Automatically tracks real-time prompt, candidate, thoughts, audio, video, image, and document token consumption per turn and session with model-specific cost estimation. - Added
GeminiLiveUsageBadge: Sleek Material widget showing live token count and estimated cost, with interactive tap dialog (GeminiLiveUsageDetailsDialog) showing full multi-modal breakdowns.
- Added
- Upstream Sync with
js-genai2.23.0 &python-genai2.24.0:- Added
TrafficType.ON_DEMAND_OFFPEAK('ON_DEMAND_OFFPEAK') enum value. - Synced Live SDK request headers and user-agent string to
google-genai-sdk/2.23.0. - Regenerated code generation artifacts (
models.g.dart).
- Added
- Example App Enhancements:
- Integrated
GeminiLiveUsageBadgeacross live demo pages. - Added Live Media Subtitle & Live Smart Notetaker workflows.
- Integrated
- Removed legacy
experimentaldesignation across package metadata and documentation to reflect the official Stable release of the Gemini Live API.
2026.9.16 #
Added #
- Gemini 3.8 Live & Extended Thinking Support:
- Added
LiveModelsclass providing canonical model identifiers:LiveModels.gemini38Live('gemini-3.8-live'): Default stable Live API model for low-latency voice and multimodal dialogue without reasoning-induced delays.LiveModels.gemini38LiveExtendedThinking('gemini-3.8-live-extended-thinking'): High-reasoning Live model for voice interactions requiring deep background reasoning.LiveModels.gemini31FlashLivePreview('gemini-3.1-flash-live-preview'): Previous preview model.LiveModels.gemini25FlashNativeAudioPreview('gemini-2.5-flash-native-audio-preview-12-2025').
- Added
- Example App Updates:
- Set default model to
gemini-3.8-liveinApiKeyStoreandLiveAPIDefaults. - Added
gemini-3.8-liveandgemini-3.8-live-extended-thinkingto model selection lists across all demo pages. - Updated connection logging to display active Gemini 3.8 Live model code.
- Set default model to
- Documentation & Guides:
- Updated
README.md,README_KR.md,README_JP.md, andREADME_ZH.mdwith official Gemini 3.8 Live models. - Added Supported Live Models table to
doc/api_reference.md. - Added Section 10: Gemini 3.8 Live Migration & Best Practices in
doc/advanced_configuration.mdcovering model selection, omittingthinking_levelongemini-3.8-live, default non-blocking function execution, and completion tracking viaLiveServerContent.isInteractionComplete. - Updated AI Agent Skill definition (
SKILL.md) to guide assistant models with Gemini 3.8 Live patterns.
- Updated
2026.9.11 #
Added #
- Added
LiveServerContent.isInteractionCompletegetter aligned with upstreampython-genai2.23.0 interaction lifecycle logic:- If
interactionStatusis specified, evaluates whether the status has settled toInteractionStatus.IDLE. - Otherwise, cleanly falls back to
turnComplete == true. - Makes handling multi-turn conversational chunking, tool call completion, and live agent turn boundaries significantly more ergonomic for Flutter developers.
- If
Changed #
- Synced Gemini Live SDK request headers and user-agent string to
google-genai-sdk/2.22.0(aligned with upstreamjs-genai2.22.0). - Bumped package version to
2026.9.11.
Tested #
- Added unit tests for
LiveServerContent.isInteractionCompleteacross all permutations (turnComplete,interactionStatustransitions).
2026.9.9 #
Added #
- Synced DTOs and features with
js-genaiversions 2.17.0 through 2.21.0 andpython-genai2.17.0 through 2.22.0 (changes through September 2026):InteractionStatusenum (UNSPECIFIED,IN_PROGRESS,@Deprecated('Use IDLE instead.') REQUIRES_ACTION,IDLE) representing the live session activity status.LiveServerContent.interactionStatusproperty sent by the server alongsideturnComplete.MediaProcessingenum (MEDIA_PROCESSING_UNSPECIFIED,STATIC,AGENTIC) andPart.mediaProcessingfield indicating how input media is processed.AudioTranscriptionConfigModeenum (MODE_UNSPECIFIED,VERBATIM,SMART) andAudioTranscriptionConfig.modefield for configuring smart disfluency removal and formatting.ToolParallelAiSearchmodel class andTool.parallelAiSearchfield (supported in enterprise agent platform grounding).ToolType.MEDIA_PROCESSINGenum value.ServiceTier.DEFERRED('deferred') enum value inServiceTier.AuthToken,LiveConnectConstraints, andCreateAuthTokenConfigDTO classes for ephemeral token constraints and configuration (expireTime,newSessionExpireTime,uses).
- Reusable Flutter Material Widgets:
GeminiLiveStatusBadge&GeminiLiveStatusBadge.fromFlags(): Real-time visual badge tracking connection state andInteractionStatuswith animated pulsing indicators.GeminiLiveMicButton: Interactive microphone button with animated ripple effects during voice recording.GeminiLiveVoiceIndicator: Lightweight waveform audio bar visualizer animating rhythmically when speech or streaming is active.
- Example App Updates:
- Integrated
GeminiLiveStatusBadge,GeminiLiveMicButton, andGeminiLiveVoiceIndicatorintoLiveAPIDemoPage,ChatPage, andRealtimeMediaDemoPage. - Added live
InteractionStatusmonitoring (IN_PROGRESS/IDLE) andAudioTranscriptionConfigMode.SMARTtoggle toLiveAPIDemoPage.
- Integrated
- Documentation & Specifications:
- Added dedicated
doc/widgets_guide.mdspecifying widget states, visual indicators, constructor APIs, and a complete end-to-end screen example. - Updated
doc/api_reference.md,README.md, andREADME_KR.mdwith official widget documentation links.
- Added dedicated
Changed #
- Upgraded package and example dependencies to their latest compatible versions (
camera: ^0.12.1,build_runner: ^2.16.1,flutter_lints: ^6.0.0, etc.). - Synced Live SDK request headers and user-agent to
google-genai-sdk/2.21.0(synced with upstreamjs-genai2.21.0). LiveService.buildSetupMessagenow explicitly validates and rejectsTool.parallelAiSearchin Gemini Developer API mode with clear descriptive error messages.- Bumped package version to
2026.9.9.
Fixed & Tested #
- Expanded widget test suite (
test/widgets_test.dart) to achieve 95%+ line coverage across all newly introduced Flutter widgets. - Verified 0 warnings and 0 errors across
dart doc --dry-runandflutter analyze --fatal-infos --fatal-warnings.
Added #
- Synced DTOs and features with
js-genaiversions 2.14.0, 2.15.0, and 2.16.0 (changes after July 24, 2026):GenerationConfig.audioTranscriptionConfig(audio_transcription_config) andPart.audioTranscription(audio_transcription).GoogleMapsmodel class andTool.googleMapsgrounding options (groundingTypes, e.g.,places,routing).TurnCompleteReason.TOO_MANY_TOOL_CALLSenum value for tool iteration safety terminations.
Changed #
- Synced Live SDK request headers to
google-genai-sdk/2.16.0(synced withjs-genai2.16.0). - Bumped package version to
2026.8.12.
2026.7.24 #
Changed #
- Synced Live SDK request headers to
google-genai-sdk/2.13.0(synced withjs-genai2.13.0). - Bumped package version to
2026.7.24.
2026.7.19 #
Added #
- Synced Live-facing DTOs with
js-genai2.12.0:HistoryConfig— new type withinitialHistoryInClientContentflag; also addedLiveClientSetup.historyConfigandLiveConnectParameters.historyConfig.AudioTranscriptionConfig.customVocabulary— preferred replacement foradaptationPhrases(which is now@Deprecated).
Changed #
- Updated Live SDK request headers to
google-genai-sdk/2.12.0. - Updated all example and documentation model references from the deprecated
gemini-live-2.5-flash-preview(shut down) togemini-3.1-flash-live-preview(latest, March 2026).- Note:
js-genairef still uses the old model string in its test/sample files; this change is based on the official Gemini API models documentation.
- Note:
- Updated README and README_KR supported model descriptions to reflect the current lineup.
- Bumped package version to
2026.7.19.
2026.7.11 #
Added #
- Synced Live-facing DTOs with
js-genai2.11.0:VoiceConsentSignature, plusReplicatedVoiceConfig.consentAudioandReplicatedVoiceConfig.voiceConsentSignature.AudioTranscriptionConfig.languageAuto,AudioTranscriptionConfig.languageHints, andAudioTranscriptionConfig.adaptationPhrases, with the newLanguageAutoandLanguageHintstypes (languageCodesis now deprecated upstream).ComputerUse.disabledSafetyPoliciesand theSafetyPolicyenum.Tool.exaAiSearchand theToolExaAiSearchtype (rejected for the Gemini API during setup).- Server fields:
LiveServerSetupComplete.voiceConsentSignature,Transcription.languageCode,LiveServerContent.interimInputTranscription,VoiceActivity.audioOffset, andUsageMetadata.serviceTierwith the new lowercase-valuedServiceTierenum. LiveSession.setupComplete, populated once the initialsetupCompletemessage arrives.
Changed #
- Renamed
StreamTranslationConfigtoTranslationConfigandGenerationConfig.streamTranslationConfigtoGenerationConfig.translationConfig(wire keytranslation_config). A deprecatedStreamTranslationConfigtypedef andGenerationConfig.streamTranslationConfiggetter remain for backward compatibility. connect()now resolves on thesetupCompletemessage instead of the first frame: messages received before setup completes (includingsetupCompleteitself) are queued and flushed toonMessagein arrival order once the session resolves.- Updated Live SDK request headers to
google-genai-sdk/2.11.0. - Updated package metadata and README installation snippets to
2026.7.11. - Updated the example lockfile to reference the current local package version.
2026.6.6 #
Changed #
- Updated package metadata and README installation snippets to
2026.6.6. - Updated the example lockfile to reference the current local package version.
2026.5.24 #
Added #
- Synced Live-facing DTOs with
js-genai2.6.0:GenerationConfig.streamTranslationConfigThinkingConfig.thinkingLevel- multi-speaker and replicated voice speech config types
FunctionCall.partialArgs/FunctionCall.willContinueFunctionResponseBlob.displayNameandFunctionResponseFileData.displayName- typed
ComputerUseconfig includingenablePromptInjectionDetection
Changed #
- Updated Live SDK request headers to
google-genai-sdk/2.6.0. - Updated package metadata and README installation snippets to
2026.5.24.
2026.4.19 #
Added #
- Added configurable logging for Live API sessions through
LiveService(logger: ...). - Example app now plays Gemini Live audio responses in-app by buffering PCM chunks, wrapping them as WAV, and playing them when a response turn completes.
- Added timestamped chat demo debug logging for connection state, user sends, recorder events, and voice playback transitions.
Changed #
- Live WebSocket traffic logging is now disabled by default.
- Passing
printas the logger restores the previous verbose logging behavior. - Updated publish metadata and README installation snippets to the current date-based version.
- Split example app Live model defaults by demo:
Realtime Medianow targetsgemini-3.1-flash-live-preview.- chat, function-calling, and feature demos stay on the 2.5 compatibility path until the SDK exposes the additional 3.1 history/session controls.
- Restored chat demo
Text Mode/Voice Modeswitching while keeping audio-response sessions compatible with current Live API behavior. - Refined chat voice playback control so autoplay is consumed once per response and old audio bubbles do not restart when the list rebuilds.
- Reduced noisy chat logging by suppressing empty text chunk logs and summarizing audio chunk progress per response.
Fixed #
- Fixed the example app disconnection issue reported in GitHub issue
#8by removing non-audio request flows from Live setup in the app demos. - Fixed example audio playback cleanup so buffered audio is cleared on interruption, connection close, and error paths.
- Fixed example playback triggering to handle turns that finish with
generationCompleteas well asturnComplete. - Fixed chat voice playback so new user input or a newer response stops the currently playing voice response instead of overlapping playback.
- Fixed macOS image picking in the example app by adding the required
user-selected read-onlysandbox entitlement. - Fixed chat screen teardown races so closing or leaving the page no longer triggers
setState()on a defunct widget after the session closes.
2026.4.17 #
Added #
- Synced additional Gemini Live setup fields from the current
js-genaireference:LiveClientSetup.avatarConfigLiveClientSetup.safetySettingsSafetySetting,AvatarConfig,CustomizedAvatar
- Expanded Live enum coverage for newer server responses:
Modality.VIDEOTurnCoverage.TURN_INCLUDES_AUDIO_ACTIVITY_AND_ALL_VIDEO- additional
TurnCompleteReasonvalues - additional
TrafficTypevalues - latest safety enums for Gemini blocking config
Changed #
- Updated Live SDK request headers to
google-genai-sdk/1.50.1. - Updated README and README_KR to match the current API surface and date-based package versioning.
2026.3.21 #
Added #
- Added the latest Gemini Live part-schema fields from the current
js-genaireference:Part.mediaResolution,Part.fileData,Part.videoMetadataPart.thoughtSignature,Part.toolCall,Part.toolResponse,Part.partMetadataPartMediaResolution,PartMediaResolutionLevel,ToolCall,ToolResponse,ToolType
- Added
AudioTranscriptionConfig.languageCodesand code execution IDs onExecutableCode/CodeExecutionResult.
Changed #
- Tightened Gemini Live setup validation to reject unsupported
input/outputAudioTranscription.languageCodesbefore sending setup. - Added client-side MIME validation for realtime audio/video payloads so malformed blobs fail fast.
Fixed #
- Fixed
LiveServerMessage.dataso multiple inline binary chunks are concatenated as bytes before base64 encoding. - Fixed session resumption parsing parity by treating
lastConsumedClientMessageIndexas a string.
0.2.2 #
Added #
- Example app now supports in-app Gemini API key configuration via Settings UI.
- Users can save/update/clear API keys directly from the app screen.
- API key is persisted locally with
shared_preferences.
- Added
examples/ephemeral_token.dart:- demonstrates Live API connection using ephemeral tokens (
auth_tokens/...) - uses
GoogleGenAI(apiVersion: 'v1alpha')
- demonstrates Live API connection using ephemeral tokens (
- Added platform-specific runtime info adapters so Dart version reporting works consistently across IO and web builds.
- Added comprehensive automated coverage for Live service flows, transport connectors, and model serialization.
Changed #
- Improved Gemini Live setup handling:
- added
LiveService.buildSetupMessage(...)to centralize setup message construction - added
LiveService.validateFunctionResponses(...)to validate tool responses before sending - default setup now falls back to
responseModalities: [Modality.AUDIO]when omitted - unsupported Gemini API options now fail fast during setup construction
- added
- Expanded Function Calling demo in the example app:
- added richer tool declarations:
get_exchange_rateconvert_currencysearch_placescreate_reminder(non-blocking)
- improved simulated tool responses with structured payloads
- added quick prompt chips for multi-tool scenarios
- added richer tool declarations:
- Updated example/docs descriptions to reflect richer function calling capabilities.
- Documented the public model API more clearly in the package docs.
Fixed #
- Enforced Gemini Live function response IDs so tool replies match
ToolCall.functionCallscontract. - Removed Gemini example usage that relied on unsupported setup parameters.
0.2.1 #
Added #
- Expanded Live tool schema support:
Tool.functionDeclarationsTool.googleSearchTool.googleSearchRetrieval
- Added richer function response fields:
FunctionResponse.schedulingFunctionResponse.willContinueFunctionResponse.parts
- Added Live generation config parity fields:
GenerationConfig.mediaResolutionGenerationConfig.speechConfig(voice config)GenerationConfig.thinkingConfigGenerationConfig.enableAffectiveDialogGenerationConfig.seed
- Added additional Live server metadata parsing:
LiveServerContent.interruptedLiveServerContent.waitingForInputLiveServerContent.turnCompleteReasonLiveServerSetupComplete.sessionId- detailed
UsageMetadatamodality/token breakdown fields
Changed #
- Updated WebSocket connection behavior for Gemini Live ephemeral tokens:
- auto-switches to
BidiGenerateContentConstrained - uses
access_tokenquery parameter when API key starts withauth_tokens/
- auto-switches to
- Added
apiVersionoption toGoogleGenAI(...)so Live API version can be configured from the top-level client. - Updated Live User-Agent version to
google-genai-sdk/1.42.0. - Updated enums and compatibility mapping for current Live API:
ActivityHandling.NO_INTERRUPTION(with backward-compatible alias)- VAD/voice activity typed signals
- traffic/modality token metadata enums
Fixed #
- Fixed tool serialization so configured tools are actually sent in
setup. - Fixed session resumption parsing type for
resumable(bool). - Fixed GoAway parsing to align with
timeLeftand added helper conversion to seconds (timeRemaining). - Improved
LiveServerMessage.textgetter to ignore thought-only parts.
0.2.0 #
New Features (Based on js-genai v1.39.0 Gemini Live API Updates) #
Live Server Message Types
- Added
LiveServerToolCall- Handle tool/function call requests from the model - Added
LiveServerToolCallCancellation- Handle tool call cancellation - Added
LiveServerGoAway- Receive server disconnect warnings - Added
LiveServerSessionResumptionUpdate- Handle session resumption updates - Added
VoiceActivityDetectionSignal- Voice activity detection start/end signals - Added
VoiceActivity- Real-time voice activity status
Live Client Setup Configuration
- Added
RealtimeInputConfig- Configure automatic activity detection, activity handling, and turn coverage - Added
SessionResumptionConfig- Enable session resumption with handle and transparent mode - Added
ContextWindowCompressionConfig- Configure context window compression with trigger tokens and sliding window - Added
AudioTranscriptionConfig- Enable input/output audio transcription - Added
ProactivityConfig- Configure proactive audio features - Added
explicitVadSignaloption - Enable explicit VAD signaling
Live Client Realtime Input Enhancements
- Added
mediaChunkssupport - Send multiple media chunks at once - Added
audioStreamEnd- Signal end of audio stream - Added
text- Send real-time text input - Added
ActivityStart/ActivityEnd- Manual activity detection signals
Function Calling Support
- Added
LiveClientToolResponse- Send tool/function responses to the model - Added
FunctionCall- Model function call representation with id, name, and args - Added
FunctionResponse- Function response with id, name, and response data
New Session Methods
- Added
sendClientContent()- Send multi-turn client content - Added
sendRealtimeInput()- Send combined real-time input (audio, video, text, activity signals) - Added
sendMediaChunks()- Send media chunks array - Added
sendAudioStreamEnd()- Signal audio stream end - Added
sendRealtimeText()- Send real-time text - Added
sendActivityStart()/sendActivityEnd()- Manual activity detection - Added
sendToolResponse()- Send tool responses - Added
sendFunctionResponse()- Send single function response - Added
close()- Close WebSocket connection - Added
isClosedgetter - Check connection status
New Enums
- Added
ActivityHandling- Activity handling strategies (START_OF_ACTIVITY_INTERRUPTS, etc.) - Added
TurnCoverage- Turn coverage options (TURN_INCLUDES_ALL_INPUT, etc.) - Added
StartSensitivity- Speech start sensitivity levels - Added
EndSensitivity- Speech end sensitivity levels
Example App Updates
- Added
live_api_demo.dart- Comprehensive demo of all new features - Added
function_calling_demo.dart- Function calling demo with weather/time functions - Added
realtime_media_demo.dart- Real-time media input with manual/auto VAD - Updated
main.dart- New home page with navigation to all demos
Improvements #
- Added
datagetter toLiveServerMessagefor accessing base64 encoded inline data - Updated User-Agent to
google-genai-sdk/1.39.0 - Added
TimeoutExceptionfor connection timeout handling - Improved documentation and examples
0.1.1 #
- Update dependencies and generated model serialization
- Update web_socket_service_web.dart
- Update web_socket_service_stub.dart
0.1.0 #
- Update Readme
- Documentation
0.0.5 #
- Update Readme
0.0.4 #
- Update Readme
0.0.3 #
- Add Example
- Improve Web Support
- Remove Platform.version (dartVersion)
0.0.2 #
- Update README.md
0.0.1 #
- Initial version of the package.
- Added Gemini Live Code