Package-level declarations
Types
Marks the end of user activity.
The different ways of handling user activity.
Marks the start of user activity.
Adapter size for tuning. This enum is not supported in Gemini API.
Aggregation metric. This enum is not supported in Gemini API.
The aggregation result for the entire dataset and all metrics. This data type is not supported in Gemini API.
The aggregation result for a single metric. This data type is not supported in Gemini API.
The generic reusable api auth config. Deprecated. Please use AuthConfig (google/cloud/aiplatform/master/auth.proto) instead. This data type is not supported in Gemini API.
The API secret. This data type is not supported in Gemini API.
Config for authentication with API key. This data type is not supported in Gemini API.
The aspect ratio for the image output.
Configuration for audio-specific output formatting.
The audio transcription configuration in Setup.
The authentication config to access the API.
Config for Google Service Account Authentication. This data type is not supported in Gemini API.
Config for HTTP Basic Authentication. This data type is not supported in Gemini API.
Config for user oauth. This data type is not supported in Gemini API.
Config for user OIDC auth. This data type is not supported in Gemini API.
Configures automatic detection of activity.
Autorater config used for evaluation.
Configures the avatar to be used in the session.
Config for batches.create return value.
Config for dest parameter.
Represents the output_info field in batch jobs.
Config for src parameter.
The BigQuery location for the input content. This data type is not supported in Gemini API.
Bleu metric value for an instance. This data type is not supported in Gemini API.
Output only. The reason why the prompt was blocked.
A custom serializer for ByteArray that encodes to and decodes from Base64 strings.
A resource used in LLM queries for users to explicitly specify what to cache.
Optional parameters.
Config for batches.cancel parameters.
Optional parameters for tunings.cancel method.
Parameters for the cancel method.
Empty response for tunings.cancel method.
A response candidate generated from the model.
Describes the machine learning model version checkpoint.
A citation for a piece of generatedcontent. This data type is not supported in Gemini API.
Citation information when the model quotes another source.
Result of executing the ExecutableCode. Generated only when the CodeExecution tool is used.
Success and error statistics of processing multiple entities (for example, DataItems or structured data rows) in batch. This data type is not supported in Gemini API.
Composite reinforcement tuning reward config.
Composite reinforcement tuning reward config weighted reward config.
Tool to support computer use.
Optional parameters for computing tokens.
Parameters for computing tokens.
Response for computing tokens.
The embedding generated from an input content.
Statistics of the input text associated with the result of content embedding.
Enables context window compression -- mechanism managing model context window so it does not exceed given length.
Config for the count_tokens method.
Parameters for counting tokens.
Response for counting tokens.
Config for optional parameters.
Config for batches.create parameters.
Optional configuration for cached content creation.
Parameters for caches.create method.
Config for optional parameters.
Config for batches.create parameters.
Used to override the default configuration.
Generates the parameters for the private _create method.
Response for the create file method.
Fine-tuning job creation request - optional fields.
Fine-tuning job creation parameters - optional fields.
Result for custom code execution metric. This data type is not supported in Gemini API.
Configures the customized avatar to be used in the session.
Spec for custom output. This data type is not supported in Gemini API.
Distribution computed over a tuning dataset. This data type is not supported in Gemini API.
Dataset bucket used to create a histogram for the distribution given a population of values. This data type is not supported in Gemini API.
Statistics computed over a tuning dataset. This data type is not supported in Gemini API.
Optional parameters for models.get method.
Config for batches.delete parameters.
Optional parameters for caches.delete method.
Parameters for caches.delete method.
Empty response for caches.delete method.
Used to override the default configuration.
Generates the parameters for the get method.
Response for the delete file method.
Configuration for deleting a tuned model.
Parameters for deleting a tuned model.
The return value of delete operation.
Statistics for distillation prompt dataset. These statistics do not include the responses sampled from the teacher model. This data type is not supported in Gemini API.
Distillation hyperparameters for tuning.
Distillation sampling spec for tuning.
Distillation tuning spec for tuning.
Used to override the default configuration.
A custom serializer for Duration that formats it as a string ending in 's'.
Describes the options to customize dynamic retrieval.
The mode of the predictor to be used in dynamic retrieval.
Parameters for the embed_content method.
Optional parameters for the embed_content method.
Request-level metadata for the Gemini Enterprise Agent Platform Embed Content API.
Parameters for the _embed_content method.
Response for the embed_content method.
Enum representing the Gemini Enterprise Agent Platform embedding API to use.
Represents a customer-managed encryption key specification that can be applied to a Vertex AI resource. This data type is not supported in Gemini API.
End of speech sensitivity.
Tool to search public web data, powered by Vertex AI Search and Sec4 compliance. This data type is not supported in Gemini API.
The environment being operated.
The results from an evaluation run performed by the EvaluationService. This data type is not supported in Gemini API.
Evaluate Dataset Run Result for Tuning Job. This data type is not supported in Gemini API.
The dataset used for evaluation. This data type is not supported in Gemini API.
Exact match metric value for an instance. This data type is not supported in Gemini API.
Code generated by the model that is meant to be executed, and the result returned to the model. Generated when using the CodeExecution tool, in which the code will be automatically executed, and a corresponding CodeExecutionResult will also be generated.
Retrieve from data source powered by external API for grounding. The external API is not owned by Google, but need to follow the pre-defined API spec. This data type is not supported in Gemini API.
The search parameters to use for the ELASTIC_SEARCH spec. This data type is not supported in Gemini API.
The search parameters to use for SIMPLE_SEARCH spec. This data type is not supported in Gemini API.
Options for feature selection preference.
A file uploaded to the API.
The FileSearch tool that retrieves knowledge from Semantic Retrieval corpora. Files are imported to Semantic Retrieval corpora using the ImportFile API. This data type is not supported in Vertex AI.
Source of the File.
Output only. The reason why the model stopped generating tokens.
Tuning Spec for Full Fine Tuning. This data type is not supported in Gemini API.
A predicted FunctionCall returned from the model that contains a string representing the FunctionDeclaration.name and a structured JSON object containing the parameters and their values.
Function calling config.
Function calling mode.
Structured representation of a function declaration as defined by the OpenAPI 3.0 specification. Included in this declaration are the function name, description, parameters and response type. This FunctionDeclaration is a representation of a block of code that can be used as a Tool by the model and executed by the client.
The result output from a FunctionCall that contains a string representing the FunctionDeclaration.name and a structured JSON object containing any output from the function is used as context to the model. This should contain the result of a FunctionCall made based on model prediction.
Raw media bytes for function response. Text should not be sent as raw bytes, use the 'text' field.
URI based data for function response. This data type is not supported in Gemini API.
A datatype containing media that is part of a FunctionResponse message. A FunctionResponsePart consists of data which has an associated datatype. A FunctionResponsePart can only contain one of the accepted types in FunctionResponsePart.data. A FunctionResponsePart must have a fixed IANA MIME type identifying the type and subtype of the media if the inline_data field is filled with raw bytes.
Specifies how the response should be scheduled in the conversation. Only applicable to NON_BLOCKING function calls, is ignored otherwise. Defaults to WHEN_IDLE.
Input example for preference optimization. This data type is not supported in Gemini API.
Completion and its preference score. This data type is not supported in Gemini API.
Optional model configuration parameters.
Config for models.generate_content parameters.
Response message for PredictionService.GenerateContent.
Content filter results for a prompt sent in the request. Note: This is sent only in the first stream chunk and only if no candidates were generated due to content violations.
Usage metadata about the content generation request and response. This message provides a detailed breakdown of token usage and other relevant metrics. This data type is not supported in Gemini API.
Generation config.
The configuration for routing the request to a specific model. This can be used to control which model is used for the generation, either automatically or by specifying a model name. This data type is not supported in Gemini API.
The configuration for automated routing. When automated routing is specified, the routing will be determined by the pretrained routing model and customer provided model routing preference. This data type is not supported in Gemini API.
The configuration for manual routing. When manual routing is specified, the model will be selected based on the model name provided. This data type is not supported in Gemini API.
Optional parameters.
Config for batches.get parameters.
Optional parameters for caches.get method.
Parameters for caches.get method.
Used to override the default configuration.
Generates the parameters for the get method.
Optional parameters for models.get method.
Optional parameters for tunings.get method.
Parameters for the get method.
Tool to retrieve knowledge from Google Maps.
Defines the types of Google Maps grounding that can be enabled and their configurations. This data type is not supported in Gemini API.
Grounding with Google Maps Places data (e.g. QueryPlaces). This is the default Google Maps grounding type when no other type is specified. This data type is not supported in Gemini API.
Grounding with Google Maps Routing APIs (ComputeRoutes and SearchAlongRoute). This data type is not supported in Gemini API.
The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide. This data type is not supported in Gemini API.
GoogleSearch tool type. Tool to support Google Search in Model. Powered by Google.
Tool to retrieve public web data for grounding, powered by Google.
Represents a whole or partial calendar date, such as a birthday. The time of day and time zone are either specified elsewhere or are insignificant. The date is relative to the Gregorian Calendar. This can represent one of the following: * A full date, with non-zero year, month, and day values. * A month and day, with a zero year (for example, an anniversary). * A year on its own, with a zero month and a zero day. * A year and month, with a zero day (for example, a credit card expiration date). Related types: * google.type.TimeOfDay * google.type.DateTime * google.protobuf.Timestamp. This data type is not supported in Gemini API.
A piece of evidence that supports a claim made by the model.
User provided metadata about the GroundingFact. This data type is not supported in Vertex AI.
An Image chunk is a piece of evidence that comes from an image search result. It contains the URI of the image search result and the URI of the image. This is used to provide the user with a link to the source of the information.
A Maps chunk is a piece of evidence that comes from Google Maps.
The sources that were used to generate the place answer.
Author attribution for a photo or review.
Encapsulates a review snippet.
Route information from Google Maps. This data type is not supported in Gemini API.
Context retrieved from a data source to ground the model's response. This is used when a retrieval tool fetches information from a user-provided corpus or a public dataset.
A list of string values. This data type is not supported in Vertex AI.
A Web chunk is a piece of evidence that comes from a web page. It contains the URI of the web page, the title of the page, and the domain of the page. This is used to provide the user with a link to the source of the information.
Information for various kinds of grounding.
A URI that can be used to flag a place or review for inappropriate content. This is populated only when the grounding source is Google Maps. This data type is not supported in Gemini API.
The method for blocking content. If not specified, the default behavior is to use the probability score. This enum is not supported in Gemini API.
The threshold for blocking content. If the harm probability exceeds this threshold, the content will be blocked.
The harm category to be blocked.
Output only. The probability of harm for this category.
Output only. The severity of harm for this category. This enum is not supported in Gemini API.
Configuration for history exchange between client and server.
The location of the API key. This enum is not supported in Gemini API.
A wrapper class for the http response.
The image generation configuration to be used in GenerateContentConfig.
The image output format for generated images. This data type is not supported in Gemini API.
Configuration for image-specific output formatting.
Image search for grounding and related configurations.
Config for inlined_embedding_responses parameter.
Config for inlined request.
Config for inlined_responses parameter.
A custom serializer for Instant that encodes to and decodes from ISO-8601 strings.
Represents a time interval, encoded as a Timestamp start (inclusive) and a Timestamp end (exclusive). The start must be less than or equal to the end. When the start equals the end, the interval is empty (matches no time). When both start and end are unspecified, the interval matches any time.
Deprecated: Language auto-detection is now the default when language_codes is omitted.
Deprecated: Use AudioTranscriptionConfig.language_codes instead.
An object that represents a latitude/longitude pair. This is expressed as a pair of doubles to represent degrees latitude and degrees longitude. Unless specified otherwise, this object must conform to the WGS84 standard. Values must be within normalized ranges.
Config for optional parameters.
Config for batches.list parameters.
Config for batches.list return value.
Config for caches.list method.
Parameters for caches.list method.
Used to override the default configuration.
Generates the parameters for the list method.
Response for the list files method.
Configuration for the list tuning jobs method.
Parameters for the list tuning jobs method.
Response for the list tuning jobs method.
Incremental update of the current conversation delivered from the client.
Messages sent by the client in the API call.
User input that is sent in real time.
Message contains configuration that will apply for the duration of the streaming session.
Client generated response to a ToolCall received from the server.
Session config for the API connection.
Incremental server update generated by the model in response to client messages.
Server will not be able to service client soon.
Response message for API call.
Update of the session resumption state.
Sent in response to a LiveGenerateContentSetup message from the client.
Request for the client to execute the function_calls and return the responses with the matching ids.
Notification for the client that a previously issued ToolCallMessage with the specified ids should have been not executed and should be cancelled.
The log probabilities of the tokens generated by the model. This is useful for understanding the model's confidence in its predictions and for debugging. For example, you can use log probabilities to identify when the model is making a less confident prediction or to explore alternative responses that the model considered. A low log probability can also indicate that the model is "hallucinating" or generating factually incorrect information.
A single token and its associated log probability.
A list of the top candidate tokens and their log probabilities at each decoding step. This can be used to see what other tokens the model considered.
Match operation to use for evaluating rewards. This enum is not supported in Gemini API.
A MCPServer is a server that can be called by the model to perform actions. It is a server that implements the MCP protocol. Next ID: 6. This data type is not supported in Vertex AI.
The modality that this token count applies to.
The media resolution to use.
Represents a breakdown of token usage by modality. This message is used in CountTokensResponse and GenerateContentResponse.UsageMetadata to provide a detailed view of how many tokens are used by each modality (e.g., text, image, video) in a request. This is particularly useful for multimodal models, allowing you to track and manage token consumption for billing and quota purposes.
A trained machine learning model.
Configuration for Model Armor. Model Armor is a Google Cloud service that provides safety and security filtering for prompts and responses. It helps protect your AI applications from risks such as harmful content, sensitive data leakage, and prompt injection attacks. This data type is not supported in Gemini API.
The model routing preference.
Config for model selection.
The stage of the underlying model. This enum is not supported in Vertex AI.
The status of the underlying model. This is used to indicate the stage of the underlying model and the retirement time if applicable. This data type is not supported in Vertex AI.
Configuration for a multi-speaker text-to-speech request.
Describes the info for output of EvaluationService. This data type is not supported in Gemini API.
Output only. Pairwise metric choice. This enum is not supported in Gemini API.
Spec for pairwise metric result. This data type is not supported in Gemini API.
A datatype containing media content.
Partial argument value of the function call. This data type is not supported in Gemini API.
Media resolution for the input media.
The tokenization quality used for given media.
Tuning spec for Partner models. This data type is not supported in Gemini API.
Sites with confidence level chosen & above this value will be blocked from the search results. This enum is not supported in Gemini API.
Spec for pointwise metric result. This data type is not supported in Gemini API.
Configuration for a prebuilt voice.
Statistics computed for datasets used for preference optimization. This data type is not supported in Gemini API.
Hyperparameters for Preference Optimization. This data type is not supported in Gemini API.
Preference optimization tuning spec for tuning.
A pre-tuned model for continuous tuning. This data type is not supported in Gemini API.
Config for proactivity features.
Controls whether prominent people (celebrities) generation is allowed. If used with personGeneration, personGeneration enum would take precedence. For instance, if ALLOW_NONE is set, all person generation would be blocked. If this field is unspecified, the default behavior is to allow prominent people. This enum is not supported in Gemini API.
A RagChunk includes the content of a chunk of a RagFile, and associated metadata. This data type is not supported in Gemini API.
Represents where the chunk starts and ends in the document. This data type is not supported in Gemini API.
Specifies the context retrieval config. This data type is not supported in Gemini API.
Config for filters. This data type is not supported in Gemini API.
Config for Hybrid Search. This data type is not supported in Gemini API.
Config for ranking and reranking. This data type is not supported in Gemini API.
Config for LlmRanker. This data type is not supported in Gemini API.
Config for Rank Service. This data type is not supported in Gemini API.
Marks the end of user activity.
Reinforcement tuning autorater scorer.
Scores autorater responses by using exact string match reward scorer. This data type is not supported in Gemini API.
Scores responses by directly converting the parsed autorater response to a float reward. Note: Reward is clipped to be within [-1, 1], i.e., reward = max(min(reward, 1.0), -1.0). This data type is not supported in Gemini API.
ReinforcementTuningCloudRunRewardScorer allows users to implement a reward function through GCP Cloud Run. Comparing with ReinforcementTuningCodeExecutionRewardScorer that runs in a Sandbox and has no internet access, Cloud Run reward scorer is fully controlled by users. The Cloud Run service should implement the following HTTP API: HTTP method: POST HTTP request body: `` { "example": ReinforcementTuningExample, "response": Content, "metadata": { "step": int "tuning_job_id": int64 } } `` * example is a ReinforcementTuningExample in ProtoJSON format, (i.e., the format is the same as as one line in the training/validation dataset except that the keys must be in camel case). System instructions (i.e., example.get("systemInstruction")) and references (i.e., example.get("references")) are also included in the example provided that they are set in the training/validation dataset. * response is a Content in ProtoJSON format (i.e., keys must be in camel case), which is the same as the Online Prediction response for Gemini models. HTTP response body: { "reward": float, "user_requested_aux_info": str // Optional } where the field "user_requested_aux_info" is any (optional) string provided by users for assisting debugging. It's in snake case. This field is mostly useful when calling the GenAiTuningService.ValidateReinforcementTuningReward API, where the proto field (not Cloud Run HTTP response body) userRequestedAuxInfo will be populated if the Cloud Run reward function sets this field in the HTTP response. The following are examples for the HTTP request and response body. Example HTTP request body: `` { "example": { "contents": [ { "role": "user", "parts": [ { "text": "What is the capital of France?" } ] } ], "references": { "answer": "Paris" } }, "response": { "parts": [ { "text": "London" } ] }, "metadata": { "step": 1, "tuning_job_id": 123456789 } } `` Example HTTP response body: `` { "reward": -1.0 } `` Note: Reward output by Cloud Run reward function is clipped to be within [-1, 1], i.e., reward = max(min(reward, 1.0), -1.0). This data type is not supported in Gemini API.
ReinforcementTuningCodeExecutionRewardScorer allows users to implement a function to evaluate rewards for the sample response. The function signature is as follows: `` def evaluate(example: dict[str, Any], response: dict[str, Any]) -> float: ... `` example is a ReinforcementTuningExample in ProtoJSON format, (i.e., the format is the same as as one line in the training/validation dataset except that the keys must be in camel case). System instructions (i.e., example.get("systemInstruction")) and references (i.e., example.get("references")) are also included in the example provided that they are set in the training/validation dataset. response is a Content in ProtoJSON format (i.e., keys must be in camel case), which is the same as the Online Prediction response for Gemini models. Note: Reward output by the evaluate function is clipped to be within [-1, 1], i.e., reward = max(min(reward, 1.0), -1.0). This data type is not supported in Gemini API.
Hyperparameters for Reinforcement Tuning.
Defines how to parse sample response config for reinforcement tuning. The parsed response (i.e., substring) will be passed to the reward functions. For example, the input prompt might be: "Perform step-by-step thoughts first to problem A, finally output answer in the `` { "parseType": "REGEX_EXTRACT", "regexExtractExpression": ".*(.*?)" } `` The resulting parsed response would be "Yes" and will be passed to the reward functions for evaluating rewards. This data type is not supported in Gemini API.
The reward info for a reward function.
Reinforcement tuning spec for tuning.
ReinforcementTuningStringMatchRewardScorer is used to score parsed responses for string matching use cases. For example, for math problems, users can use string match scorer to check if the correct exact answer is generated. Note: Reward returned by the string match reward function is clipped to be within [-1, 1] if wrongAnswerReward or correctAnswerReward are beyond the range, i.e., reward = max(min(reward, 1.0), -1.0). This data type is not supported in Gemini API.
JsonMatchExpression supports converting the parsed responses to JSON format, finding the value in the JSON response that matches the key_name in the first level, and performing StringMatchExpression operation on the matched JSON value. This data type is not supported in Gemini API.
Evaluates parsed response using match type against the expression. Returns true if MatchOperation(target, expression) evaluates to true, and false otherwise. This data type is not supported in Gemini API.
Represents how much to think for the tuning job.
Sample reinforcement tuning user data in the training dataset. The contents are truncated for better UI showing. This data type is not supported in Gemini API.
The configuration for the replicated voice to use.
Configuration for the model to configure output formatting and delivery. This data type is not supported in Gemini API.
Defines the type for parsing sample response. This enum is not supported in Gemini API.
Defines a retrieval tool that model can call to access external knowledge. This data type is not supported in Gemini API.
Retrieval config.
Metadata returned to client when grounding is enabled.
Rouge metric value for an instance. This data type is not supported in Gemini API.
SafetyPolicy
A safety rating for a piece of content. The safety rating contains the harm category and the harm probability level.
A safety setting that affects the safety-blocking behavior. A SafetySetting consists of a harm category and a threshold for that category.
Schema is used to define the format of input/output data.
The entry point used to search for grounding sources.
Different types of search that can be enabled on the GoogleSearch tool.
Pricing and performance service tier.
Configuration of session resumption mechanism.
Config for response parameter.
Single reinforcement tuning reward config.
Context window will be truncated by keeping only suffix of it.
Configuration for a single speaker in a multi-speaker setup.
Config for speech generation and transcription.
Start of speech sensitivity.
A transport that can stream HTTP requests and responses. Next ID: 6. This data type is not supported in Vertex AI.
Hyperparameters for SFT. This data type is not supported in Gemini API.
Dataset distribution for Supervised Tuning. This data type is not supported in Gemini API.
Dataset bucket used to create a histogram for the distribution given a population of values. This data type is not supported in Gemini API.
Tuning data statistics for Supervised Tuning. This data type is not supported in Gemini API.
Supervised tuning spec for tuning.
Configuration for text-specific output formatting.
The thinking features configuration.
The number of thoughts tokens that the model should generate.
Tokens info with a list of tokens and the corresponding list of token ids.
Tool details of a tool that the model may use to generate a response.
Tool that executes code generated by the model, and automatically returns the result to the model. See also ExecutableCode and CodeExecutionResult, which are input and output to this tool. This data type is not supported in Gemini API.
Tool config. This config is shared for all tools provided in the request.
ExaAiSearch tool type. A tool that uses the Exa.ai search engine for grounding. This data type is not supported in Gemini API.
ParallelAiSearch tool type. A tool that uses the Parallel.ai search engine for grounding. This data type is not supported in Gemini API.
The output from a server-side ToolCall execution.
Output only. The traffic type for this request. This enum is not supported in Gemini API.
Config for stream translation.
TunedModel for the Tuned Model of a Tuning Job.
TunedModelCheckpoint for the Tuned Model of a Tuning Job.
A tuned machine learning model.
Supervised fine-tuning training dataset.
The tuning data statistic values for TuningJob. This data type is not supported in Gemini API.
A single example for tuning. This data type is not supported in Vertex AI.
A tuning job.
Tuning job metadata. This data type is not supported in Gemini API.
Output only. The detail state of the tuning job (while the overall JobState is running). This enum is not supported in Gemini API.
Enum representing the tuning method.
Tuning mode. This enum is not supported in Gemini API.
A long-running operation.
The speed of the tuning job. Only supported for Veo 3.0 models. This enum is not supported in Gemini API.
The tuning task for Veo. This enum is not supported in Gemini API.
The reason why the turn is complete.
Options about which input is included in the user's turn.
Optional parameters for caches.update method.
Configuration for updating a tuned model.
Configuration for updating a tuned model.
Used to override the default configuration.
Tool to support URL context.
Metadata returned when the model uses the url_context tool to get information from a user-provided URL.
The metadata for a single URL retrieval.
The status of the URL retrieval.
Usage metadata about response(s).
The type of the VAD signal.
Optional parameters for tunings.validate_reward.
Parameters for the validate_reward method.
Response for the validate_reward method.
Hyperparameters for Veo. This data type is not supported in Gemini API.
Tuning Spec for Veo LoRA Model Tuning. This data type is not supported in Gemini API.
Tuning Spec for Veo Model Tuning. This data type is not supported in Gemini API.
Retrieve from Vertex AI Search datastore or engine for grounding. datastore and engine are mutually exclusive. See https://cloud.google.com/products/agent-builder. This data type is not supported in Gemini API.
Define data stores within engine to filter on in a search call and configurations for those data stores. For more information, see https://cloud.google.com/generative-ai-app-builder/docs/reference/rpc/google.cloud.discoveryengine.v1#datastorespec. This data type is not supported in Gemini API.
This class is experimental and may change in future versions.
Retrieve from Vertex RAG Store for grounding. This data type is not supported in Gemini API.
The definition of the Rag resource. This data type is not supported in Gemini API.
Provides metadata for a video, including the start and end offsets for clipping and the frame rate.
The orientation of the video. Defaults to LANDSCAPE. This enum is not supported in Gemini API.
Configuration for video-specific output formatting. This data type is not supported in Gemini API.
Voice activity signal.
The type of the voice activity signal.
The configuration for the voice to use.
The signature of the voice consent check.
Configuration for webhook notifications.