Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window. Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window.

Cloud Speech-to-Text API

Converts audio to text by applying powerful neural network models.

Service: speech.googleapis.com

The Service name speech.googleapis.com is needed to create RPC client stubs.

`google.cloud.speech.v1.Adaptation`

Methods
`CreateCustomClass`	Create a custom class.
`CreatePhraseSet`	Create a set of phrase hints.
`DeleteCustomClass`	Delete a custom class.
`DeletePhraseSet`	Delete a phrase set.
`GetCustomClass`	Get a custom class.
`GetPhraseSet`	Get a phrase set.
`ListCustomClasses`	List custom classes.
`ListPhraseSet`	List phrase sets.
`UpdateCustomClass`	Update a custom class.
`UpdatePhraseSet`	Update a phrase set.

`google.cloud.speech.v1.Speech`

Methods
`LongRunningRecognize`	Performs asynchronous speech recognition: receive results via the google.longrunning.Operations interface.
`Recognize`	Performs synchronous speech recognition: receive results after all audio has been sent and processed.
`StreamingRecognize`	Performs bidirectional streaming speech recognition: receive results while sending audio.

`google.cloud.speech.v1p1beta1.Adaptation`

Methods
`CreateCustomClass`	Create a custom class.
`CreatePhraseSet`	Create a set of phrase hints.
`DeleteCustomClass`	Delete a custom class.
`DeletePhraseSet`	Delete a phrase set.
`GetCustomClass`	Get a custom class.
`GetPhraseSet`	Get a phrase set.
`ListCustomClasses`	List custom classes.
`ListPhraseSet`	List phrase sets.
`UpdateCustomClass`	Update a custom class.
`UpdatePhraseSet`	Update a phrase set.

`google.cloud.speech.v1p1beta1.Speech`

Methods
`LongRunningRecognize`	Performs asynchronous speech recognition: receive results via the google.longrunning.Operations interface.
`Recognize`	Performs synchronous speech recognition: receive results after all audio has been sent and processed.
`StreamingRecognize`	Performs bidirectional streaming speech recognition: receive results while sending audio.

`google.longrunning.Operations`

Methods
`CancelOperation`	Starts asynchronous cancellation on a long-running operation.
`DeleteOperation`	Deletes a long-running operation.
`GetOperation`	Gets the latest state of a long-running operation.
`ListOperations`	Lists operations that match the specified filter in the request.
`WaitOperation`	Waits until the specified long-running operation is done or reaches at most a specified timeout, returning the latest state.