Diatheke API Reference

Session data, used to determine the correct Cubic model to use for ASR, with other contextual information.

Audio data to transcribe.

The transcription.

Confidence estimate between 0 and 1. A higher number represents a higher likelihood of the output being correct.

True if a timeout was defined for the session’s current input state in the Diatheke model, and the timeout expired before getting a transcription. This timeout refers to the amount of time a user has to verbally respond to Diatheke after the ASR stream has been created, and should not be confused with a network connection timeout.

The user must provide input to Diatheke.

The client app must execute the specified command.

The client app should provide the reply to the user.

The client app should call the Transcribe method to capture the user’s input.

The ID of the command to execute, as defined in the Diatheke model.

The command ID, as given by the CommandAction

Output from the command expected by the Diatheke model. For example, this could be the result of a data query.

If there was an error during execution, indicate it here with a brief message that will be logged by Diatheke.

Diatheke model ID, which is used to create a new session.

Pretty model name, which may be used for display purposes.

Language code of the model.

The ASR audio sample rate, if ASR is enabled.

The TTS audio sample rate, if TTS is enabled.

Text of the reply

TTS model to use with the TTSReply method

The session token.

Process the user supplied text.

Process an ASR result.

Process the result of a completed command.

Change the current session state.

The updated session token.

The list of actions the client should take next, using the session token returned with this result.

Specifies the Diatheke model ID to use for the session.

Specifies a custom wakeword to use for this session. The wakeword must be enabled in the Diatheke model for this to have any effect. It will override the default wakeword specified in the model.

The ID of the story to run, as defined in the Diatheke model.

A list of parameters to set before running the given story. This will replace any parameters currently defined in the session.

Session ID, useful for correlating logging between a client and the server.

Additional data supplied by the client app, which will be logged with other session info by the server.

The ID of the transcribe action, which is useful to differentiate separate transcription tasks within a single sesssion.

(Required) The ASR model to use for transcription.

(Optional) A Diatheke model to use for end-of-stream conditions. If empty, the server will not be able to automatically close the transcribe stream based on conditions defined in the model, such as a non-speech timeout or an “end-transcription” intent. When empty, the stream must be closed by the client application.

Action defining the transcribe configuration.

Audio data to transcribe.

The transcription.

Confidence estimate between 0 and 1. A higher number represents a higher likelihood that the transcription is correct.

True if this is a partial result, in which case the next result will be for the same audio, either repeating or correcting the text in this result. When false, this represents the final transcription for an utterance, which will not change with further audio input. It is sent when the ASR has identified an endpoint. After the final transcription is sent, any additional results sent on the Transcribe stream belong to the next utterance.

Dialog management engine

NLU engine

ASR engine

TTS engine

True if the next user input must begin with a wake-word.

True if the input is required immediately (i.e., in response to a question Diatheke asked the user). When false, the client should be allowed to wait indefinitely for the user to provide input.