Package google.assistant.embedded.v1alpha1

Index

EmbeddedAssistant

Service that implements Google Assistant API.

Converse

rpc Converse(ConverseRequest) returns (ConverseResponse)

Initiates or continues a conversation with the embedded assistant service. Each call performs one round-trip, sending an audio request to the service and receiving the audio response. Uses bidirectional streaming to receive results, such as the END_OF_UTTERANCE event, while sending audio.

A conversation is one or more gRPC connections, each consisting of several streamed requests and responses. For example, the user says Add to my shopping list and the assistant responds What do you want to add?. The sequence of streamed requests and responses in the first gRPC message could be:

  • ConverseRequest.config
  • ConverseRequest.audio_in
  • ConverseRequest.audio_in
  • ConverseRequest.audio_in
  • ConverseRequest.audio_in
  • ConverseResponse.event_type.END_OF_UTTERANCE
  • ConverseResponse.result.microphone_mode.DIALOG_FOLLOW_ON
  • ConverseResponse.audio_out
  • ConverseResponse.audio_out
  • ConverseResponse.audio_out

The user then says bagels and the assistant responds OK, I've added bagels to your shopping list. This is sent as another gRPC connection call to the Converse method, again with streamed requests and responses, such as:

  • ConverseRequest.config
  • ConverseRequest.audio_in
  • ConverseRequest.audio_in
  • ConverseRequest.audio_in
  • ConverseResponse.event_type.END_OF_UTTERANCE
  • ConverseResponse.result.microphone_mode.CLOSE_MICROPHONE
  • ConverseResponse.audio_out
  • ConverseResponse.audio_out
  • ConverseResponse.audio_out
  • ConverseResponse.audio_out

Although the precise order of responses is not guaranteed, sequential ConverseResponse.audio_out messages will always contain sequential portions of audio.

Authorization

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/assistant-sdk-prototype

For more information, see the Auth Guide.

AudioInConfig

Specifies how to process the audio_in data that will be provided in subsequent requests. For recommended settings, see the Google Assistant gRPC API best practices.

Fields
encoding

Encoding

Required Encoding of audio data sent in all audio_in messages.

sample_rate_hertz

int32

Required Sample rate (in Hertz) of the audio data sent in all audio_in messages. Valid values are from 16000-24000, but 16000 is optimal. For best results, set the sampling rate of the audio source to 16000 Hz. If that's not possible, use the native sample rate of the audio source (instead of re-sampling).

Encoding

Audio encoding of the data sent in the audio message. Audio must be one-channel (mono). The only language supported is "en-US".

Enums
ENCODING_UNSPECIFIED Not specified. Will return result google.rpc.Code.INVALID_ARGUMENT.
LINEAR16 Uncompressed 16-bit signed little-endian samples (Linear PCM). This encoding includes no header, only the raw audio bytes.
FLAC FLAC (Free Lossless Audio Codec) is the recommended encoding because it is lossless--therefore recognition is not compromised--and requires only about half the bandwidth of LINEAR16. This encoding includes the FLAC stream header followed by audio data. It supports 16-bit and 24-bit samples, however, not all fields in STREAMINFO are supported.

AudioOut

The audio containing the assistant's response to the query. Sequential chunks of audio data are received in sequential ConverseResponse messages.

Fields
audio_data

bytes

Output-only The audio data containing the assistant's response to the query. Sequential chunks of audio data are received in sequential ConverseResponse messages.

AudioOutConfig

Specifies the desired format for the server to use when it returns audio_out messages.

Fields
encoding

Encoding

Required The encoding of audio data to be returned in all audio_out messages.

sample_rate_hertz

int32

Required The sample rate in Hertz of the audio data returned in audio_out messages. Valid values are: 16000-24000.

volume_percentage

int32

Required Current volume setting of the device's audio output. Valid values are 1 to 100 (corresponding to 1% to 100%).

Encoding

Audio encoding of the data returned in the audio message. All encodings are raw audio bytes with no header, except as indicated below.

Enums
ENCODING_UNSPECIFIED Not specified. Will return result google.rpc.Code.INVALID_ARGUMENT.
LINEAR16 Uncompressed 16-bit signed little-endian samples (Linear PCM).
MP3 MP3 audio encoding. The sample rate is encoded in the payload.
OPUS_IN_OGG Opus-encoded audio wrapped in an ogg container. The result will be a file which can be played natively on Android and in some browsers (such as Chrome). The quality of the encoding is considerably higher than MP3 while using the same bitrate. The sample rate is encoded in the payload.

ConverseConfig

Specifies how to process the ConverseRequest messages.

Fields
audio_in_config

AudioInConfig

Required Specifies how to process the subsequent incoming audio.

audio_out_config

AudioOutConfig

Required Specifies how to format the audio that will be returned.

converse_state

ConverseState

Required Represents the current dialog state.

ConverseRequest

The top-level message sent by the client. Clients must send at least two, and typically numerous ConverseRequest messages. The first message must contain a config message and must not contain audio_in data. All subsequent messages must contain audio_in data and must not contain a config message.

Fields
Union field converse_request. Exactly one of these fields must be specified in each ConverseRequest. converse_request can be only one of the following:
config

ConverseConfig

The config message provides information to the recognizer that specifies how to process the request. The first ConverseRequest message must contain a config message.

audio_in

bytes

The audio data to be recognized. Sequential chunks of audio data are sent in sequential ConverseRequest messages. The first ConverseRequest message must not contain audio_in data and all subsequent ConverseRequest messages must contain audio_in data. The audio bytes must be encoded as specified in AudioInConfig. Audio must be sent at approximately real-time (16000 samples per second). An error will be returned if audio is sent significantly faster or slower.

ConverseResponse

The top-level message received by the client. A series of one or more ConverseResponse messages are streamed back to the client.

Fields
Union field converse_response. Exactly one of these fields will be populated in each ConverseResponse. converse_response can be only one of the following:
error

Status

Output-only If set, returns a google.rpc.Status message that specifies the error for the operation. If an error occurs during processing, this message will be set and there will be no further messages sent.

event_type

EventType

Output-only Indicates the type of event.

audio_out

AudioOut

Output-only The audio containing the assistant's response to the query.

result

ConverseResult

Output-only The semantic result for the user's spoken query.

EventType

Indicates the type of event.

Enums
EVENT_TYPE_UNSPECIFIED No event specified.
END_OF_UTTERANCE This event indicates that the server has detected the end of the user's speech utterance and expects no additional speech. Therefore, the server will not process additional audio (although it may subsequently return additional results). The client should stop sending additional audio data, half-close the gRPC connection, and wait for any additional results until the server closes the gRPC connection.

ConverseResult

The semantic result for the user's spoken query.

Fields
spoken_request_text

string

Output-only The recognized transcript of what the user said.

spoken_response_text

string

Output-only The text of the assistant's spoken response. This is only returned for an IFTTT action.

conversation_state

bytes

Output-only State information for subsequent ConverseRequest. This value should be saved in the client and returned in the conversation_state with the next ConverseRequest. (The client does not need to interpret or otherwise use this value.) There is no need to save this information across device restarts.

microphone_mode

MicrophoneMode

Output-only Specifies the mode of the microphone after this Converse RPC is processed.

volume_percentage

int32

Output-only Updated volume level. The value will be 0 or omitted (indicating no change) unless a voice command such as "Increase the volume" or "Set volume level 4" was recognized, in which case the value will be between 1 and 100 (corresponding to the new volume level of 1% to 100%). Typically, a client should use this volume level when playing the audio_out data, and retain this value as the current volume level and supply it in the AudioOutConfig of the next ConverseRequest. (Some clients may also implement other ways to allow the current volume level to be changed, for example, by providing a knob that the user can turn.)

MicrophoneMode

Possible states of the microphone after a Converse RPC completes.

Enums
MICROPHONE_MODE_UNSPECIFIED No mode specified.
CLOSE_MICROPHONE The service is not expecting a follow-on question from the user. The microphone should remain off until the user re-activates it.
DIALOG_FOLLOW_ON The service is expecting a follow-on question from the user. The microphone should be re-opened when the AudioOut playback completes (by starting a new Converse RPC call to send the new audio).

ConverseState

Provides information about the current dialog state.

Fields
conversation_state

bytes

Required The conversation_state value returned in the prior ConverseResponse. Omit (do not set the field) if there was no prior ConverseResponse. If there was a prior ConverseResponse, do not omit this field; doing so will end that conversation (and this new request will start a new conversation).