Creates a new conversation. Conversations are auto-completed after 24 hours. Conversation Lifecycle: There are two stages during a conversation: Automated Agent Stage and Assist Stage. For Automated Agent Stage, there will be a dialogflow agent responding to user queries. For Assist Stage, there's no dialogflow agent responding to user queries. But we will provide suggestions which are generated from conversation. If Conversation.conversation_profile is configured for a dialogflow agent, conversation will start from Automated Agent Stage, otherwise, it will start from Assist Stage. And during Automated Agent Stage, once an Intent with Intent.live_agent_handoff is triggered, conversation will transfer to Assist Stage.


You will need authorization for at least one of the following scopes to make a valid call:


If unset, the scope for this method defaults to You can set the scope for this method like this: dialogflow2 --scope <scope> projects conversations-create ...

Required Scalar Argument

  • <parent> (string)
    • Required. Resource identifier of the project creating the conversation. Format: projects//locations/.

Required Request Value

The request value is a data-structure with various fields. Each field may be a simple scalar or another data-structure. In the latter case it is advised to set the field-cursor to the data-structure's field to specify values more concisely.

For example, a structure like this:

  conversation-profile: string
  conversation-stage: string
  end-time: string
  lifecycle-state: string
  name: string
    phone-number: string
  start-time: string

can be set completely with the following arguments which are assumed to be executed in the given order. Note how the cursor position is adjusted to the respective structures, allowing simple field names to be used most of the time.

  • -r . conversation-profile=dolores
    • Required. The Conversation Profile to be used to configure this Conversation. This field cannot be updated. Format: projects//locations//conversationProfiles/.
  • conversation-stage=consetetur
    • The stage of a conversation. It indicates whether the virtual agent or a human agent is handling the conversation. If the conversation is created with the conversation profile that has Dialogflow config set, defaults to ConversationStage.VIRTUAL_AGENT_STAGE; Otherwise, defaults to ConversationStage.HUMAN_ASSIST_STAGE. If the conversation is created with the conversation profile that has Dialogflow config set but explicitly sets conversation_stage to ConversationStage.HUMAN_ASSIST_STAGE, it skips ConversationStage.VIRTUAL_AGENT_STAGE stage and directly goes to ConversationStage.HUMAN_ASSIST_STAGE.
  • end-time=stet
    • Output only. The time the conversation was finished.
  • lifecycle-state=accusam
    • Output only. The current state of the Conversation.
  • name=consetetur
    • Output only. The unique identifier of this conversation. Format: projects//locations//conversations/.
  • phone-number phone-number=takimata

    • Output only. The phone number to connect to this conversation.
  • .. start-time=sed

    • Output only. The time the conversation was started.

About Cursors

The cursor position is key to comfortably set complex nested structures. The following rules apply:

  • The cursor position is always set relative to the current one, unless the field name starts with the . character. Fields can be nested such as in -r f.s.o .
  • The cursor position is set relative to the top-level structure if it starts with ., e.g. -r .s.s
  • You can also set nested fields without setting the cursor explicitly. For example, to set a value relative to the current cursor position, you would specify -r struct.sub_struct=bar.
  • You can move the cursor one level up by using ... Each additional . moves it up one additional level. E.g. ... would go three levels up.

Optional Output Flags

The method's return value a JSON encoded structure, which will be written to standard output by default.

  • -o out
    • out specifies the destination to which to write the server's result to. It will be a JSON-encoded structure. The destination may be - to indicate standard output, or a filepath that is to contain the received bytes. If unset, it defaults to standard output.

Optional Method Properties

You may set the following properties to further configure the call. Please note that -p is followed by one or more key-value-pairs, and is called like this -p k1=v1 k2=v2 even though the listing below repeats the -p for completeness.

  • -p conversation-id=string
    • Optional. Identifier of the conversation. Generally it's auto generated by Google. Only set it if you cannot wait for the response to return a auto-generated one to you. The conversation ID must be compliant with the regression fomula a-zA-Z* with the characters length in range of [3,64]. If the field is provided, the caller is resposible for 1. the uniqueness of the ID, otherwise the request will be rejected. 2. the consistency for whether to use custom ID or not under a project to better ensure uniqueness.

Optional General Properties

The following properties can configure any call, and are not specific to this method.

  • -p $-xgafv=string

    • V1 error format.
  • -p access-token=string

    • OAuth access token.
  • -p alt=string

    • Data format for response.
  • -p callback=string

    • JSONP
  • -p fields=string

    • Selector specifying which fields to include in a partial response.
  • -p key=string

    • API key. Your API key identifies your project and provides you with API access, quota, and reports. Required unless you provide an OAuth 2.0 token.
  • -p oauth-token=string

    • OAuth 2.0 token for the current user.
  • -p pretty-print=boolean

    • Returns response with indentations and line breaks.
  • -p quota-user=string

    • Available to use for quota purposes for server-side applications. Can be any arbitrary string assigned to a user, but should not exceed 40 characters.
  • -p upload-type=string

    • Legacy upload protocol for media (e.g. "media", "multipart").
  • -p upload-protocol=string

    • Upload protocol for media (e.g. "raw", "multipart").