Hume AI Speech To Speech (EVI) API

openapi: 3.2.0
info:
  title: Speech-to-speech (EVI) Speech To Speech (EVI) API
  version: 1.0.0
servers:
- url: https://api.hume.ai
tags:
- name: Speech To Speech (EVI)
paths: {}
webhooks:
  chat-ended:
    post:
      operationId: chat-ended
      summary: Chat Ended
      description: Sent when an EVI chat ends.
      responses:
        '200':
          description: Webhook received successfully
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/WebhookEventChatEnded'
      tags:
      - Speech To Speech (EVI)
  chat-started:
    post:
      operationId: chat-started
      summary: Chat Started
      description: Sent when an EVI chat is started.
      responses:
        '200':
          description: Webhook received successfully
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/WebhookEventChatStarted'
      tags:
      - Speech To Speech (EVI)
  tool-call:
    post:
      operationId: tool-call
      summary: Tool Call
      description: Sent when EVI triggers a tool call
      responses:
        '200':
          description: Webhook received successfully
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/WebhookEventToolCall'
      tags:
      - Speech To Speech (EVI)
components:
  schemas:
    WebhookEventChatStartType:
      type: string
      enum:
      - new_chat_group
      - resumed_chat_group
      title: WebhookEventChatStartType
    ToolCallMessage:
      type: object
      properties:
        custom_session_id:
          type:
          - string
          - 'null'
          description: Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions.
        name:
          type: string
          description: Name of the tool called.
        parameters:
          type: string
          description: 'Parameters of the tool.


            These parameters define the inputs needed for the tool''s execution, including the expected data type and description for each input field. Structured as a stringified JSON schema, this format ensures the tool receives data in the expected format.'
        response_required:
          type: boolean
          description: Indicates whether a response to the tool call is required from the developer, either in the form of a [Tool Response message](/reference/empathic-voice-interface-evi/chat/chat#send.Tool%20Response%20Message.type) or a [Tool Error message](/reference/empathic-voice-interface-evi/chat/chat#send.Tool%20Error%20Message.type).
        tool_call_id:
          type: string
          description: 'The unique identifier for a specific tool call instance.


            This ID is used to track the request and response of a particular tool invocation, ensuring that the correct response is linked to the appropriate request.'
        tool_type:
          $ref: '#/components/schemas/ToolType'
          description: Type of tool called. Either `builtin` for natively implemented tools, like web search, or `function` for user-defined tools.
        type:
          type: string
          enum:
          - tool_call
          description: 'The type of message sent through the socket; for a Tool Call message, this must be `tool_call`.


            This message indicates that the supplemental LLM has detected a need to invoke the specified tool.'
      required:
      - name
      - parameters
      - response_required
      - tool_call_id
      - tool_type
      - type
      description: '**Indicates that the supplemental LLM has detected a need to invoke the specified tool.** This message is only received for user-defined function tools.


        Contains the tool name, parameters (as a stringified JSON schema), whether a response is required from the developer (either in the form of a `ToolResponseMessage` or a `ToolErrorMessage`), the unique tool call ID for tracking the request and response, and the tool type. See our [Tool Use Guide](/docs/speech-to-speech-evi/features/tool-use) for further details.'
      title: ToolCallMessage
    WebhookEventChatStarted:
      type: object
      properties:
        chat_group_id:
          type: string
          description: Unique ID of the **Chat Group** associated with the **Chat** session.
        chat_id:
          type: string
          description: Unique ID of the **Chat** session.
        config_id:
          type:
          - string
          - 'null'
          description: Unique ID of the EVI **Config** used for the session.
        caller_number:
          type:
          - string
          - 'null'
          description: Phone number of the caller in E.164 format (e.g., `+12223333333`). This field is included only if the Chat was created via the [Twilio phone calling](/docs/empathic-voice-interface-evi/phone-calling) integration.
        chat_start_type:
          $ref: '#/components/schemas/WebhookEventChatStartType'
          description: Indicates whether the chat is the first in a new Chat Group (`new_chat_group`) or the continuation of an existing chat group (`resumed_chat_group`).
        custom_session_id:
          type:
          - string
          - 'null'
          description: User-defined session ID. Relevant only when employing a [custom language model](/docs/empathic-voice-interface-evi/custom-language-model) in the EVI Config.
        event_name:
          type: string
          enum:
          - chat_started
          description: Always `chat_started`.
        start_time:
          type: integer
          description: Unix timestamp (in milliseconds) indicating when the session started.
        twilio_metadata:
          type:
          - object
          - 'null'
          additionalProperties:
            type: string
          description: Twilio metadata associated with the chat. This field is included only if the Chat was created via the [Twilio phone calling](/docs/empathic-voice-interface-evi/phone-calling) integration. Fields may include `call_sid`, `account_sid`, `from_number`, `to_number`, `caller_name`, `caller_number`, `from_city`, `from_state`, `from_zip`, `from_country`, `to_city`, `to_state`, `to_zip`, and `to_country`. If a specific metadata is not available, this field will be set to an empty string.
      required:
      - chat_group_id
      - chat_id
      - config_id
      - caller_number
      - chat_start_type
      - custom_session_id
      - start_time
      - twilio_metadata
      title: WebhookEventChatStarted
    WebhookEventChatStatus:
      type: string
      enum:
      - ACTIVE
      - USER_ENDED
      - USER_TIMEOUT
      - INACTIVITY_TIMEOUT
      - MAX_DURATION_TIMEOUT
      - SILENCE_TIMEOUT
      - ERROR
      title: WebhookEventChatStatus
    WebhookEventChatEnded:
      type: object
      properties:
        chat_group_id:
          type: string
          description: Unique ID of the **Chat Group** associated with the **Chat** session.
        chat_id:
          type: string
          description: Unique ID of the **Chat** session.
        config_id:
          type:
          - string
          - 'null'
          description: Unique ID of the EVI **Config** used for the session.
        caller_number:
          type:
          - string
          - 'null'
          description: Phone number of the caller in E.164 format (e.g., `+12223333333`). This field is included only if the Chat was created via the [Twilio phone calling](/docs/empathic-voice-interface-evi/phone-calling) integration.
        custom_session_id:
          type:
          - string
          - 'null'
          description: User-defined session ID. Relevant only when employing a [custom language model](/docs/empathic-voice-interface-evi/custom-language-model) in the EVI Config.
        duration_seconds:
          type: integer
          description: Total duration of the session in seconds.
        end_reason:
          $ref: '#/components/schemas/WebhookEventChatStatus'
          description: Reason for the session's termination.
        end_time:
          type: integer
          description: Unix timestamp (in milliseconds) indicating when the session ended.
        event_name:
          type: string
          enum:
          - chat_ended
          description: Always `chat_ended`.
        twilio_metadata:
          type:
          - object
          - 'null'
          additionalProperties:
            type: string
          description: Twilio metadata associated with the chat. This field is included only if the Chat was created via the [Twilio phone calling](/docs/empathic-voice-interface-evi/phone-calling) integration. Fields may include `call_sid`, `account_sid`, `from_number`, `to_number`, `caller_name`, `caller_number`, `from_city`, `from_state`, `from_zip`, `from_country`, `to_city`, `to_state`, `to_zip`, and `to_country`.If a specific metadata is not available, this field will be set to an empty string.
      required:
      - chat_group_id
      - chat_id
      - config_id
      - caller_number
      - custom_session_id
      - duration_seconds
      - end_reason
      - end_time
      - twilio_metadata
      title: WebhookEventChatEnded
    WebhookEventToolCall:
      type: object
      properties:
        chat_group_id:
          type: string
          description: Unique ID of the **Chat Group** associated with the **Chat** session.
        chat_id:
          type: string
          description: Unique ID of the **Chat** session.
        config_id:
          type:
          - string
          - 'null'
          description: Unique ID of the EVI **Config** used for the session.
        caller_number:
          type:
          - string
          - 'null'
          description: Phone number of the caller in E.164 format (e.g., `+12223333333`). This field is included only if the Chat was created via the [Twilio phone calling](/docs/empathic-voice-interface-evi/phone-calling) integration.
        custom_session_id:
          type:
          - string
          - 'null'
          description: User-defined session ID. Relevant only when employing a [custom language model](/docs/empathic-voice-interface-evi/custom-language-model) in the EVI Config.
        event_name:
          type: string
          enum:
          - tool_call
          description: Always `tool_call`.
        timestamp:
          type: integer
          description: Unix timestamp (in milliseconds) indicating when the tool call was triggered.
        tool_call_message:
          $ref: '#/components/schemas/ToolCallMessage'
          description: The tool call.
        twilio_metadata:
          type:
          - object
          - 'null'
          additionalProperties:
            type: string
          description: Twilio metadata associated with the chat. This field is included only if the Chat was created via the [Twilio phone calling](/docs/empathic-voice-interface-evi/phone-calling) integration. Fields may include `call_sid`, `account_sid`, `from_number`, `to_number`, `caller_name`, `caller_number`, `from_city`, `from_state`, `from_zip`, `from_country`, `to_city`, `to_state`, `to_zip`, and `to_country`.If a specific metadata is not available, this field will be set to an empty string.
      required:
      - chat_group_id
      - chat_id
      - config_id
      - caller_number
      - custom_session_id
      - timestamp
      - tool_call_message
      - twilio_metadata
      title: WebhookEventToolCall
    ToolType:
      type: string
      enum:
      - builtin
      - function
      title: ToolType
  securitySchemes:
    bearerAuth:
      type: apiKey
      in: header
      name: X-Hume-Api-Key