AsyncAPI YAML

        • **Required for client responses**: Should match the id from
          the corresponding `FunctionCallRequest`
        • **Optional for server responses**: Server may omit when responding
          to internal function executions
    name:
      type: string
      description: The name of the function being called
    content:
      type: string
      description: The content or result of the function call
  required:
    - type
    - name
    - content
  description: |
    Function call response message used bidirectionally:

    • **Client → Server**: Response after client executes a function
      marked as client_side: true
    • **Server → Client**: Response after server executes a function
      marked as client_side: false

    The same message structure serves both directions, enabling a unified
    interface for function call responses regardless of execution location.
  title: AgentV1_AgentV1ReceiveFunctionCallResponse
AgentV1_AgentV1PromptUpdated:
  type: object
  properties:
    type:
      type: string
      enum:
        - PromptUpdated
      description: Message type identifier for prompt update confirmation
  required:
    - type
  title: AgentV1_AgentV1PromptUpdated
AgentV1_AgentV1SpeakUpdated:
  type: object
  properties:
    type:
      type: string
      enum:
        - SpeakUpdated
      description: Message type identifier for speak update confirmation
  required:
    - type
  title: AgentV1_AgentV1SpeakUpdated
AgentV1_AgentV1InjectionRefused:
  type: object
  properties:
    type:
      type: string
      enum:
        - InjectionRefused
      description: Message type identifier for injection refused
    message:
      type: string
      description: Details about why the injection was refused
  required:
    - type
    - message
  title: AgentV1_AgentV1InjectionRefused
AgentV1_AgentV1Welcome:
  type: object
  properties:
    type:
      type: string
      enum:
        - Welcome
      description: Message type identifier for welcome message
    request_id:
      type: string
      description: Unique identifier for the request
  required:
    - type
    - request_id
  title: AgentV1_AgentV1Welcome
AgentV1_AgentV1SettingsApplied:
  type: object
  properties:
    type:
      type: string
      enum:
        - SettingsApplied
      description: Message type identifier for settings applied confirmation
  required:
    - type
  title: AgentV1_AgentV1SettingsApplied
ChannelsAgentV1MessagesAgentV1ConversationTextRole:
  type: string
  enum:
    - user
    - assistant
  description: Identifies who spoke the statement
  title: ChannelsAgentV1MessagesAgentV1ConversationTextRole
AgentV1_AgentV1ConversationText:
  type: object
  properties:
    type:
      type: string
      enum:
        - ConversationText
      description: Message type identifier for conversation text
    role:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1ConversationTextRole'
      description: Identifies who spoke the statement
    content:
      type: string
      description: The actual statement that was spoken
    languages_hinted:
      type: array
      items:
        type: string
      description: >-
        The language hints that were active at the time of the turn. Only present on user-role messages when the
        listen model is flux-general-multi.
    languages:
      type: array
      items:
        type: string
      description: >-
        Languages detected in the user's speech, sorted by word count (descending). Only present on user-role
        messages when the listen model is flux-general-multi.
  required:
    - type
    - role
    - content
  title: AgentV1_AgentV1ConversationText
AgentV1_AgentV1UserStartedSpeaking:
  type: object
  properties:
    type:
      type: string
      enum:
        - UserStartedSpeaking
      description: Message type identifier indicating that the user has begun speaking
  required:
    - type
  title: AgentV1_AgentV1UserStartedSpeaking
AgentV1_AgentV1AgentThinking:
  type: object
  properties:
    type:
      type: string
      enum:
        - AgentThinking
      description: Message type identifier for agent thinking
    content:
      type: string
      description: The text of the agent's thought process
  required:
    - type
    - content
  title: AgentV1_AgentV1AgentThinking
AgentV1_AgentV1LatencyReport:
  type: object
  properties:
    type:
      type: string
      enum:
        - LatencyReport
      description: Message type identifier for the latency report
    stt_latency:
      type: string
      title: float
      description: 'Speech-to-text: time from audio received to transcript produced, in seconds'
    ttt_token_latency:
      type: string
      title: float
      description: Time to first token of any type (text, tool call, or thinking), in seconds
    ttt_text_latency:
      type: string
      title: float
      description: Time to first text token from the LLM, in seconds
    ttt_tool_latency:
      type: string
      title: float
      description: Time to first tool-call token from the LLM, in seconds
    ttt_thinking_latency:
      type: string
      title: float
      description: Time to first thinking token from the LLM, in seconds
    tts_latency:
      type: string
      title: float
      description: 'Text-to-speech: time from first text token to first audio byte, in seconds'
    total_latency:
      type: string
      title: float
      description: 'End-to-end: time from user utterance end to first audio byte, in seconds'
  required:
    - type
  title: AgentV1_AgentV1LatencyReport
ChannelsAgentV1MessagesAgentV1FunctionCallRequestFunctionsItems:
  type: object
  properties:
    id:
      type: string
      description: Unique identifier for the function call
    name:
      type: string
      description: The name of the function to call
    arguments:
      type: string
      description: JSON string containing the function arguments
    client_side:
      type: boolean
      description: Whether the function should be executed client-side
    thought_signature:
      type: string
      description: Some Gemini models require this as an additional function call identifier
  required:
    - id
    - name
    - arguments
    - client_side
  title: ChannelsAgentV1MessagesAgentV1FunctionCallRequestFunctionsItems
AgentV1_AgentV1FunctionCallRequest:
  type: object
  properties:
    type:
      type: string
      enum:
        - FunctionCallRequest
      description: Message type identifier for function call requests
    functions:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1FunctionCallRequestFunctionsItems'
      description: Array of functions to be called
  required:
    - type
    - functions
  title: AgentV1_AgentV1FunctionCallRequest
ChannelsAgentV1MessagesAgentV1FunctionCallCancelledFunctionsItems:
  type: object
  properties:
    id:
      type: string
      description: The id from the FunctionCallRequest that is now cancelled. Send no FunctionCallResponse for this id
    name:
      type: string
      description: The name of the cancelled function
  required:
    - id
    - name
  title: ChannelsAgentV1MessagesAgentV1FunctionCallCancelledFunctionsItems
AgentV1_AgentV1FunctionCallCancelled:
  type: object
  properties:
    type:
      type: string
      enum:
        - FunctionCallCancelled
      description: Message type identifier for cancelled function calls
    functions:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1FunctionCallCancelledFunctionsItems'
      description: The function calls that are no longer valid
  required:
    - type
    - functions
  title: AgentV1_AgentV1FunctionCallCancelled
AgentV1_AgentV1AgentStartedSpeaking:
  type: object
  properties:
    type:
      type: string
      enum:
        - AgentStartedSpeaking
      description: Message type identifier for agent started speaking
    total_latency:
      type: string
      title: float
      description: Seconds from receiving the user's utterance to producing the agent's reply
    tts_latency:
      type: string
      title: float
      description: The portion of total latency attributable to text-to-speech
    ttt_latency:
      type: string
      title: float
      description: The portion of total latency attributable to text-to-text (usually an LLM)
  required:
    - type
    - total_latency
    - tts_latency
    - ttt_latency
  title: AgentV1_AgentV1AgentStartedSpeaking
AgentV1_AgentV1AgentAudioDone:
  type: object
  properties:
    type:
      type: string
      enum:
        - AgentAudioDone
      description: Message type identifier indicating the agent has finished sending audio
  required:
    - type
  title: AgentV1_AgentV1AgentAudioDone
ChannelsAgentV1MessagesAgentV1ErrorType:
  type: string
  enum:
    - Error
  description: Message type identifier for error responses
  title: ChannelsAgentV1MessagesAgentV1ErrorType
AgentV1_AgentV1Error:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1ErrorType'
      description: Message type identifier for error responses
    description:
      type: string
      description: A description of what went wrong
    code:
      type: string
      description: Error code identifying the type of error
  required:
    - type
    - description
    - code
  title: AgentV1_AgentV1Error
ChannelsAgentV1MessagesAgentV1WarningType:
  type: string
  enum:
    - Warning
  description: Message type identifier for warnings
  title: ChannelsAgentV1MessagesAgentV1WarningType
AgentV1_AgentV1Warning:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1WarningType'
      description: Message type identifier for warnings
    description:
      type: string
      description: Description of the warning
    code:
      type: string
      description: Warning code identifier
  required:
    - type
    - description
    - code
  description: Notifies the client of non-fatal errors or warnings
  title: AgentV1_AgentV1Warning
ChannelsAgentV1MessagesAgentV1HistoryOneOf0Role:
  type: string
  enum:
    - user
    - assistant
  description: Identifies who spoke the statement
  title: ChannelsAgentV1MessagesAgentV1HistoryOneOf0Role
AgentV1AgentV1History0:
  type: object
  properties:
    type:
      type: string
      enum:
        - History
      description: Message type identifier for conversation text
    role:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1HistoryOneOf0Role'
      description: Identifies who spoke the statement
    content:
      type: string
      description: The actual statement that was spoken
  required:
    - type
    - role
    - content
  description: Conversation text as part of the conversation history
  title: AgentV1AgentV1History0
ChannelsAgentV1MessagesAgentV1HistoryOneOf1FunctionCallsItems:
  type: object
  properties:
    id:
      type: string
      description: Unique identifier for the function call
    name:
      type: string
      description: Name of the function called
    client_side:
      type: boolean
      description: Indicates if the call was client-side or server-side
    arguments:
      type: string
      description: Arguments passed to the function
    response:
      type: string
      description: Response from the function call
    thought_signature:
      type: string
      description: Some Gemini models require this as an additional function call identifier
  required:
    - id
    - name
    - client_side
    - arguments
    - response
  title: ChannelsAgentV1MessagesAgentV1HistoryOneOf1FunctionCallsItems
AgentV1AgentV1History1:
  type: object
  properties:
    type:
      type: string
      enum:
        - History
    function_calls:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1HistoryOneOf1FunctionCallsItems'
      description: List of function call objects
  required:
    - type
    - function_calls
  description: Client-side or server-side function call request and response as part of the conversation history
  title: AgentV1AgentV1History1
AgentV1_AgentV1History:
  oneOf:
    - $ref: '#/components/schemas/AgentV1AgentV1History0'
    - $ref: '#/components/schemas/AgentV1AgentV1History1'
  description: A history message is either a conversational message or a function call
  title: AgentV1_AgentV1History
AgentV1_AgentV1Audio:
  type: string
  format: binary
  title: AgentV1_AgentV1Audio
ChannelsAgentV1MessagesAgentV1SettingsFlags:
  type: object
  properties:
    history:
      type: boolean
      default: true
      description: Enable or disable history message reporting
  title: ChannelsAgentV1MessagesAgentV1SettingsFlags
ChannelsAgentV1MessagesAgentV1SettingsAudioInputEncoding:
  type: string
  enum:
    - linear16
    - linear32
    - flac
    - alaw
    - mulaw
    - amr-nb
    - amr-wb
    - opus
    - ogg-opus
    - speex
    - g729
  default: linear16
  description: Audio encoding format
  title: ChannelsAgentV1MessagesAgentV1SettingsAudioInputEncoding
ChannelsAgentV1MessagesAgentV1SettingsAudioInput:
  type: object
  properties:
    encoding:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAudioInputEncoding'
      description: Audio encoding format
    sample_rate:
      type: integer
      default: 24000
      description: Sample rate in Hz. Common values are 16000, 24000, 44100, 48000
  required:
    - encoding
    - sample_rate
  description: >-
    Audio input configuration settings. If omitted, defaults to encoding=linear16 and sample_rate=24000. Higher
    sample rates like 44100 Hz provide better audio quality.
  title: ChannelsAgentV1MessagesAgentV1SettingsAudioInput
ChannelsAgentV1MessagesAgentV1SettingsAudioOutputEncoding:
  type: string
  enum:
    - linear16
    - mulaw
    - alaw
    - mp3
    - opus
    - flac
    - aac
  default: linear16
  description: Audio encoding format for streaming TTS output
  title: ChannelsAgentV1MessagesAgentV1SettingsAudioOutputEncoding
ChannelsAgentV1MessagesAgentV1SettingsAudioOutputContainer:
  type: string
  enum:
    - none
    - wav
    - ogg
  default: none
  description: Audio container format.
  title: ChannelsAgentV1MessagesAgentV1SettingsAudioOutputContainer
ChannelsAgentV1MessagesAgentV1SettingsAudioOutput:
  type: object
  properties:
    encoding:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAudioOutputEncoding'
      default: linear16
      description: Audio encoding format for streaming TTS output
    sample_rate:
      type: integer
      description: Sample rate in Hz
    bitrate:
      type: integer
      description: Audio bitrate in bits per second
    container:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAudioOutputContainer'
      default: none
      description: Audio container format.
  description: Audio output configuration settings
  title: ChannelsAgentV1MessagesAgentV1SettingsAudioOutput
ChannelsAgentV1MessagesAgentV1SettingsAudio:
  type: object
  properties:
    input:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAudioInput'
      description: >-
        Audio input configuration settings. If omitted, defaults to encoding=linear16 and sample_rate=24000. Higher
        sample rates like 44100 Hz provide better audio quality.
    output:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAudioOutput'
      description: Audio output configuration settings
  title: ChannelsAgentV1MessagesAgentV1SettingsAudio
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItemsOneOf0Role:
  type: string
  enum:
    - user
    - assistant
  description: Identifies who spoke the statement
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItemsOneOf0Role
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems0:
  type: object
  properties:
    type:
      type: string
      enum:
        - History
      description: Message type identifier for conversation text
    role:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItemsOneOf0Role'
      description: Identifies who spoke the statement
    content:
      type: string
      description: The actual statement that was spoken
  required:
    - type
    - role
    - content
  description: Conversation text as part of the conversation history
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems0
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItemsOneOf1FunctionCallsItems:
  type: object
  properties:
    id:
      type: string
      description: Unique identifier for the function call
    name:
      type: string
      description: Name of the function called
    client_side:
      type: boolean
      description: Indicates if the call was client-side or server-side
    arguments:
      type: string
      description: Arguments passed to the function
    response:
      type: string
      description: Response from the function call
    thought_signature:
      type: string
      description: Some Gemini models require this as an additional function call identifier
  required:
    - id
    - name
    - client_side
    - arguments
    - response
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItemsOneOf1FunctionCallsItems
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems1:
  type: object
  properties:
    type:
      type: string
      enum:
        - History
    function_calls:
      type: array
      items:
        $ref: >-
          #/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItemsOneOf1FunctionCallsItems
      description: List of function call objects
  required:
    - type
    - function_calls
  description: Client-side or server-side function call request and response as part of the conversation history
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems1
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems:
  oneOf:
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems0'
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems1'
  description: A history message is either a conversational message or a function call
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Context:
  type: object
  properties:
    messages:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ContextMessagesItems'
      description: Conversation history as a list of messages and function calls
  description: Conversation context including the history of messages and function calls
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Context
DeepgramListenProviderV1:
  type: object
  properties:
    type:
      type: string
      enum:
        - deepgram
      description: Provider type for speech-to-text
    version:
      type: string
      enum:
        - v1
      description: Specifies usage of the V1 Deepgram speech-to-text API
    model:
      type: string
      description: Model to use for speech to text using the V1 API (e.g. Nova-3, Nova-2)
    language:
      type: string
      default: en-US
      description: >-
        Language code to use for speech-to-text. Can be a BCP-47 language tag (e.g. `en`), or `multi` for
        code-switching transcription
    keyterms:
      type: array
      items:
        type: string
      description: Prompt keyterm recognition to improve Keyword Recall Rate
    smart_format:
      type: boolean
      default: false
      description: Applies smart formatting to improve transcript readability
  required:
    - type
  title: DeepgramListenProviderV1
DeepgramListenProviderV2:
  type: object
  properties:
    type:
      type: string
      enum:
        - deepgram
      description: Provider type for speech-to-text
    version:
      type: string
      enum:
        - v2
      description: Specifies usage of the V2 Deepgram speech-to-text API (e.g. Flux)
    model:
      type: string
      description: Model to use for speech to text using the V2 API (e.g. flux-general-en, flux-general-multi)
    language_hints:
      type: array
      items:
        type: string
      description: >-
        An array of one or more BCP-47 language codes to bias the model toward specific languages. Only supported
        when model is flux-general-multi. Without hints, the model auto-detects the spoken language. See the
        Language Prompting guide for details.
    eot_threshold:
      type: number
      format: double
      description: >-
        End-of-turn confidence required to finish a turn. Valid range: 0.5 - 1.0. Defaults to 0.7. Set to 1.0 to
        fully suppress confidence-based end-of-turn detection. `eot_timeout_ms` still ends idle turns; increase it
        when using ForceEndTurn for full manual turn control.
    eager_eot_threshold:
      type: number
      format: double
      description: >-
        End-of-turn confidence required to fire an eager end-of-turn event. When set, enables EagerEndOfTurn and
        TurnResumed events. Valid range: 0.3 - 0.9.
    eot_timeout_ms:
      type: integer
      description: >-
        A turn will be finished when this much time in milliseconds has passed after speech, regardless of EOT
        confidence. Defaults to 5000.
    keyterms:
      type: array
      items:
        type: string
      description: Prompt keyterm recognition to improve Keyword Recall Rate
  required:
    - type
    - model
  title: DeepgramListenProviderV2
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ListenProvider:
  oneOf:
    - $ref: '#/components/schemas/DeepgramListenProviderV1'
    - $ref: '#/components/schemas/DeepgramListenProviderV2'
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ListenProvider
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Listen:
  type: object
  properties:
    provider:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0ListenProvider'
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Listen
OpenAiThinkProviderVersion:
  type: string
  enum:
    - v1
  description: The REST API version for the OpenAI chat completions API
  title: OpenAiThinkProviderVersion
OpenAiThinkProviderModel:
  type: string
  enum:
    - gpt-5
    - gpt-5-mini
    - gpt-5-nano
    - gpt-4.1
    - gpt-4.1-mini
    - gpt-4.1-nano
    - gpt-4o
    - gpt-4o-mini
  description: OpenAI model to use
  title: OpenAiThinkProviderModel
OpenAiThinkProviderReasoningMode:
  type: string
  enum:
    - none
    - minimal
    - low
    - medium
    - high
  description: OpenAI reasoning_effort
  title: OpenAiThinkProviderReasoningMode
OpenAiThinkProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - open_ai
    version:
      $ref: '#/components/schemas/OpenAiThinkProviderVersion'
      description: The REST API version for the OpenAI chat completions API
    model:
      $ref: '#/components/schemas/OpenAiThinkProviderModel'
      description: OpenAI model to use
    temperature:
      type: number
      format: double
      minimum: 0
      maximum: 2
      description: OpenAI temperature (0-2)
    reasoning_mode:
      $ref: '#/components/schemas/OpenAiThinkProviderReasoningMode'
      description: OpenAI reasoning_effort
  required:
    - type
    - model
  title: OpenAiThinkProvider
AwsBedrockThinkProviderModel:
  type: string
  enum:
    - anthropic/claude-3-5-sonnet-20240620-v1:0
    - anthropic/claude-3-5-haiku-20240307-v1:0
  description: AWS Bedrock model to use
  title: AwsBedrockThinkProviderModel
AwsBedrockThinkProviderCredentialsType:
  type: string
  enum:
    - sts
    - iam
  description: AWS credentials type (STS short-lived or IAM long-lived)
  title: AwsBedrockThinkProviderCredentialsType
AwsBedrockThinkProviderCredentials:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/AwsBedrockThinkProviderCredentialsType'
      description: AWS credentials type (STS short-lived or IAM long-lived)
    region:
      type: string
      description: AWS region
    access_key_id:
      type: string
      description: AWS access key
    secret_access_key:
      type: string
      description: AWS secret access key
    session_token:
      type: string
      description: AWS session token (required for STS only)
  description: AWS credentials type (STS short-lived or IAM long-lived)
  title: AwsBedrockThinkProviderCredentials
AwsBedrockThinkProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - aws_bedrock
    model:
      $ref: '#/components/schemas/AwsBedrockThinkProviderModel'
      description: AWS Bedrock model to use
    temperature:
      type: number
      format: double
      minimum: 0
      maximum: 2
      description: AWS Bedrock temperature (0-2)
    credentials:
      $ref: '#/components/schemas/AwsBedrockThinkProviderCredentials'
      description: AWS credentials type (STS short-lived or IAM long-lived)
  required:
    - type
    - model
  title: AwsBedrockThinkProvider
AnthropicThinkProviderVersion:
  type: string
  enum:
    - v1
  description: The REST API version for the Anthropic Messages API
  title: AnthropicThinkProviderVersion
AnthropicThinkProviderModel:
  type: string
  enum:
    - claude-3-5-haiku-latest
    - claude-sonnet-4-20250514
  description: Anthropic model to use
  title: AnthropicThinkProviderModel
AnthropicThinkProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - anthropic
    version:
      $ref: '#/components/schemas/AnthropicThinkProviderVersion'
      description: The REST API version for the Anthropic Messages API
    model:
      $ref: '#/components/schemas/AnthropicThinkProviderModel'
      description: Anthropic model to use
    temperature:
      type: number
      format: double
      minimum: 0
      maximum: 1
      description: Anthropic temperature (0-1)
  required:
    - type
    - model
  title: AnthropicThinkProvider
GoogleThinkProviderVersion:
  type: string
  enum:
    - ai-studio-v1beta
    - gemini-enterprise-agent-v1
    - v1beta
  description: >-
    The Google API used for the request: ai-studio-v1beta for the AI Studio API, or gemini-enterprise-agent-v1 for
    the Gemini Enterprise Agent (GEA) API. v1beta is accepted as an alias for ai-studio-v1beta. Defaults based on
    the Deepgram Voice Agent endpoint you connect to.
  title: GoogleThinkProviderVersion
GoogleThinkProviderModel:
  type: string
  enum:
    - gemini-2.0-flash
    - gemini-2.0-flash-lite
    - gemini-2.5-flash
  description: Google model to use
  title: GoogleThinkProviderModel
GoogleThinkProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - google
    version:
      $ref: '#/components/schemas/GoogleThinkProviderVersion'
      description: >-
        The Google API used for the request: ai-studio-v1beta for the AI Studio API, or gemini-enterprise-agent-v1
        for the Gemini Enterprise Agent (GEA) API. v1beta is accepted as an alias for ai-studio-v1beta. Defaults
        based on the Deepgram Voice Agent endpoint you connect to.
    model:
      $ref: '#/components/schemas/GoogleThinkProviderModel'
      description: Google model to use
    temperature:
      type: number
      format: double
      minimum: 0
      maximum: 2
      description: Google temperature (0-2)
  required:
    - type
    - model
  title: GoogleThinkProvider
GroqThinkProviderVersion:
  type: string
  enum:
    - v1
  description: The REST API version for the Groq's chat completions API (mostly OpenAI-compatible)
  title: GroqThinkProviderVersion
GroqThinkProviderModel:
  type: string
  enum:
    - openai/gpt-oss-20b
  description: Groq model to use
  title: GroqThinkProviderModel
GroqThinkProviderReasoningMode:
  type: string
  enum:
    - none
    - minimal
    - low
    - medium
    - high
  description: OpenAI reasoning_effort
  title: GroqThinkProviderReasoningMode
GroqThinkProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - groq
    version:
      $ref: '#/components/schemas/GroqThinkProviderVersion'
      description: The REST API version for the Groq's chat completions API (mostly OpenAI-compatible)
    model:
      $ref: '#/components/schemas/GroqThinkProviderModel'
      description: Groq model to use
    temperature:
      type: number
      format: double
      minimum: 0
      maximum: 2
      description: Groq temperature (0-2)
    reasoning_mode:
      $ref: '#/components/schemas/GroqThinkProviderReasoningMode'
      description: OpenAI reasoning_effort
  required:
    - type
    - model
  title: GroqThinkProvider
ThinkSettingsV1Provider:
  oneOf:
    - $ref: '#/components/schemas/OpenAiThinkProvider'
    - $ref: '#/components/schemas/AwsBedrockThinkProvider'
    - $ref: '#/components/schemas/AnthropicThinkProvider'
    - $ref: '#/components/schemas/GoogleThinkProvider'
    - $ref: '#/components/schemas/GroqThinkProvider'
  title: ThinkSettingsV1Provider
ThinkSettingsV1Endpoint:
  type: object
  properties:
    url:
      type: string
      description: Custom LLM endpoint URL
    headers:
      type: object
      additionalProperties:
        type: string
      description: Custom headers for the endpoint
  description: |
    Optional for non-Deepgram LLM providers. When present, must include url field and headers object
  title: ThinkSettingsV1Endpoint
ThinkSettingsV1FunctionsItemsParameters:
  type: object
  properties: 
  description: Function parameters
  title: ThinkSettingsV1FunctionsItemsParameters
ThinkSettingsV1FunctionsItemsEndpoint:
  type: object
  properties:
    url:
      type: string
      description: Endpoint URL
    method:
      type: string
      description: HTTP method
    headers:
      type: object
      additionalProperties:
        type: string
  description: The Function endpoint to call. if not passed, function is called client-side
  title: ThinkSettingsV1FunctionsItemsEndpoint
ThinkSettingsV1FunctionsItems:
  type: object
  properties:
    name:
      type: string
      description: Function name
    description:
      type: string
      description: Function description
    parameters:
      $ref: '#/components/schemas/ThinkSettingsV1FunctionsItemsParameters'
      description: Function parameters
    defer_until_eot:
      type: boolean
      default: false
      description: >-
        Hold this function call until the user's turn is confirmed instead of dispatching it speculatively. Set it
        to true for actions that cannot be undone. If the turn resumes, a deferred call is discarded before it runs.
        Defaults to false
    endpoint:
      $ref: '#/components/schemas/ThinkSettingsV1FunctionsItemsEndpoint'
      description: The Function endpoint to call. if not passed, function is called client-side
  title: ThinkSettingsV1FunctionsItems
ThinkSettingsV1ContextLength0:
  type: string
  enum:
    - max
  description: Agent will not discard context regardless of length
  title: ThinkSettingsV1ContextLength0
ThinkSettingsV1ContextLength:
  oneOf:
    - $ref: '#/components/schemas/ThinkSettingsV1ContextLength0'
    - type: number
      format: double
      minimum: 2
  description: >
    Specifies the number of characters retained in context between user messages, agent responses, and function
    calls. This setting is only configurable when a custom think endpoint is used
  title: ThinkSettingsV1ContextLength
ThinkSettingsV1:
  type: object
  properties:
    provider:
      $ref: '#/components/schemas/ThinkSettingsV1Provider'
    endpoint:
      $ref: '#/components/schemas/ThinkSettingsV1Endpoint'
      description: |
        Optional for non-Deepgram LLM providers. When present, must include url field and headers object
    functions:
      type: array
      items:
        $ref: '#/components/schemas/ThinkSettingsV1FunctionsItems'
    prompt:
      type: string
    context_length:
      $ref: '#/components/schemas/ThinkSettingsV1ContextLength'
      description: >
        Specifies the number of characters retained in context between user messages, agent responses, and function
        calls. This setting is only configurable when a custom think endpoint is used
  required:
    - provider
  title: ThinkSettingsV1
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Think1:
  type: array
  items:
    $ref: '#/components/schemas/ThinkSettingsV1'
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Think1
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Think:
  oneOf:
    - $ref: '#/components/schemas/ThinkSettingsV1'
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Think1'
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Think
DeepgramSpeakProviderModel:
  type: string
  enum:
    - aura-asteria-en
    - aura-luna-en
    - aura-stella-en
    - aura-athena-en
    - aura-hera-en
    - aura-orion-en
    - aura-arcas-en
    - aura-perseus-en
    - aura-angus-en
    - aura-orpheus-en
    - aura-helios-en
    - aura-zeus-en
    - aura-2-amalthea-en
    - aura-2-andromeda-en
    - aura-2-apollo-en
    - aura-2-arcas-en
    - aura-2-aries-en
    - aura-2-asteria-en
    - aura-2-athena-en
    - aura-2-atlas-en
    - aura-2-aurora-en
    - aura-2-callista-en
    - aura-2-cora-en
    - aura-2-cordelia-en
    - aura-2-delia-en
    - aura-2-draco-en
    - aura-2-electra-en
    - aura-2-harmonia-en
    - aura-2-helena-en
    - aura-2-hera-en
    - aura-2-hermes-en
    - aura-2-hyperion-en
    - aura-2-iris-en
    - aura-2-janus-en
    - aura-2-juno-en
    - aura-2-jupiter-en
    - aura-2-luna-en
    - aura-2-mars-en
    - aura-2-minerva-en
    - aura-2-neptune-en
    - aura-2-odysseus-en
    - aura-2-ophelia-en
    - aura-2-orion-en
    - aura-2-orpheus-en
    - aura-2-pandora-en
    - aura-2-phoebe-en
    - aura-2-pluto-en
    - aura-2-saturn-en
    - aura-2-selene-en
    - aura-2-thalia-en
    - aura-2-theia-en
    - aura-2-vesta-en
    - aura-2-zeus-en
    - aura-2-sirio-es
    - aura-2-nestor-es
    - aura-2-carina-es
    - aura-2-celeste-es
    - aura-2-alvaro-es
    - aura-2-diana-es
    - aura-2-aquila-es
    - aura-2-selena-es
    - aura-2-estrella-es
    - aura-2-javier-es
    - flux-alexis-en
    - flux-bree-en
    - flux-brittany-en
    - flux-brooke-en
    - flux-bruce-en
    - flux-cliff-en
    - flux-cole-en
    - flux-colin-en
    - flux-conor-en
    - flux-donovan-en
    - flux-drew-en
    - flux-elise-en
    - flux-gemma-en
    - flux-haley-en
    - flux-hannah-en
    - flux-heather-en
    - flux-jack-en
    - flux-kai-en
    - flux-kelsey-en
    - flux-kit-en
    - flux-maeve-en
    - flux-marcelo-en
    - flux-marcus-en
    - flux-meena-en
    - flux-meghan-en
    - flux-miles-en
    - flux-naveen-en
    - flux-paige-en
    - flux-priya-en
    - flux-rufus-en
    - flux-sean-en
    - flux-sharon-en
    - flux-sienna-en
    - flux-tanner-en
    - flux-wade-en
    - flux-wes-en
  description: >-
    Deepgram TTS model. Aura models (version v1) use the aura-* voices; Flux TTS (version v2) uses the
    flux-- voices (e.g. flux-alexis-en). Defaults to flux-kit-en when agent.speak is omitted.
  title: DeepgramSpeakProviderModel
DeepgramSpeakProviderExpressivity:
  type: string
  enum:
    - '-2'
    - '-1'
    - '0'
    - '1'
    - '2'
  description: >-
    Delivery register of the generated speech, on a calm-to-animated axis. Flux TTS (version v2) only, on every Flux
    voice. Accepts the whole numbers -2 to 2, where 0 (the default) is the voice's tuned delivery and the only value
    validated for production, -2 the calm end of the range and 2 the animated end. Fixed for the session. Beta:
    behavior may change in future model versions, and non-default values increase the risk of hallucinations and
    pronunciation errors. See [Expressivity](/guides/tts-voice-controls-tts-expressivity).
  title: DeepgramSpeakProviderExpressivity
DeepgramSpeakProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - deepgram
    version:
      type: string
      default: v1
      description: >-
        The Deepgram text-to-speech model family. Accepted values: `v1` (Aura, the default) and `v2` (Flux TTS). Use
        `v1` with an aura-* model and `v2` with a flux-* model. Defaults to `v1` when omitted.
    model:
      $ref: '#/components/schemas/DeepgramSpeakProviderModel'
      description: >-
        Deepgram TTS model. Aura models (version v1) use the aura-* voices; Flux TTS (version v2) uses the
        flux-- voices (e.g. flux-alexis-en). Defaults to flux-kit-en when agent.speak is omitted.
    speed:
      type: number
      format: double
      minimum: 0.5
      maximum: 1.5
      default: 1
      description: >-
        Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and
        voice quality. Aura (version v1) accepts any value from 0.7 to 1.5. Flux TTS (version v2) accepts values
        from 0.5 to 1.5 in 0.05 increments; a value the family does not accept ends the session with
        FAILED_TO_SPEAK. Not yet supported in all languages.
    expressivity:
      $ref: '#/components/schemas/DeepgramSpeakProviderExpressivity'
      default: 0
      description: >-
        Delivery register of the generated speech, on a calm-to-animated axis. Flux TTS (version v2) only, on every
        Flux voice. Accepts the whole numbers -2 to 2, where 0 (the default) is the voice's tuned delivery and the
        only value validated for production, -2 the calm end of the range and 2 the animated end. Fixed for the
        session. Beta: behavior may change in future model versions, and non-default values increase the risk of
        hallucinations and pronunciation errors. See [Expressivity](/guides/tts-voice-controls-tts-expressivity).
  required:
    - type
    - model
  description: >-
    Deepgram text-to-speech provider. Aura models use version v1 (default); Flux TTS uses version v2 and a flux-*
    model. Flux TTS is the default when agent.speak is omitted, using the flux-kit-en voice.
  title: DeepgramSpeakProvider
ElevenLabsSpeakProviderVersion:
  type: string
  enum:
    - v1
  description: The REST API version for the ElevenLabs text-to-speech API
  title: ElevenLabsSpeakProviderVersion
ElevenLabsSpeakProviderModelId:
  type: string
  enum:
    - eleven_turbo_v2_5
    - eleven_monolingual_v1
    - eleven_multilingual_v2
  description: Eleven Labs model ID
  title: ElevenLabsSpeakProviderModelId
ElevenLabsSpeakProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - eleven_labs
    version:
      $ref: '#/components/schemas/ElevenLabsSpeakProviderVersion'
      description: The REST API version for the ElevenLabs text-to-speech API
    model_id:
      $ref: '#/components/schemas/ElevenLabsSpeakProviderModelId'
      description: Eleven Labs model ID
    language:
      type: string
      description: Optional language to use, e.g. 'en-US'. Corresponds to the `language_code` parameter in the ElevenLabs API
    language_code:
      type: string
      description: Use the `language` field instead.
      deprecated: true
  required:
    - type
    - model_id
  title: ElevenLabsSpeakProvider
CartesiaSpeakProviderVersion:
  type: string
  enum:
    - '2025-03-17'
  description: The API version header for the Cartesia text-to-speech API
  title: CartesiaSpeakProviderVersion
CartesiaSpeakProviderModelId:
  type: string
  enum:
    - sonic-2
    - sonic-multilingual
  description: Cartesia model ID
  title: CartesiaSpeakProviderModelId
CartesiaSpeakProviderVoice:
  type: object
  properties:
    mode:
      type: string
      description: Cartesia voice mode
    id:
      type: string
      description: Cartesia voice ID
  required:
    - mode
    - id
  title: CartesiaSpeakProviderVoice
CartesiaSpeakProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - cartesia
    version:
      $ref: '#/components/schemas/CartesiaSpeakProviderVersion'
      description: The API version header for the Cartesia text-to-speech API
    model_id:
      $ref: '#/components/schemas/CartesiaSpeakProviderModelId'
      description: Cartesia model ID
    voice:
      $ref: '#/components/schemas/CartesiaSpeakProviderVoice'
    language:
      type: string
      description: Cartesia language code
    volume:
      type: number
      format: double
      minimum: 0.5
      maximum: 2
      description: >
        Volume level for Cartesia TTS output. Valid range: 0.5 to 2.0. See [Cartesia
        documentation](https://docs.cartesia.ai/build-with-cartesia/sonic-3/volume-speed-emotion#volume-speed-and-emotion).
  required:
    - type
    - model_id
    - voice
  title: CartesiaSpeakProvider
OpenAiSpeakProviderVersion:
  type: string
  enum:
    - v1
  description: The REST API version for the OpenAI text-to-speech API
  title: OpenAiSpeakProviderVersion
OpenAiSpeakProviderModel:
  type: string
  enum:
    - tts-1
    - tts-1-hd
  description: OpenAI TTS model
  title: OpenAiSpeakProviderModel
OpenAiSpeakProviderVoice:
  type: string
  enum:
    - alloy
    - echo
    - fable
    - onyx
    - nova
    - shimmer
  description: OpenAI voice
  title: OpenAiSpeakProviderVoice
OpenAiSpeakProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - open_ai
    version:
      $ref: '#/components/schemas/OpenAiSpeakProviderVersion'
      description: The REST API version for the OpenAI text-to-speech API
    model:
      $ref: '#/components/schemas/OpenAiSpeakProviderModel'
      description: OpenAI TTS model
    voice:
      $ref: '#/components/schemas/OpenAiSpeakProviderVoice'
      description: OpenAI voice
  required:
    - type
    - model
    - voice
  title: OpenAiSpeakProvider
AwsPollySpeakProviderVoice:
  type: string
  enum:
    - Matthew
    - Joanna
    - Amy
    - Emma
    - Brian
    - Arthur
    - Aria
    - Ayanda
  description: AWS Polly voice name
  title: AwsPollySpeakProviderVoice
AwsPollySpeakProviderEngine:
  type: string
  enum:
    - generative
    - long-form
    - standard
    - neural
  title: AwsPollySpeakProviderEngine
AwsPollySpeakProviderCredentialsType:
  type: string
  enum:
    - sts
    - iam
  title: AwsPollySpeakProviderCredentialsType
AwsPollySpeakProviderCredentials:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/AwsPollySpeakProviderCredentialsType'
    region:
      type: string
    access_key_id:
      type: string
    secret_access_key:
      type: string
    session_token:
      type: string
      description: Required for STS only
  required:
    - type
    - region
    - access_key_id
    - secret_access_key
  title: AwsPollySpeakProviderCredentials
AwsPollySpeakProvider:
  type: object
  properties:
    type:
      type: string
      enum:
        - aws_polly
    voice:
      $ref: '#/components/schemas/AwsPollySpeakProviderVoice'
      description: AWS Polly voice name
    language:
      type: string
      description: Language code to use, e.g. 'en-US'. Corresponds to the `language_code` parameter in the AWS Polly API
    language_code:
      type: string
      description: Use the `language` field instead.
      deprecated: true
    engine:
      $ref: '#/components/schemas/AwsPollySpeakProviderEngine'
    credentials:
      $ref: '#/components/schemas/AwsPollySpeakProviderCredentials'
  required:
    - type
    - voice
    - language
    - engine
    - credentials
  title: AwsPollySpeakProvider
SpeakSettingsV1Provider:
  oneOf:
    - $ref: '#/components/schemas/DeepgramSpeakProvider'
    - $ref: '#/components/schemas/ElevenLabsSpeakProvider'
    - $ref: '#/components/schemas/CartesiaSpeakProvider'
    - $ref: '#/components/schemas/OpenAiSpeakProvider'
    - $ref: '#/components/schemas/AwsPollySpeakProvider'
  title: SpeakSettingsV1Provider
SpeakSettingsV1Endpoint:
  type: object
  properties:
    url:
      type: string
      description: >
        Custom TTS endpoint URL. Cannot contain `output_format` or `model_id` query parameters when the provider is
        Eleven Labs.
    headers:
      type: object
      additionalProperties:
        type: string
  description: >
    Optional if provider is Deepgram. Required for non-Deepgram TTS providers.

    When present, must include url field and headers object. Valid schemes are https and wss with wss only supported
    for Eleven Labs.
  title: SpeakSettingsV1Endpoint
SpeakSettingsV1:
  type: object
  properties:
    provider:
      $ref: '#/components/schemas/SpeakSettingsV1Provider'
    endpoint:
      $ref: '#/components/schemas/SpeakSettingsV1Endpoint'
      description: >
        Optional if provider is Deepgram. Required for non-Deepgram TTS providers.

        When present, must include url field and headers object. Valid schemes are https and wss with wss only
        supported for Eleven Labs.
  required:
    - provider
  title: SpeakSettingsV1
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Speak1:
  type: array
  items:
    $ref: '#/components/schemas/SpeakSettingsV1'
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Speak1
ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Speak:
  oneOf:
    - $ref: '#/components/schemas/SpeakSettingsV1'
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Speak1'
  title: ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Speak
ChannelsAgentV1MessagesAgentV1SettingsAgent0:
  type: object
  properties:
    language:
      type: string
      default: en
      description: Deprecated. Use `listen.provider.language` and `speak.provider.language` fields instead.
      deprecated: true
    context:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Context'
      description: Conversation context including the history of messages and function calls
    listen:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Listen'
    think:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Think'
    speak:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgentOneOf0Speak'
    greeting:
      type: string
      description: Optional message that agent will speak at the start
  title: ChannelsAgentV1MessagesAgentV1SettingsAgent0
ChannelsAgentV1MessagesAgentV1SettingsAgent:
  oneOf:
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgent0'
    - type: string
      format: uuid
  title: ChannelsAgentV1MessagesAgentV1SettingsAgent
AgentV1_AgentV1Settings:
  type: object
  properties:
    type:
      type: string
      enum:
        - Settings
    tags:
      type: array
      items:
        type: string
      description: Tags to associate with the request
    experimental:
      type: boolean
      default: false
      description: To enable experimental features
    flags:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsFlags'
    mip_opt_out:
      type: boolean
      default: false
      description: To opt out of Deepgram Model Improvement Program
    audio:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAudio'
    agent:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1SettingsAgent'
  required:
    - type
    - audio
    - agent
  title: AgentV1_AgentV1Settings
ChannelsAgentV1MessagesAgentV1UpdateListenListenProvider:
  oneOf:
    - $ref: '#/components/schemas/DeepgramListenProviderV1'
    - $ref: '#/components/schemas/DeepgramListenProviderV2'
  title: ChannelsAgentV1MessagesAgentV1UpdateListenListenProvider
ChannelsAgentV1MessagesAgentV1UpdateListenListen:
  type: object
  properties:
    provider:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1UpdateListenListenProvider'
  required:
    - provider
  description: >-
    Listen configuration to update. Contains a provider object with the same schema as Settings. The model and
    language can be changed mid-session. Keyterms can only be updated mid-session for Flux models.
  title: ChannelsAgentV1MessagesAgentV1UpdateListenListen
AgentV1_AgentV1UpdateListen:
  type: object
  properties:
    type:
      type: string
      enum:
        - UpdateListen
      description: Message type identifier for updating the listen configuration
    listen:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1UpdateListenListen'
      description: >-
        Listen configuration to update. Contains a provider object with the same schema as Settings. The model and
        language can be changed mid-session. Keyterms can only be updated mid-session for Flux models.
  required:
    - type
    - listen
  title: AgentV1_AgentV1UpdateListen
ChannelsAgentV1MessagesAgentV1UpdateThinkThink1:
  type: array
  items:
    $ref: '#/components/schemas/ThinkSettingsV1'
  title: ChannelsAgentV1MessagesAgentV1UpdateThinkThink1
ChannelsAgentV1MessagesAgentV1UpdateThinkThink:
  oneOf:
    - $ref: '#/components/schemas/ThinkSettingsV1'
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1UpdateThinkThink1'
  title: ChannelsAgentV1MessagesAgentV1UpdateThinkThink
AgentV1_AgentV1UpdateThink:
  type: object
  properties:
    type:
      type: string
      enum:
        - UpdateThink
      description: Message type identifier for updating the think model
    think:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1UpdateThinkThink'
  required:
    - type
    - think
  title: AgentV1_AgentV1UpdateThink
ChannelsAgentV1MessagesAgentV1UpdateSpeakSpeak1:
  type: array
  items:
    $ref: '#/components/schemas/SpeakSettingsV1'
  title: ChannelsAgentV1MessagesAgentV1UpdateSpeakSpeak1
ChannelsAgentV1MessagesAgentV1UpdateSpeakSpeak:
  oneOf:
    - $ref: '#/components/schemas/SpeakSettingsV1'
    - $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1UpdateSpeakSpeak1'
  title: ChannelsAgentV1MessagesAgentV1UpdateSpeakSpeak
AgentV1_AgentV1UpdateSpeak:
  type: object
  properties:
    type:
      type: string
      enum:
        - UpdateSpeak
      description: Message type identifier for updating the speak model
    speak:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1UpdateSpeakSpeak'
  required:
    - type
    - speak
  title: AgentV1_AgentV1UpdateSpeak
AgentV1_AgentV1InjectUserMessage:
  type: object
  properties:
    type:
      type: string
      enum:
        - InjectUserMessage
      description: Message type identifier for injecting a user message
    content:
      type: string
      description: The specific phrase or statement the agent should respond to
  required:
    - type
    - content
  title: AgentV1_AgentV1InjectUserMessage
ChannelsAgentV1MessagesAgentV1InjectAgentMessageBehavior:
  type: string
  enum:
    - default
    - queue
    - interrupt
  default: default
  description: >
    Controls how the injection interacts with any in-progress user or agent turn.


    * `default` — The agent speaks only if neither the user nor the agent is mid-turn. If a turn is in progress, the
    server replies with `InjectionRefused`.

    * `queue` — The message is appended after any already-queued `ConversationText` without interrupting the current
    agent turn or think response. If nothing is queued, the message plays immediately.

    * `interrupt` — The agent immediately speaks. If the agent was already speaking, it interrupts the current
    speech and replaces it with the new message. If the user is speaking, the agent interrupts with the new message,
    but the user's continued speech triggers `UserStartedSpeaking`, which quickly interrupts the agent.
  title: ChannelsAgentV1MessagesAgentV1InjectAgentMessageBehavior
AgentV1_AgentV1InjectAgentMessage:
  type: object
  properties:
    type:
      type: string
      enum:
        - InjectAgentMessage
      description: Message type identifier for injecting an agent message
    message:
      type: string
      description: The statement that the agent should say
    behavior:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1InjectAgentMessageBehavior'
      default: default
      description: >
        Controls how the injection interacts with any in-progress user or agent turn.


        * `default` — The agent speaks only if neither the user nor the agent is mid-turn. If a turn is in progress,
        the server replies with `InjectionRefused`.

        * `queue` — The message is appended after any already-queued `ConversationText` without interrupting the
        current agent turn or think response. If nothing is queued, the message plays immediately.

        * `interrupt` — The agent immediately speaks. If the agent was already speaking, it interrupts the current
        speech and replaces it with the new message. If the user is speaking, the agent interrupts with the new
        message, but the user's continued speech triggers `UserStartedSpeaking`, which quickly interrupts the agent.
  required:
    - type
    - message
  title: AgentV1_AgentV1InjectAgentMessage
AgentV1_AgentV1SendFunctionCallResponse:
  type: object
  properties:
    type:
      type: string
      enum:
        - FunctionCallResponse
      description: Message type identifier for function call responses
    id:
      type: string
      description: |
        The unique identifier for the function call.

        • **Required for client responses**: Should match the id from
          the corresponding `FunctionCallRequest`
        • **Optional for server responses**: Server may omit when responding
          to internal function executions
    name:
      type: string
      description: The name of the function being called
    content:
      type: string
      description: The content or result of the function call
  required:
    - type
    - name
    - content
  description: |
    Function call response message used bidirectionally:

    • **Client → Server**: Response after client executes a function
      marked as client_side: true
    • **Server → Client**: Response after server executes a function
      marked as client_side: false

    The same message structure serves both directions, enabling a unified
    interface for function call responses regardless of execution location.
  title: AgentV1_AgentV1SendFunctionCallResponse
ChannelsAgentV1MessagesAgentV1KeepAliveType:
  type: string
  enum:
    - KeepAlive
  description: Message type identifier
  title: ChannelsAgentV1MessagesAgentV1KeepAliveType
AgentV1_AgentV1KeepAlive:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsAgentV1MessagesAgentV1KeepAliveType'
      description: Message type identifier
  required:
    - type
  description: Send a control message to the agent
  title: AgentV1_AgentV1KeepAlive
AgentV1_AgentV1UpdatePrompt:
  type: object
  properties:
    type:
      type: string
      enum:
        - UpdatePrompt
      description: Message type identifier for prompt update request
    prompt:
      type: string
      description: The new system prompt to be used by the agent
  required:
    - type
    - prompt
  title: AgentV1_AgentV1UpdatePrompt
AgentV1_AgentV1ForceEndTurn:
  type: object
  properties:
    type:
      type: string
      enum:
        - ForceEndTurn
      description: Message type identifier for forcing the end of the current turn
  required:
    - type
  title: AgentV1_AgentV1ForceEndTurn
AgentV1_AgentV1Media:
  type: string
  format: binary
  title: AgentV1_AgentV1Media
ListenV1Callback:
  description: Any type
  title: ListenV1Callback
ListenV1CallbackMethod:
  type: string
  enum:
    - POST
    - GET
    - PUT
    - DELETE
  default: POST
  description: HTTP method by which the callback request will be made
  title: ListenV1CallbackMethod
ListenV1Channels:
  description: Any type
  title: ListenV1Channels
ListenV1DetectEntities:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: >-
    Identifies and extracts key entities from content in submitted audio. Entities appear in final results. When
    enabled, Punctuation will also be enabled by default
  title: ListenV1DetectEntities
ListenV1Diarize:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: >-
    Deprecated. Use `diarize_model` instead. Defaults to `false`. Recognize speaker changes. Each word in the
    transcript will be assigned a speaker number starting at 0
  title: ListenV1Diarize
  deprecated: true
ListenV1_diarize_model:
  type: string
  enum:
    - latest
    - v1
  title: ListenV1_diarize_model
ListenV1Dictation:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: Identify and extract key entities from content in submitted audio
  title: ListenV1Dictation
ListenV1Encoding:
  type: string
  enum:
    - linear16
    - linear32
    - flac
    - alaw
    - mulaw
    - amr-nb
    - amr-wb
    - opus
    - ogg-opus
    - speex
    - g729
  description: Specify the expected encoding of your submitted audio
  title: ListenV1Encoding
ListenV1Endpointing:
  description: Any type
  title: ListenV1Endpointing
ListenV1Extra:
  description: Any type
  title: ListenV1Extra
ListenV1InterimResults:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: >-
    Specifies whether the streaming endpoint should provide ongoing transcription updates as more audio is received.
    When set to true, the endpoint sends continuous updates, meaning transcription results may evolve over time
  title: ListenV1InterimResults
ListenV1Keyterm:
  description: Any type
  title: ListenV1Keyterm
ListenV1Keywords:
  description: Any type
  title: ListenV1Keywords
ListenV1Language:
  description: Any type
  title: ListenV1Language
ListenV1MipOptOut:
  description: Any type
  title: ListenV1MipOptOut
ListenV1Model:
  type: string
  enum:
    - nova-3
    - nova-3-general
    - nova-3-medical
    - nova-2
    - nova-2-general
    - nova-2-meeting
    - nova-2-finance
    - nova-2-conversationalai
    - nova-2-voicemail
    - nova-2-video
    - nova-2-medical
    - nova-2-drivethru
    - nova-2-automotive
    - nova
    - nova-general
    - nova-phonecall
    - nova-medical
    - enhanced
    - enhanced-general
    - enhanced-meeting
    - enhanced-phonecall
    - enhanced-finance
    - base
    - meeting
    - phonecall
    - finance
    - conversationalai
    - voicemail
    - video
    - custom
  description: AI model to use for the transcription
  title: ListenV1Model
ListenV1Multichannel:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: Transcribe each audio channel independently
  title: ListenV1Multichannel
ListenV1Numerals:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: Convert numbers from written format to numerical format
  title: ListenV1Numerals
ListenV1ProfanityFilter:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: >-
    Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or
    removes it from the transcript completely
  title: ListenV1ProfanityFilter
ListenV1Punctuate:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: Add punctuation and capitalization to the transcript
  title: ListenV1Punctuate
ListenV1Redact:
  type: string
  enum:
    - 'true'
    - 'false'
    - pci
    - numbers
    - aggressive_numbers
    - ssn
  default: 'false'
  description: Redaction removes sensitive information from your transcripts
  title: ListenV1Redact
ListenV1Replace:
  description: Any type
  title: ListenV1Replace
ListenV1SampleRate:
  description: Any type
  title: ListenV1SampleRate
ListenV1Search:
  description: Any type
  title: ListenV1Search
ListenV1SmartFormat:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: >-
    Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to
    improve readability
  title: ListenV1SmartFormat
ListenV1Tag:
  description: Any type
  title: ListenV1Tag
ListenV1UtteranceEndMs:
  description: Any type
  title: ListenV1UtteranceEndMs
ListenV1VadEvents:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: Indicates that speech has started. You'll begin receiving Speech Started messages upon speech starting
  title: ListenV1VadEvents
ListenV1Version:
  description: Any type
  title: ListenV1Version
ChannelsListenV1MessagesListenV1ResultsType:
  type: string
  enum:
    - Results
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1ResultsType
ChannelsListenV1MessagesListenV1ResultsChannelAlternativesItemsWordsItems:
  type: object
  properties:
    word:
      type: string
      description: The word of the transcription
    start:
      type: number
      format: double
      description: The start time of the word
    end:
      type: number
      format: double
      description: The end time of the word
    confidence:
      type: number
      format: double
      description: The confidence of the word
    language:
      type: string
      description: The language of the word
    punctuated_word:
      type: string
      description: The punctuated word of the word
    speaker:
      type: integer
      description: The speaker of the word, present when diarization is enabled
  required:
    - word
    - start
    - end
    - confidence
  title: ChannelsListenV1MessagesListenV1ResultsChannelAlternativesItemsWordsItems
ChannelsListenV1MessagesListenV1ResultsChannelAlternativesItems:
  type: object
  properties:
    transcript:
      type: string
      description: The transcript of the transcription
    confidence:
      type: number
      format: double
      description: The confidence of the transcription
    languages:
      type: array
      items:
        type: string
    words:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsChannelAlternativesItemsWordsItems'
  required:
    - transcript
    - confidence
    - words
  title: ChannelsListenV1MessagesListenV1ResultsChannelAlternativesItems
ChannelsListenV1MessagesListenV1ResultsChannel:
  type: object
  properties:
    alternatives:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsChannelAlternativesItems'
  required:
    - alternatives
  title: ChannelsListenV1MessagesListenV1ResultsChannel
ChannelsListenV1MessagesListenV1ResultsMetadataModelInfo:
  type: object
  properties:
    name:
      type: string
      description: The name of the model
    version:
      type: string
      description: The version of the model
    arch:
      type: string
      description: The arch of the model
  required:
    - name
    - version
    - arch
  title: ChannelsListenV1MessagesListenV1ResultsMetadataModelInfo
ChannelsListenV1MessagesListenV1ResultsMetadataDiarizeInfo:
  type: object
  properties:
    model_uuid:
      type: string
      description: The diarizer model UUID
    arch:
      type: string
      description: The diarizer arch, such as `v1` or `v2`
  required:
    - model_uuid
    - arch
  description: The diarizer that produced the speaker labels. Present only when a diarizer ran.
  title: ChannelsListenV1MessagesListenV1ResultsMetadataDiarizeInfo
ChannelsListenV1MessagesListenV1ResultsMetadata:
  type: object
  properties:
    request_id:
      type: string
      description: The request ID
    model_info:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsMetadataModelInfo'
    model_uuid:
      type: string
      description: The model UUID
    diarize_info:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsMetadataDiarizeInfo'
      description: The diarizer that produced the speaker labels. Present only when a diarizer ran.
  required:
    - request_id
    - model_info
    - model_uuid
  title: ChannelsListenV1MessagesListenV1ResultsMetadata
ChannelsListenV1MessagesListenV1ResultsEntitiesItems:
  type: object
  properties:
    label:
      type: string
      description: The type/category of the entity (e.g., NAME, PHONE_NUMBER, EMAIL_ADDRESS, ORGANIZATION, CARDINAL)
    value:
      type: string
      description: The formatted text representation of the entity
    raw_value:
      type: string
      description: The original spoken text of the entity (present when formatting is enabled)
    confidence:
      type: number
      format: double
      description: The confidence score of the entity detection
    start_word:
      type: integer
      description: The index of the first word of the entity in the transcript (inclusive)
    end_word:
      type: integer
      description: The index of the last word of the entity in the transcript (exclusive)
  required:
    - label
    - value
    - raw_value
    - confidence
    - start_word
    - end_word
  title: ChannelsListenV1MessagesListenV1ResultsEntitiesItems
ListenV1_ListenV1Results:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsType'
      description: Message type identifier
    channel_index:
      type: array
      items:
        type: integer
      description: The index of the channel
    duration:
      type: number
      format: double
      description: The duration of the transcription
    start:
      type: number
      format: double
      description: The start time of the transcription
    is_final:
      type: boolean
      description: Whether the transcription is final
    speech_final:
      type: boolean
      description: Whether the transcription is speech final
    channel:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsChannel'
    metadata:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsMetadata'
    from_finalize:
      type: boolean
      description: Whether the transcription is from a finalize message
    entities:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1ResultsEntitiesItems'
      description: >-
        Extracted entities from the audio when detect_entities is enabled. Only present in is_final messages.
        Returns an empty array if no entities are detected
  required:
    - type
    - channel_index
    - duration
    - start
    - channel
    - metadata
  title: ListenV1_ListenV1Results
ChannelsListenV1MessagesListenV1MetadataType:
  type: string
  enum:
    - Metadata
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1MetadataType
ListenV1_ListenV1Metadata:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1MetadataType'
      description: Message type identifier
    transaction_key:
      type: string
      description: The transaction key
      deprecated: true
    request_id:
      type: string
      format: uuid
      description: The request ID
    sha256:
      type: string
      description: The sha256
    created:
      type: string
      description: The created
    duration:
      type: number
      format: double
      description: The duration
    channels:
      type: integer
      description: The channels
  required:
    - type
    - transaction_key
    - request_id
    - sha256
    - created
    - duration
    - channels
  title: ListenV1_ListenV1Metadata
ChannelsListenV1MessagesListenV1UtteranceEndType:
  type: string
  enum:
    - UtteranceEnd
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1UtteranceEndType
ListenV1_ListenV1UtteranceEnd:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1UtteranceEndType'
      description: Message type identifier
    channel:
      type: array
      items:
        type: integer
      description: The channel
    last_word_end:
      type: number
      format: double
      description: The last word end
  required:
    - type
    - channel
    - last_word_end
  title: ListenV1_ListenV1UtteranceEnd
ChannelsListenV1MessagesListenV1SpeechStartedType:
  type: string
  enum:
    - SpeechStarted
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1SpeechStartedType
ListenV1_ListenV1SpeechStarted:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1SpeechStartedType'
      description: Message type identifier
    channel:
      type: array
      items:
        type: integer
      description: The channel
    timestamp:
      type: number
      format: double
      description: The timestamp
  required:
    - type
    - channel
    - timestamp
  title: ListenV1_ListenV1SpeechStarted
ListenV1_ListenV1Media:
  type: string
  format: binary
  title: ListenV1_ListenV1Media
ChannelsListenV1MessagesListenV1FinalizeType:
  type: string
  enum:
    - Finalize
    - CloseStream
    - KeepAlive
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1FinalizeType
ListenV1_ListenV1Finalize:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1FinalizeType'
      description: Message type identifier
  required:
    - type
  title: ListenV1_ListenV1Finalize
ChannelsListenV1MessagesListenV1CloseStreamType:
  type: string
  enum:
    - Finalize
    - CloseStream
    - KeepAlive
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1CloseStreamType
ListenV1_ListenV1CloseStream:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1CloseStreamType'
      description: Message type identifier
  required:
    - type
  title: ListenV1_ListenV1CloseStream
ChannelsListenV1MessagesListenV1KeepAliveType:
  type: string
  enum:
    - Finalize
    - CloseStream
    - KeepAlive
  description: Message type identifier
  title: ChannelsListenV1MessagesListenV1KeepAliveType
ListenV1_ListenV1KeepAlive:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV1MessagesListenV1KeepAliveType'
      description: Message type identifier
  required:
    - type
  title: ListenV1_ListenV1KeepAlive
ListenV2Model:
  type: string
  enum:
    - flux-general-en
    - flux-general-multi
  description: Defines the AI model used to process submitted audio.
  title: ListenV2Model
ListenV2Encoding:
  type: string
  enum:
    - linear16
    - linear32
    - mulaw
    - alaw
    - opus
    - ogg-opus
  description: >-
    Encoding of the audio stream. Required if sending non-containerized/raw audio. If sending containerized audio,
    this parameter should be omitted.
  title: ListenV2Encoding
ListenV2SampleRate:
  description: Any type
  title: ListenV2SampleRate
ListenV2EagerEotThreshold:
  description: Any type
  title: ListenV2EagerEotThreshold
ListenV2EotThreshold:
  description: Any type
  title: ListenV2EotThreshold
ListenV2EotTimeoutMs:
  description: Any type
  title: ListenV2EotTimeoutMs
ListenV2Keyterm:
  oneOf:
    - type: string
    - type: array
      items:
        type: string
  description: |
    Keyterm prompting improves recognition of specialized terminology.

    `keyterm` accepts plain terms only. Unlike the legacy `keywords` feature,
    it does not support weights or intensifiers. Appending one
    (for example, `keyterm=term:0.15`) is not rejected—the weight is
    silently ignored and the entire value is treated as a literal keyterm.

    To boost multiple separate keyterms, repeat the `keyterm` parameter
    (for example, `keyterm=term1&keyterm=term2`). To boost one multi-word
    phrase as a single keyterm, join the words with `%20` or `+`
    (for example, `keyterm=customer%20service`). Do not separate keyterms
    with commas, semicolons, or line breaks.
  title: ListenV2Keyterm
ListenV2LanguageHint:
  oneOf:
    - type: string
    - type: array
      items:
        type: string
  description: |
    Language hints constrain and prioritize language detection for the
    flux-general-multi model. Pass multiple language_hint query parameters
    to specify multiple language codes. Empty values are rejected.
    Only valid when model is flux-general-multi.
  title: ListenV2LanguageHint
ListenV2ProfanityFilter:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: >-
    Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or
    removes it from the transcript completely.
  title: ListenV2ProfanityFilter
ListenV2Numerals:
  type: string
  enum:
    - 'true'
    - 'false'
  default: 'false'
  description: Numerals converts numbers from written format to numerical format
  title: ListenV2Numerals
ListenV2Redact:
  type: string
  enum:
    - numbers
    - aggressive_numbers
  description: >-
    Redaction removes sensitive information from your transcripts. On Flux, only `numbers` and `aggressive_numbers`
    are supported.
  title: ListenV2Redact
ListenV2MipOptOut:
  description: Any type
  title: ListenV2MipOptOut
ListenV2Tag:
  description: Any type
  title: ListenV2Tag
ChannelsListenV2MessagesListenV2ConnectedType:
  type: string
  enum:
    - Connected
  description: Message type identifier
  title: ChannelsListenV2MessagesListenV2ConnectedType
ListenV2_ListenV2Connected:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2ConnectedType'
      description: Message type identifier
    request_id:
      type: string
      format: uuid
      description: The unique identifier of the request
    sequence_id:
      type: integer
      minimum: 0
      description: |
        Starts at `0` and increments for each message the server sends
        to the client.  This includes messages of other types, like
        `TurnInfo` messages.
  required:
    - type
    - request_id
    - sequence_id
  title: ListenV2_ListenV2Connected
ChannelsListenV2MessagesListenV2TurnInfoEvent:
  type: string
  enum:
    - Update
    - StartOfTurn
    - EagerEndOfTurn
    - TurnResumed
    - EndOfTurn
  description: >
    The type of event being reported.


    - **Update** - Additional audio has been transcribed, but the turn state hasn't changed

    - **StartOfTurn** - The user has begun speaking for the first time in the turn

    - **EagerEndOfTurn** - The system has moderate confidence that the user has finished speaking for the turn. This
    is an opportunity to begin preparing an agent reply

    - **TurnResumed** - The system detected that speech had ended and therefore sent an **EagerEndOfTurn** event,
    but speech is actually continuing for this turn

    - **EndOfTurn** - The user has finished speaking for the turn
  title: ChannelsListenV2MessagesListenV2TurnInfoEvent
ChannelsListenV2MessagesListenV2TurnInfoWordsItems:
  type: object
  properties:
    word:
      type: string
      description: The individual punctuated, properly-cased word from the transcript
    confidence:
      type: string
      title: float
      description: Confidence that this word was transcribed correctly
    start:
      type: number
      format: double
      minimum: 0
      description: The start time of the word
    end:
      type: number
      format: double
      minimum: 0
      description: The end time of the word
  required:
    - word
    - confidence
  title: ChannelsListenV2MessagesListenV2TurnInfoWordsItems
ListenV2_ListenV2TurnInfo:
  type: object
  properties:
    type:
      type: string
      enum:
        - TurnInfo
    request_id:
      type: string
      format: uuid
      description: The unique identifier of the request
    sequence_id:
      type: integer
      minimum: 0
      description: >
        Starts at `0` and increments for each message the server sends to the client.  This includes messages of
        other types, like `Connected` messages.
    event:
      $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2TurnInfoEvent'
      description: >
        The type of event being reported.


        - **Update** - Additional audio has been transcribed, but the turn state hasn't changed

        - **StartOfTurn** - The user has begun speaking for the first time in the turn

        - **EagerEndOfTurn** - The system has moderate confidence that the user has finished speaking for the turn.
        This is an opportunity to begin preparing an agent reply

        - **TurnResumed** - The system detected that speech had ended and therefore sent an **EagerEndOfTurn**
        event, but speech is actually continuing for this turn

        - **EndOfTurn** - The user has finished speaking for the turn
    turn_index:
      type: integer
      minimum: 0
      description: The index of the current turn
    audio_window_start:
      type: string
      title: float
      description: Start time in seconds of the audio range that was transcribed
    audio_window_end:
      type: string
      title: float
      description: End time in seconds of the audio range that was transcribed
    transcript:
      type: string
      description: Text that was said over the course of the current turn
    words:
      type: array
      items:
        $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2TurnInfoWordsItems'
      description: The words in the `transcript`
    end_of_turn_confidence:
      type: string
      title: float
      description: Confidence that no more speech is coming in this turn
    trigger:
      type: string
      description: >
        The cause of the turn ending. Present on every `EndOfTurn` event and only there.


        - **model** - the turn ended by Flux's native end-of-turn detection


        - **manual** - the turn ended because a `ForceEndTurn` message was sent


        - **timeout** - the turn ended because `eot_timeout_ms` elapsed


        This is an open enum. New values may be added over time, so clients must tolerate values they do not
        recognize.
    languages:
      type: array
      items:
        type: string
      description: |
        Detected languages sorted by descending frequency in the
        transcript. Only present when the flux-general-multi model
        detects languages in the audio.
    languages_hinted:
      type: array
      items:
        type: string
      description: |
        The language hints that were supplied for this turn. Only
        present when language hints are configured.
  required:
    - type
    - request_id
    - sequence_id
    - event
    - turn_index
    - audio_window_start
    - audio_window_end
    - transcript
    - words
    - end_of_turn_confidence
  description: Describes the current turn and latest state of the turn
  title: ListenV2_ListenV2TurnInfo
ChannelsListenV2MessagesListenV2ConfigureSuccessThresholds:
  type: object
  properties:
    eager_eot_threshold:
      $ref: '#/components/schemas/ListenV2EagerEotThreshold'
    eot_threshold:
      $ref: '#/components/schemas/ListenV2EotThreshold'
      default: '0.7'
    eot_timeout_ms:
      $ref: '#/components/schemas/ListenV2EotTimeoutMs'
      default: '5000'
  description: |
    Updates each parameter, if it is supplied. If a particular threshold parameter
    is not supplied, the configuration continues using the currently configured value.
  title: ChannelsListenV2MessagesListenV2ConfigureSuccessThresholds
ListenV2ConfigureNumerals:
  type: boolean
  default: false
  description: >-
    Numerals converts numbers from written format to numerical format. Applies to transcripts Flux STT sends after
    it processes the update.
  title: ListenV2ConfigureNumerals
ListenV2_ListenV2ConfigureSuccess:
  type: object
  properties:
    type:
      type: string
      enum:
        - ConfigureSuccess
      description: Message type identifier
    request_id:
      type: string
      format: uuid
      description: The unique identifier of the request
    thresholds:
      $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2ConfigureSuccessThresholds'
      description: |
        Updates each parameter, if it is supplied. If a particular threshold parameter
        is not supplied, the configuration continues using the currently configured value.
    keyterms:
      $ref: '#/components/schemas/ListenV2Keyterm'
    language_hints:
      type: array
      items:
        type: string
      description: |
        The currently active language hints. Only applicable to the flux-general-multi model.
    numerals:
      $ref: '#/components/schemas/ListenV2ConfigureNumerals'
      default: false
      description: Whether numeral formatting is enabled for transcripts Flux STT sends after it processes the update.
    sequence_id:
      type: integer
      minimum: 0
      description: |
        Starts at `0` and increments for each message the server sends
        to the client.  This includes messages of other types, like
        `TurnInfo` messages.
  required:
    - type
    - request_id
    - thresholds
    - keyterms
    - sequence_id
  title: ListenV2_ListenV2ConfigureSuccess
ListenV2_ListenV2ConfigureFailure:
  type: object
  properties:
    type:
      type: string
      enum:
        - ConfigureFailure
      description: Message type identifier
    request_id:
      type: string
      format: uuid
      description: The unique identifier of the request
    sequence_id:
      type: integer
      minimum: 0
      description: |
        Starts at `0` and increments for each message the server sends
        to the client.  This includes messages of other types, like
        `TurnInfo` messages.
    code:
      type: string
      description: Failure code identifying the rejected configuration
    description:
      type: string
      description: A human-readable description of the configuration failure
  required:
    - type
    - request_id
    - sequence_id
  title: ListenV2_ListenV2ConfigureFailure
ListenV2_ListenV2Warning:
  type: object
  properties:
    type:
      type: string
      enum:
        - Warning
      description: Message type identifier
    request_id:
      type: string
      format: uuid
      description: The unique identifier of the request
    sequence_id:
      type: integer
      minimum: 0
      description: |
        Starts at `0` and increments for each message the server sends
        to the client. This includes messages of other types, like
        `TurnInfo` messages.
    code:
      type: string
      description: Warning code identifying the condition, in `SCREAMING_SNAKE_CASE`
    description:
      type: string
      description: A human-readable description of the warning
  required:
    - type
    - request_id
    - sequence_id
    - code
    - description
  title: ListenV2_ListenV2Warning
ChannelsListenV2MessagesListenV2FatalErrorType:
  type: string
  enum:
    - Error
  description: Message type identifier
  title: ChannelsListenV2MessagesListenV2FatalErrorType
ListenV2_ListenV2FatalError:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2FatalErrorType'
      description: Message type identifier
    sequence_id:
      type: integer
      minimum: 0
      description: |
        Starts at `0` and increments for each message the server sends
        to the client.  This includes messages of other types, like
        `Connected` messages.
    code:
      type: string
      description: A string code describing the error, e.g. `INTERNAL_SERVER_ERROR`
    description:
      type: string
      description: Prose description of the error
  required:
    - type
    - sequence_id
    - code
    - description
  title: ListenV2_ListenV2FatalError
ListenV2_ListenV2Media:
  type: string
  format: binary
  title: ListenV2_ListenV2Media
ChannelsListenV2MessagesListenV2CloseStreamType:
  type: string
  enum:
    - CloseStream
  description: Message type identifier
  title: ChannelsListenV2MessagesListenV2CloseStreamType
ListenV2_ListenV2CloseStream:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2CloseStreamType'
      description: Message type identifier
  required:
    - type
  title: ListenV2_ListenV2CloseStream
ListenV2_ListenV2ForceEndTurn:
  type: object
  properties:
    type:
      type: string
      enum:
        - ForceEndTurn
      description: Message type identifier
  required:
    - type
  title: ListenV2_ListenV2ForceEndTurn
ChannelsListenV2MessagesListenV2ConfigureThresholds:
  type: object
  properties:
    eager_eot_threshold:
      $ref: '#/components/schemas/ListenV2EagerEotThreshold'
    eot_threshold:
      $ref: '#/components/schemas/ListenV2EotThreshold'
      default: '0.7'
    eot_timeout_ms:
      $ref: '#/components/schemas/ListenV2EotTimeoutMs'
      default: '5000'
  description: |
    Updates each parameter, if it is supplied. If a particular threshold parameter
    is not supplied, the configuration continues using the currently configured value.
  title: ChannelsListenV2MessagesListenV2ConfigureThresholds
ListenV2_ListenV2Configure:
  type: object
  properties:
    type:
      type: string
      enum:
        - Configure
      description: Message type identifier
    thresholds:
      $ref: '#/components/schemas/ChannelsListenV2MessagesListenV2ConfigureThresholds'
      description: |
        Updates each parameter, if it is supplied. If a particular threshold parameter
        is not supplied, the configuration continues using the currently configured value.
    keyterms:
      $ref: '#/components/schemas/ListenV2Keyterm'
    language_hints:
      type: array
      items:
        type: string
      description: |
        Language hints to constrain and prioritize language detection.
        Only valid when the model is flux-general-multi. If this field is not supplied,
        the session will continue to use the currently configured value.
    numerals:
      $ref: '#/components/schemas/ListenV2ConfigureNumerals'
      default: false
  required:
    - type
  title: ListenV2_ListenV2Configure
SpeakV1Encoding:
  type: string
  enum:
    - linear16
    - mulaw
    - alaw
  default: linear16
  description: >-
    Encoding allows you to specify the expected encoding of your audio output for streaming TTS. Only
    streaming-compatible encodings are supported.
  title: SpeakV1Encoding
SpeakV1MipOptOut:
  description: Any type
  title: SpeakV1MipOptOut
SpeakV1Model:
  type: string
  enum:
    - aura-angus-en
    - aura-arcas-en
    - aura-asteria-en
    - aura-athena-en
    - aura-helios-en
    - aura-hera-en
    - aura-luna-en
    - aura-orion-en
    - aura-orpheus-en
    - aura-perseus-en
    - aura-stella-en
    - aura-zeus-en
    - aura-2-amalthea-en
    - aura-2-andromeda-en
    - aura-2-apollo-en
    - aura-2-arcas-en
    - aura-2-aries-en
    - aura-2-asteria-en
    - aura-2-athena-en
    - aura-2-atlas-en
    - aura-2-aurora-en
    - aura-2-callista-en
    - aura-2-cora-en
    - aura-2-cordelia-en
    - aura-2-delia-en
    - aura-2-draco-en
    - aura-2-electra-en
    - aura-2-harmonia-en
    - aura-2-helena-en
    - aura-2-hera-en
    - aura-2-hermes-en
    - aura-2-hyperion-en
    - aura-2-iris-en
    - aura-2-janus-en
    - aura-2-juno-en
    - aura-2-jupiter-en
    - aura-2-luna-en
    - aura-2-mars-en
    - aura-2-minerva-en
    - aura-2-neptune-en
    - aura-2-odysseus-en
    - aura-2-ophelia-en
    - aura-2-orion-en
    - aura-2-orpheus-en
    - aura-2-pandora-en
    - aura-2-phoebe-en
    - aura-2-pluto-en
    - aura-2-saturn-en
    - aura-2-selene-en
    - aura-2-thalia-en
    - aura-2-theia-en
    - aura-2-vesta-en
    - aura-2-zeus-en
    - aura-2-agustina-es
    - aura-2-alvaro-es
    - aura-2-antonia-es
    - aura-2-aquila-es
    - aura-2-carina-es
    - aura-2-celeste-es
    - aura-2-diana-es
    - aura-2-estrella-es
    - aura-2-gloria-es
    - aura-2-javier-es
    - aura-2-luciano-es
    - aura-2-nestor-es
    - aura-2-olivia-es
    - aura-2-selena-es
    - aura-2-silvia-es
    - aura-2-sirio-es
    - aura-2-valerio-es
    - aura-2-aurelia-de
    - aura-2-elara-de
    - aura-2-fabian-de
    - aura-2-julius-de
    - aura-2-kara-de
    - aura-2-lara-de
    - aura-2-viktoria-de
    - aura-2-beatrix-nl
    - aura-2-cornelia-nl
    - aura-2-daphne-nl
    - aura-2-hestia-nl
    - aura-2-lars-nl
    - aura-2-leda-nl
    - aura-2-rhea-nl
    - aura-2-roman-nl
    - aura-2-sander-nl
    - aura-2-agathe-fr
    - aura-2-hector-fr
    - aura-2-cesare-it
    - aura-2-cinzia-it
    - aura-2-demetra-it
    - aura-2-dionisio-it
    - aura-2-elio-it
    - aura-2-flavio-it
    - aura-2-livia-it
    - aura-2-maia-it
    - aura-2-melia-it
    - aura-2-ama-ja
    - aura-2-ebisu-ja
    - aura-2-fujin-ja
    - aura-2-izanami-ja
    - aura-2-uzume-ja
  default: aura-asteria-en
  description: AI model used to process submitted text
  title: SpeakV1Model
SpeakV1SampleRate:
  type: string
  enum:
    - '8000'
    - '16000'
    - '24000'
    - '32000'
    - '48000'
  default: '24000'
  description: >-
    Sample Rate specifies the sample rate for the output audio. Based on encoding 8000 or 24000 are possible
    defaults. For some encodings sample rate is not configurable.
  title: SpeakV1SampleRate
SpeakV1Speed:
  type: number
  format: double
  minimum: 0.7
  maximum: 1.5
  default: 1
  description: >-
    Speaking rate multiplier that adjusts the pace of generated speech while preserving natural prosody and voice
    quality. Not yet supported in all languages.
  title: SpeakV1Speed
SpeakV1_SpeakV1Audio:
  type: string
  format: binary
  title: SpeakV1_SpeakV1Audio
ChannelsSpeakV1MessagesSpeakV1MetadataType:
  type: string
  enum:
    - Metadata
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1MetadataType
SpeakV1_SpeakV1Metadata:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1MetadataType'
      description: Message type identifier
    request_id:
      type: string
      format: uuid
      description: Unique identifier for the request
    model_name:
      type: string
      description: Name of the model being used
    model_version:
      type: string
      description: Version of the primary model being used
    model_uuid:
      type: string
      format: uuid
      description: Unique identifier for the primary model used
    additional_model_uuids:
      type: array
      items:
        type: string
        format: uuid
      description: List of unique identifiers for any additional models used to serve the request
  required:
    - type
    - request_id
    - model_name
    - model_version
    - model_uuid
  title: SpeakV1_SpeakV1Metadata
ChannelsSpeakV1MessagesSpeakV1FlushedType:
  type: string
  enum:
    - Flushed
    - Cleared
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1FlushedType
SpeakV1_SpeakV1Flushed:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1FlushedType'
      description: Message type identifier
    sequence_id:
      type: integer
      description: The sequence ID of the response
  required:
    - type
    - sequence_id
  title: SpeakV1_SpeakV1Flushed
ChannelsSpeakV1MessagesSpeakV1ClearedType:
  type: string
  enum:
    - Flushed
    - Cleared
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1ClearedType
SpeakV1_SpeakV1Cleared:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1ClearedType'
      description: Message type identifier
    sequence_id:
      type: integer
      description: The sequence ID of the response
  required:
    - type
    - sequence_id
  title: SpeakV1_SpeakV1Cleared
ChannelsSpeakV1MessagesSpeakV1WarningType:
  type: string
  enum:
    - Warning
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1WarningType
SpeakV1_SpeakV1Warning:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1WarningType'
      description: Message type identifier
    description:
      type: string
      description: A description of what went wrong
    code:
      type: string
      description: Error code identifying the type of error
  required:
    - type
    - description
    - code
  title: SpeakV1_SpeakV1Warning
ChannelsSpeakV1MessagesSpeakV1TextType:
  type: string
  enum:
    - Speak
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1TextType
SpeakV1_SpeakV1Text:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1TextType'
      description: Message type identifier
    text:
      type: string
      description: The input text to be converted to speech
  required:
    - type
    - text
  title: SpeakV1_SpeakV1Text
ChannelsSpeakV1MessagesSpeakV1FlushType:
  type: string
  enum:
    - Flush
    - Clear
    - Close
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1FlushType
SpeakV1_SpeakV1Flush:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1FlushType'
      description: Message type identifier
  required:
    - type
  title: SpeakV1_SpeakV1Flush
ChannelsSpeakV1MessagesSpeakV1ClearType:
  type: string
  enum:
    - Flush
    - Clear
    - Close
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1ClearType
SpeakV1_SpeakV1Clear:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1ClearType'
      description: Message type identifier
  required:
    - type
  title: SpeakV1_SpeakV1Clear
ChannelsSpeakV1MessagesSpeakV1CloseType:
  type: string
  enum:
    - Flush
    - Clear
    - Close
  description: Message type identifier
  title: ChannelsSpeakV1MessagesSpeakV1CloseType
SpeakV1_SpeakV1Close:
  type: object
  properties:
    type:
      $ref: '#/components/schemas/ChannelsSpeakV1MessagesSpeakV1CloseType'
      description: Message type identifier
  required:
    - type
  title: SpeakV1_SpeakV1Close
SpeakV2Model:
  type: string
  description: >-
    The Flux TTS model used to synthesize speech. Required on every connection. Model strings follow the format
    `flux-{voice}-{language}` (e.g. `flux-alexis-en`). An Aura model string is rejected on `/v2/speak`; use
    `/v1/speak` for Aura voices.
  title: SpeakV2Model
SpeakV2Encoding:
  type: string
  enum:
    - linear16
    - mulaw
    - alaw
  default: linear16
  description: >-
    Encoding of the raw output audio. The streaming WebSocket emits raw (non-containerized) audio, so only
    streaming-compatible encodings are supported. Compressed and containerized encodings (`mp3`, `opus`, `flac`,
    `aac`) are available on the batch REST transport only.
  title: SpeakV2Encoding
SpeakV2SampleRate:
  type: string
  enum:
    - '8000'
    - '16000'
    - '24000'
    - '32000'
    - '44100'
    - '48000'
  description: >-
    Output sample rate in Hz. With `linear16`, valid values are `8000`, `16000`, `24000`, `32000`, `44100`, and
    `48000`. With `mulaw` or `alaw`, valid values are `8000` and `16000`. Defaults to the model's native sample
    rate.
  title: SpeakV2SampleRate
SpeakV2Speed:
  type: number
  format: double
  minimum: 0.5
  maximum: 1.5
  multipleOf: 0.05
  default: 1
  description: >-
    Speech-rate multiplier. `1.0` is the model's nominal rate; lower is slower. Accepted values run `0.5` to `1.5`
    in `0.05` increments. A value outside that range is rejected with `SPEED_OUT_OF_RANGE`; a value inside it but
    off the `0.05` increment with `SPEED_INCREMENT_INVALID`. Models and languages without runtime speed control
    reject any value with `SPEED_NOT_SUPPORTED`.
  title: SpeakV2Speed
SpeakV2Expressivity:
  type: string
  enum:
    - '-2'
    - '-1'
    - '0'
    - '1'
    - '2'
  description: >-
    Expressive range of the generated speech, on a calm-to-animated axis. Accepted values: `-2`, `-1`, `0`, `1`,
    `2`. `0` (the default) is the voice's tuned delivery and the production-validated setting, with `-2` the calm
    end of the range and `2` the animated end. Supported on all Flux voices. Fixed for the connection — not settable
    via `Configure`. Beta: behavior may change in future model versions, and non-default values increase the risk of
    hallucinations and pronunciation errors; audition before shipping. An invalid value fails the connection with a
    `400` — `EXPRESSIVITY_OUT_OF_RANGE` for a value outside the range, `EXPRESSIVITY_INCREMENT_INVALID` for a
    fractional value. See [Expressivity](/guides/tts-voice-controls-tts-expressivity).
  title: SpeakV2Expressivity
SpeakV2MipOptOut:
  description: Any type
  title: SpeakV2MipOptOut
SpeakV2Tag:
  description: Any type
  title: SpeakV2Tag
SpeakV2_SpeakV2Audio:
  type: string
  format: binary
  title: SpeakV2_SpeakV2Audio
SpeakV2_SpeakV2Connected:
  type: object
  properties:
    type:
      type: string
      enum:
        - Connected
      description: Message type identifier
    request_id:
      type: string
      format: uuid
      description: The unique identifier of the `/v2/speak` request
    model_name:
      type: string
      description: Resolved model name
    model_version:
      type: string
      description: Resolved model version
    model_uuids:
      type: array
      items:
        type: string
        format: uuid
      description: Resolved model UUIDs. A list, because a resolved model may be backed by more than one underlying model.
  required:
    - type
    - request_id
    - model_name
    - model_version
    - model_uuids
  title: SpeakV2_SpeakV2Connected
SpeakV2_SpeakV2SpeechStarted:
  type: object
  properties:
    type:
      type: string
      enum:
        - SpeechStarted
      description: Message type identifier
    speech_id:
      type: string
      description: Server-minted identifier for this turn, of the form `dg_sp_<12 hex digits>`. Informational.
  required:
    - type
    - speech_id
  title: SpeakV2_SpeakV2SpeechStarted
ChannelsSpeakV2MessagesSpeakV2SpeechMetadataControlsApplied:
  type: object
  properties:
    pronunciations_applied:
      type: integer
      description: >-
        Pronunciation overrides successfully applied. Mirrors the Aura-2 `dg-pronunciations-applied` REST header.
        Currently always `0`.
    breaks_applied:
      type: integer
      description: >-
        Pause (break) controls successfully applied. Mirrors the Aura-2 `dg-breaks-applied` REST header. Currently
        always `0`.
    pronunciation_warnings:
      type: integer
      description: >-
        Pronunciation entries that triggered a warning (invalid IPA, word too long). Mirrors the Aura-2
        `dg-pronunciation-warnings` REST header. Currently always `0`.
  required:
    - pronunciations_applied
    - breaks_applied
    - pronunciation_warnings
  description: >-
    Counts of the inline controls the server acted on during the turn. Inline pause and pronunciation controls are
    not applied at launch — support is coming soon — so every count is currently `0`.
  title: ChannelsSpeakV2MessagesSpeakV2SpeechMetadataControlsApplied
SpeakV2_SpeakV2SpeechMetadata:
  type: object
  properties:
    type:
      type: string
      enum:
        - SpeechMetadata
      description: Message type identifier
    speech_id:
      type: string
      description: Server-assigned turn identifier
    audio_duration_ms:
      type: integer
      description: Total audio duration produced for this turn, in milliseconds
    input_character_count:
      type: integer
      description: Raw input character count for this turn, before text normalization
    billable_character_count:
      type: integer
      description: >-
        Billable character count for this turn — the input character count with stripped control characters removed.
        Always less than or equal to `input_character_count`.
    controls_applied:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2SpeechMetadataControlsApplied'
      description: >-
        Counts of the inline controls the server acted on during the turn. Inline pause and pronunciation controls
        are not applied at launch — support is coming soon — so every count is currently `0`.
  required:
    - type
    - speech_id
    - audio_duration_ms
    - input_character_count
    - billable_character_count
    - controls_applied
  title: SpeakV2_SpeakV2SpeechMetadata
ChannelsSpeakV2MessagesSpeakV2SpeechInterruptedMetadataControlsApplied:
  type: object
  properties:
    pronunciations_applied:
      type: integer
      description: >-
        Pronunciation overrides successfully applied. Mirrors the Aura-2 `dg-pronunciations-applied` REST header.
        Currently always `0`.
    breaks_applied:
      type: integer
      description: >-
        Pause (break) controls successfully applied. Mirrors the Aura-2 `dg-breaks-applied` REST header. Currently
        always `0`.
    pronunciation_warnings:
      type: integer
      description: >-
        Pronunciation entries that triggered a warning (invalid IPA, word too long). Mirrors the Aura-2
        `dg-pronunciation-warnings` REST header. Currently always `0`.
  required:
    - pronunciations_applied
    - breaks_applied
    - pronunciation_warnings
  description: >-
    Counts of the inline controls the server acted on during the turn. Inline pause and pronunciation controls are
    not applied at launch — support is coming soon — so every count is currently `0`.
  title: ChannelsSpeakV2MessagesSpeakV2SpeechInterruptedMetadataControlsApplied
ChannelsSpeakV2MessagesSpeakV2SpeechInterruptedMetadata:
  type: object
  properties:
    speech_id:
      type: string
      description: Server-assigned turn identifier
    audio_duration_ms:
      type: integer
      description: Audio duration produced for this turn, in milliseconds
    input_character_count:
      type: integer
      description: Raw input character count for this turn, before text normalization
    billable_character_count:
      type: integer
      description: >-
        Billable character count for this turn — the input character count with stripped control characters removed.
        Always less than or equal to `input_character_count`.
    controls_applied:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2SpeechInterruptedMetadataControlsApplied'
      description: >-
        Counts of the inline controls the server acted on during the turn. Inline pause and pronunciation controls
        are not applied at launch — support is coming soon — so every count is currently `0`.
  required:
    - speech_id
    - audio_duration_ms
    - input_character_count
    - billable_character_count
    - controls_applied
  description: Billing and timing for a single turn.
  title: ChannelsSpeakV2MessagesSpeakV2SpeechInterruptedMetadata
SpeakV2_SpeakV2SpeechInterrupted:
  type: object
  properties:
    type:
      type: string
      enum:
        - SpeechInterrupted
      description: Message type identifier
    audio_played_ms:
      type: integer
      description: >-
        How much audio the client had played when the interrupt landed, in milliseconds from the start of the
        session. Echoes the `Interrupt`'s `playback_offset` when one was supplied. Otherwise it is the server's own
        total, representing the audio that has been generated so far. A client that sends its first `Interrupt`
        without an offset can use this value as the baseline the next one must advance past.
    text_spoken:
      type: string
      description: The portion of the turn's text the user heard. Omitted when the `Interrupt` carried no `playback_offset`.
    text_remaining:
      type: string
      description: >-
        The portion of the turn's text the user did not hear. Omitted when the `Interrupt` carried no
        `playback_offset`.
    metadata:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2SpeechInterruptedMetadata'
      description: Billing and timing for a single turn.
  required:
    - type
    - audio_played_ms
    - metadata
  title: SpeakV2_SpeakV2SpeechInterrupted
SpeakV2_SpeakV2Flushed:
  type: object
  properties:
    type:
      type: string
      enum:
        - Flushed
      description: Message type identifier
    speech_id:
      type: string
      description: Server-assigned turn identifier
  required:
    - type
    - speech_id
  title: SpeakV2_SpeakV2Flushed
SpeakV2_SpeakV2SessionMetadata:
  type: object
  properties:
    type:
      type: string
      enum:
        - SessionMetadata
      description: Message type identifier
    total_audio_duration_ms:
      type: integer
      description: >-
        Cumulative audio duration produced across the session, in milliseconds. An `Interrupt` rebases this onto the
        audio the client actually played.
    total_input_character_count:
      type: integer
      description: Cumulative raw input character count across the session
    total_billable_character_count:
      type: integer
      description: Cumulative billable character count across the session
  required:
    - type
    - total_audio_duration_ms
    - total_input_character_count
    - total_billable_character_count
  title: SpeakV2_SpeakV2SessionMetadata
SpeakV2SpeedValue:
  type: number
  format: double
  minimum: 0.5
  maximum: 1.5
  multipleOf: 0.05
  default: 1
  description: >-
    Speech-rate multiplier. `1.0` is the model's nominal rate; lower is slower. Accepted values run `0.5` to `1.5`
    in `0.05` increments. A value outside that range is rejected with `SPEED_OUT_OF_RANGE`; a value inside it but
    off the `0.05` increment with `SPEED_INCREMENT_INVALID`. Models and languages without runtime speed control
    reject any value with `SPEED_NOT_SUPPORTED`.
  title: SpeakV2SpeedValue
ChannelsSpeakV2MessagesSpeakV2ConfigureSuccessApplied:
  type: object
  properties:
    speed:
      $ref: '#/components/schemas/SpeakV2SpeedValue'
      default: 1
  description: Synthesis configuration. A field is present only when it has been set on this session.
  title: ChannelsSpeakV2MessagesSpeakV2ConfigureSuccessApplied
SpeakV2_SpeakV2ConfigureSuccess:
  type: object
  properties:
    type:
      type: string
      enum:
        - ConfigureSuccess
      description: Message type identifier
    applied:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2ConfigureSuccessApplied'
      description: Synthesis configuration. A field is present only when it has been set on this session.
  required:
    - type
    - applied
  title: SpeakV2_SpeakV2ConfigureSuccess
ChannelsSpeakV2MessagesSpeakV2ConfigureFailureCode:
  type: string
  enum:
    - SPEED_OUT_OF_RANGE
    - SPEED_INCREMENT_INVALID
    - SPEED_NOT_SUPPORTED
    - INTERNAL_ERROR
  description: >-
    Failure code, in `SCREAMING_SNAKE_CASE`. `SPEED_OUT_OF_RANGE`: outside the range the model publishes.
    `SPEED_INCREMENT_INVALID`: inside the published range but off the `0.05` increment. `SPEED_NOT_SUPPORTED`: this
    model or language has no runtime speed control at all. `INTERNAL_ERROR`: the configuration was acceptable but
    the server could not apply it — unlike the others, a server-side failure rather than a statement about the
    request.
  title: ChannelsSpeakV2MessagesSpeakV2ConfigureFailureCode
ChannelsSpeakV2MessagesSpeakV2ConfigureFailureField:
  type: string
  enum:
    - speed
  description: The configuration field the failure is about. Absent when the failure is not tied to one field.
  title: ChannelsSpeakV2MessagesSpeakV2ConfigureFailureField
SpeakV2_SpeakV2ConfigureFailure:
  type: object
  properties:
    type:
      type: string
      enum:
        - ConfigureFailure
      description: Message type identifier
    code:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2ConfigureFailureCode'
      description: >-
        Failure code, in `SCREAMING_SNAKE_CASE`. `SPEED_OUT_OF_RANGE`: outside the range the model publishes.
        `SPEED_INCREMENT_INVALID`: inside the published range but off the `0.05` increment. `SPEED_NOT_SUPPORTED`:
        this model or language has no runtime speed control at all. `INTERNAL_ERROR`: the configuration was
        acceptable but the server could not apply it — unlike the others, a server-side failure rather than a
        statement about the request.
    field:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2ConfigureFailureField'
      description: The configuration field the failure is about. Absent when the failure is not tied to one field.
    value:
      type: number
      format: double
      description: >-
        The rejected value for `field`. Absent when there is no offending value to echo — `SPEED_NOT_SUPPORTED`
        names the field but carries no value, because the rejection is a property of the model.
    description:
      type: string
      description: A human-readable description of the failure
  required:
    - type
    - code
    - description
  title: SpeakV2_SpeakV2ConfigureFailure
SpeakV2_SpeakV2Warning:
  type: object
  properties:
    type:
      type: string
      enum:
        - Warning
      description: Message type identifier
    code:
      type: string
      description: >-
        Warning code identifying the condition, in `SCREAMING_SNAKE_CASE`.


        Turn-scoped codes: `NO_ACTIVE_SPEECH` (a speech-scoped message arrived with no active turn),
        `NO_SYNTHESIZABLE_TEXT` (the turn's text was entirely whitespace or punctuation, so it produced no audio and
        is completed with a zero-duration `SpeechMetadata`), and `SYNTHESIS_RETRYING` (a synthesis request failed
        and is being retried).


        Inline-control codes are reserved and not currently emitted, because inline pause and pronunciation controls
        are not yet applied: `BREAKS_LIMIT_EXCEEDED` (too many pause controls, or two pauses with no intervening
        text), `BREAK_TOKENS_OUT_OF_RANGE` (pause durations outside the range the model supports),
        `BREAK_TOKENS_WITH_INVALID_INCREMENTS` (pause durations off the model's supported increment),
        `PRONUNCIATION_WARNINGS` (a pronunciation override contained invalid IPA), `PRONUNCIATION_TOO_LONG` (an IPA
        string exceeded the length limit), `PRONUNCIATIONS_LIMIT_EXCEEDED` (too many pronunciation controls in one
        turn).


        Interrupt-scoped codes, each meaning the `Interrupt` was ignored: `NO_AUDIO_GENERATED` (the session has
        produced no audio yet, so there is nothing to interrupt), `INTERRUPT_IN_PROGRESS` (an earlier `Interrupt` is
        still being processed — at most one is handled at a time), `INVALID_INTERRUPT_OFFSET` (the `playback_offset`
        did not advance past the position a prior interrupt established).
    description:
      type: string
      description: A human-readable description of the warning
  required:
    - type
    - code
    - description
  title: SpeakV2_SpeakV2Warning
ChannelsSpeakV2MessagesSpeakV2ErrorCode:
  type: string
  enum:
    - MESSAGE-0000
    - DATA-0000
    - DATA-0002
    - BIG-0000
    - NET-0000
    - NET-0001
    - NET-0002
    - NET-0003
    - NET-0004
  description: A code identifying the error, e.g. `MESSAGE-0000` or `NET-0000`.
  title: ChannelsSpeakV2MessagesSpeakV2ErrorCode
SpeakV2_SpeakV2Error:
  type: object
  properties:
    type:
      type: string
      enum:
        - Error
      description: Message type identifier
    code:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2ErrorCode'
      description: A code identifying the error, e.g. `MESSAGE-0000` or `NET-0000`.
    description:
      type: string
      description: Prose description of the error
  required:
    - type
    - code
    - description
  title: SpeakV2_SpeakV2Error
SpeakV2_SpeakV2Speak:
  type: object
  properties:
    type:
      type: string
      enum:
        - Speak
      description: Message type identifier
    text:
      type: string
      description: >-
        The input text to synthesize. Inline pause and pronunciation controls are not yet applied; they are stripped
        from the text before synthesis.
  required:
    - type
    - text
  title: SpeakV2_SpeakV2Speak
SpeakV2_SpeakV2Flush:
  type: object
  properties:
    type:
      type: string
      enum:
        - Flush
      description: Message type identifier
  required:
    - type
  title: SpeakV2_SpeakV2Flush
ChannelsSpeakV2MessagesSpeakV2InterruptPlaybackOffset:
  type: object
  properties:
    type:
      type: string
      enum:
        - time_ms
      description: Offset unit. `time_ms` is the only supported form.
    value:
      type: integer
      description: Milliseconds of session audio the client played before barging in.
  required:
    - type
    - value
  description: >-
    How much audio the client had played when the user barged in. Optional: without it the server cannot split the
    turn's text, so `SpeechInterrupted` omits `text_spoken` and `text_remaining`.


    The offset is cumulative from the start of the *session*, not from the start of the current turn. Each
    `Interrupt` must advance past the position the previous one established.
  title: ChannelsSpeakV2MessagesSpeakV2InterruptPlaybackOffset
SpeakV2_SpeakV2Interrupt:
  type: object
  properties:
    type:
      type: string
      enum:
        - Interrupt
      description: Message type identifier
    playback_offset:
      $ref: '#/components/schemas/ChannelsSpeakV2MessagesSpeakV2InterruptPlaybackOffset'
      description: >-
        How much audio the client had played when the user barged in. Optional: without it the server cannot split
        the turn's text, so `SpeechInterrupted` omits `text_spoken` and `text_remaining`.


        The offset is cumulative from the start of the *session*, not from the start of the current turn. Each
        `Interrupt` must advance past the position the previous one established.
  required:
    - type
  title: SpeakV2_SpeakV2Interrupt
SpeakV2_SpeakV2Configure:
  type: object
  properties:
    type:
      type: string
      enum:
        - Configure
      description: Message type identifier
    speed:
      $ref: '#/components/schemas/SpeakV2SpeedValue'
      default: 1
  required:
    - type
  title: SpeakV2_SpeakV2Configure
SpeakV2_SpeakV2Close:
  type: object
  properties:
    type:
      type: string
      enum:
        - Close
      description: Message type identifier
  required:
    - type
  title: SpeakV2_SpeakV2Close