hume 0.13.6 → 0.13.8

package/.mock/definition/empathic-voice/__package__.yml

@@ -6,15 +6,29 @@ errors:
     examples:
       - value: {}
 types:
-  AssistantInput:
-    docs: When provided, the input is spoken by EVI.
+  AssistantEnd:
+    docs: When provided, the output is an assistant end message.
     properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
       type:
-        type: literal<"assistant_input">
+        type: literal<"assistant_end">
         docs: >-
-          The type of message sent through the socket; must be `assistant_input`
-          for our server to correctly identify and process it as an Assistant
-          Input message.
+          The type of message sent through the socket; for an Assistant End
+          message, this must be `assistant_end`.
+
+
+          This message indicates the conclusion of the assistant's response,
+          signaling that the assistant has finished speaking for the current
+          conversational turn.
+    source:
+      openapi: evi-asyncapi.json
+  AssistantInput:
+    docs: When provided, the input is spoken by EVI.
+    properties:
       custom_session_id:
         type: optional<string>
         docs: >-
@@ -33,16 +47,84 @@ types:
           the context of the conversation. The synthesized audio is streamed
           back to the user as an [Assistant
           Message](/reference/speech-to-speech-evi/chat#receive.AssistantMessage).
+      type:
+        type: literal<"assistant_input">
+        docs: >-
+          The type of message sent through the socket; must be `assistant_input`
+          for our server to correctly identify and process it as an Assistant
+          Input message.
+    source:
+      openapi: evi-asyncapi.json
+  AssistantMessage:
+    docs: When provided, the output is an assistant message.
+    properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      from_text:
+        type: boolean
+        docs: >-
+          Indicates if this message was inserted into the conversation as text
+          from an [Assistant Input
+          message](/reference/speech-to-speech-evi/chat#send.AssistantInput.text).
+      id:
+        type: optional<string>
+        docs: >-
+          ID of the assistant message. Allows the Assistant Message to be
+          tracked and referenced.
+      message:
+        type: ChatMessage
+        docs: Transcript of the message.
+      models:
+        type: Inference
+        docs: Inference model results.
+      type:
+        type: literal<"assistant_message">
+        docs: >-
+          The type of message sent through the socket; for an Assistant Message,
+          this must be `assistant_message`.
+
+
+          This message contains both a transcript of the assistant's response
+          and the expression measurement predictions of the assistant's audio
+          output.
+    source:
+      openapi: evi-asyncapi.json
+  AssistantProsody:
+    docs: When provided, the output is an Assistant Prosody message.
+    properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      id:
+        type: optional<string>
+        docs: Unique identifier for the segment.
+      models:
+        type: Inference
+        docs: Inference model results.
+      type:
+        type: literal<"assistant_prosody">
+        docs: >-
+          The type of message sent through the socket; for an Assistant Prosody
+          message, this must be `assistant_PROSODY`.
+
+
+          This message the expression measurement predictions of the assistant's
+          audio output.
     source:
       openapi: evi-asyncapi.json
   AudioConfiguration:
     properties:
-      encoding:
-        type: Encoding
-        docs: Encoding format of the audio input, such as `linear16`.
       channels:
         type: integer
         docs: Number of audio channels.
+      encoding:
+        type: Encoding
+        docs: Encoding format of the audio input, such as `linear16`.
       sample_rate:
         type: integer
         docs: >-
@@ -53,17 +135,6 @@ types:
   AudioInput:
     docs: When provided, the input is audio.
     properties:
-      type:
-        type: literal<"audio_input">
-        docs: >-
-          The type of message sent through the socket; must be `audio_input` for
-          our server to correctly identify and process it as an Audio Input
-          message.
-
-
-          This message is used for sending audio input data to EVI for
-          processing and expression measurement. Audio data should be sent as a
-          continuous stream, encoded in Base64.
       custom_session_id:
         type: optional<string>
         docs: >-
@@ -86,6 +157,48 @@ types:
 
           Hume recommends streaming audio with a buffer window of 20
           milliseconds (ms), or 100 milliseconds (ms) for web applications.
+      type:
+        type: literal<"audio_input">
+        docs: >-
+          The type of message sent through the socket; must be `audio_input` for
+          our server to correctly identify and process it as an Audio Input
+          message.
+
+
+          This message is used for sending audio input data to EVI for
+          processing and expression measurement. Audio data should be sent as a
+          continuous stream, encoded in Base64.
+    source:
+      openapi: evi-asyncapi.json
+  AudioOutput:
+    docs: >-
+      The type of message sent through the socket; for an Audio Output message,
+      this must be `audio_output`.
+    properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      data:
+        type: string
+        docs: >-
+          Base64 encoded audio output. This encoded audio is transmitted to the
+          client, where it can be decoded and played back as part of the user
+          interaction.
+      id:
+        type: string
+        docs: >-
+          ID of the audio output. Allows the Audio Output message to be tracked
+          and referenced.
+      index:
+        type: integer
+        docs: Index of the chunk of audio relative to the whole audio segment.
+      type:
+        type: literal<"audio_output">
+        docs: >-
+          The type of message sent through the socket; for an Audio Output
+          message, this must be `audio_output`.
     source:
       openapi: evi-asyncapi.json
   BuiltInTool:
@@ -99,31 +212,87 @@ types:
       openapi: evi-asyncapi.json
   BuiltinToolConfig:
     properties:
-      name:
-        type: BuiltInTool
       fallback_content:
         type: optional<string>
         docs: >-
           Optional text passed to the supplemental LLM if the tool call fails.
           The LLM then uses this text to generate a response back to the user,
           ensuring continuity in the conversation.
+      name:
+        type: BuiltInTool
     source:
       openapi: evi-asyncapi.json
-  Context:
+  ChatMessageToolResult:
+    discriminated: false
+    docs: Function call response from client.
+    union:
+      - type: ToolResponseMessage
+      - type: ToolErrorMessage
+    source:
+      openapi: evi-asyncapi.json
+    inline: true
+  ChatMessage:
     properties:
-      type:
-        type: optional<ContextType>
+      content:
+        type: optional<string>
+        docs: Transcript of the message.
+      role:
+        type: Role
+        docs: Role of who is providing the message.
+      tool_call:
+        type: optional<ToolCallMessage>
+        docs: Function call name and arguments.
+      tool_result:
+        type: optional<ChatMessageToolResult>
+        docs: Function call response from client.
+    source:
+      openapi: evi-asyncapi.json
+  ChatMetadata:
+    docs: When provided, the output is a chat metadata message.
+    properties:
+      chat_group_id:
+        type: string
         docs: >-
-          The persistence level of the injected context. Specifies how long the
-          injected context will remain active in the session.
+          ID of the Chat Group.
 
 
-          - **Temporary**: Context that is only applied to the following
-          assistant response.
+          Used to resume a Chat when passed in the
+          [resumed_chat_group_id](/reference/speech-to-speech-evi/chat#request.query.resumed_chat_group_id)
+          query parameter of a subsequent connection request. This allows EVI to
+          continue the conversation from where it left off within the Chat
+          Group.
 
 
-          - **Persistent**: Context that is applied to all subsequent assistant
-          responses for the remainder of the Chat.
+          Learn more about [supporting chat
+          resumability](/docs/speech-to-speech-evi/faq#does-evi-support-chat-resumability)
+          from the EVI FAQ.
+      chat_id:
+        type: string
+        docs: >-
+          ID of the Chat session. Allows the Chat session to be tracked and
+          referenced.
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      request_id:
+        type: optional<string>
+        docs: ID of the initiating request.
+      type:
+        type: literal<"chat_metadata">
+        docs: >-
+          The type of message sent through the socket; for a Chat Metadata
+          message, this must be `chat_metadata`.
+
+
+          The Chat Metadata message is the first message you receive after
+          establishing a connection with EVI and contains important identifiers
+          for the current Chat session.
+    source:
+      openapi: evi-asyncapi.json
+  Context:
+    properties:
       text:
         type: string
         docs: >-
@@ -138,6 +307,19 @@ types:
           remind EVI of its role as a helpful weather assistant, the context you
           insert will be appended to the end of user messages as `{Context: You
           are a helpful weather assistant}`.
+      type:
+        type: optional<ContextType>
+        docs: >-
+          The persistence level of the injected context. Specifies how long the
+          injected context will remain active in the session.
+
+
+          - **Temporary**: Context that is only applied to the following
+          assistant response.
+
+
+          - **Persistent**: Context that is applied to all subsequent assistant
+          responses for the remainder of the Chat.
     source:
       openapi: evi-asyncapi.json
   ContextType:
@@ -146,18 +328,132 @@ types:
       - temporary
     source:
       openapi: evi-asyncapi.json
-  Encoding:
-    type: literal<"linear16">
-  ErrorLevel:
-    type: literal<"warn">
-  PauseAssistantMessage:
-    docs: >-
-      Pause responses from EVI. Chat history is still saved and sent after
-      resuming. 
+  EmotionScores:
     properties:
-      type:
-        type: literal<"pause_assistant_message">
-        docs: >-
+      Admiration: double
+      Adoration: double
+      Aesthetic Appreciation: double
+      Amusement: double
+      Anger: double
+      Anxiety: double
+      Awe: double
+      Awkwardness: double
+      Boredom: double
+      Calmness: double
+      Concentration: double
+      Confusion: double
+      Contemplation: double
+      Contempt: double
+      Contentment: double
+      Craving: double
+      Desire: double
+      Determination: double
+      Disappointment: double
+      Disgust: double
+      Distress: double
+      Doubt: double
+      Ecstasy: double
+      Embarrassment: double
+      Empathic Pain: double
+      Entrancement: double
+      Envy: double
+      Excitement: double
+      Fear: double
+      Guilt: double
+      Horror: double
+      Interest: double
+      Joy: double
+      Love: double
+      Nostalgia: double
+      Pain: double
+      Pride: double
+      Realization: double
+      Relief: double
+      Romance: double
+      Sadness: double
+      Satisfaction: double
+      Shame: double
+      Surprise (negative): double
+      Surprise (positive): double
+      Sympathy: double
+      Tiredness: double
+      Triumph: double
+    source:
+      openapi: evi-asyncapi.json
+  Encoding:
+    type: literal<"linear16">
+  WebSocketError:
+    docs: When provided, the output is an error message.
+    properties:
+      code:
+        type: string
+        docs: Error code. Identifies the type of error encountered.
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      message:
+        type: string
+        docs: Detailed description of the error.
+      request_id:
+        type: optional<string>
+        docs: ID of the initiating request.
+      slug:
+        type: string
+        docs: >-
+          Short, human-readable identifier and description for the error. See a
+          complete list of error slugs on the [Errors
+          page](/docs/resources/errors).
+      type:
+        type: literal<"error">
+        docs: >-
+          The type of message sent through the socket; for a Web Socket Error
+          message, this must be `error`.
+
+
+          This message indicates a disruption in the WebSocket connection, such
+          as an unexpected disconnection, protocol error, or data transmission
+          issue.
+    source:
+      openapi: evi-asyncapi.json
+  ErrorLevel:
+    type: literal<"warn">
+  Inference:
+    properties:
+      prosody:
+        type: optional<ProsodyInference>
+        docs: >-
+          Prosody model inference results.
+
+
+          EVI uses the prosody model to measure 48 emotions related to speech
+          and vocal characteristics within a given expression.
+    source:
+      openapi: evi-asyncapi.json
+  MillisecondInterval:
+    properties:
+      begin:
+        type: integer
+        docs: Start time of the interval in milliseconds.
+      end:
+        type: integer
+        docs: End time of the interval in milliseconds.
+    source:
+      openapi: evi-asyncapi.json
+  PauseAssistantMessage:
+    docs: >-
+      Pause responses from EVI. Chat history is still saved and sent after
+      resuming. 
+    properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      type:
+        type: literal<"pause_assistant_message">
+        docs: >-
           The type of message sent through the socket; must be
           `pause_assistant_message` for our server to correctly identify and
           process it as a Pause Assistant message.
@@ -168,11 +464,24 @@ types:
           message](/reference/speech-to-speech-evi/chat#send.ResumeAssistantMessage)
           is sent. When paused, EVI won't respond, but transcriptions of your
           audio inputs will still be recorded.
-      custom_session_id:
-        type: optional<string>
+    source:
+      openapi: evi-asyncapi.json
+  ProsodyInference:
+    properties:
+      scores:
+        type: EmotionScores
         docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
+          The confidence scores for 48 emotions within the detected expression
+          of an audio sample.
+
+
+          Scores typically range from 0 to 1, with higher values indicating a
+          stronger confidence level in the measured attribute.
+
+
+          See our guide on [interpreting expression measurement
+          results](/docs/expression-measurement/faq#how-do-i-interpret-my-results)
+          to learn more.
     source:
       openapi: evi-asyncapi.json
   ResumeAssistantMessage:
@@ -180,6 +489,11 @@ types:
       Resume responses from EVI. Chat history sent while paused will now be
       sent. 
     properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
       type:
         type: literal<"resume_assistant_message">
         docs: >-
@@ -194,11 +508,15 @@ types:
           then send a `resume_assistant_message`, EVI will respond to the second
           question and have added the first question to its conversation
           context.)
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
+    source:
+      openapi: evi-asyncapi.json
+  Role:
+    enum:
+      - assistant
+      - system
+      - user
+      - all
+      - tool
     source:
       openapi: evi-asyncapi.json
   SessionSettingsVariablesValue:
@@ -213,22 +531,48 @@ types:
   SessionSettings:
     docs: Settings for this chat session.
     properties:
-      type:
-        type: literal<"session_settings">
+      audio:
+        type: optional<AudioConfiguration>
         docs: >-
-          The type of message sent through the socket; must be
-          `session_settings` for our server to correctly identify and process it
-          as a Session Settings message.
+          Configuration details for the audio input used during the session.
+          Ensures the audio is being correctly set up for processing.
 
 
-          Session settings are temporary and apply only to the current Chat
-          session. These settings can be adjusted dynamically based on the
-          requirements of each session to ensure optimal performance and user
-          experience.
+          This optional field is only required when the audio input is encoded
+          in PCM Linear 16 (16-bit, little-endian, signed PCM WAV data). For
+          detailed instructions on how to configure session settings for PCM
+          Linear 16 audio, please refer to the [Session Settings
+          guide](/docs/speech-to-speech-evi/configuration/session-settings).
+      builtin_tools:
+        type: optional<list<BuiltinToolConfig>>
+        docs: >-
+          List of built-in tools to enable for the session.
 
 
-          For more information, please refer to the [Session Settings
-          guide](/docs/speech-to-speech-evi/configuration/session-settings).
+          Tools are resources used by EVI to perform various tasks, such as
+          searching the web or calling external APIs. Built-in tools, like web
+          search, are natively integrated, while user-defined tools are created
+          and invoked by the user. To learn more, see our [Tool Use
+          Guide](/docs/speech-to-speech-evi/features/tool-use).
+
+
+          Currently, the only built-in tool Hume provides is **Web Search**.
+          When enabled, Web Search equips EVI with the ability to search the web
+          for up-to-date information.
+      context:
+        type: optional<Context>
+        docs: >-
+          Field for injecting additional context into the conversation, which is
+          appended to the end of user messages for the session.
+
+
+          When included in a Session Settings message, the provided context can
+          be used to remind the LLM of its role in every user message, prevent
+          it from forgetting important details, or add new relevant information
+          to the conversation.
+
+
+          Set to `null` to clear injected context.
       custom_session_id:
         type: optional<string>
         docs: >-
@@ -247,6 +591,17 @@ types:
           language
           model](/docs/speech-to-speech-evi/guides/custom-language-model) with
           EVI to learn more.
+      language_model_api_key:
+        type: optional<string>
+        docs: >-
+          Third party API key for the supplemental language model.
+
+
+          When provided, EVI will use this key instead of Hume's API key for the
+          supplemental LLM. This allows you to bypass rate limits and utilize
+          your own API key as needed.
+      metadata:
+        type: optional<map<string, unknown>>
       system_prompt:
         type: optional<string>
         docs: >-
@@ -269,70 +624,33 @@ types:
 
           For help writing a system prompt, see our [Prompting
           Guide](/docs/speech-to-speech-evi/guides/prompting).
-      context:
-        type: optional<Context>
+      tools:
+        type: optional<list<Tool>>
         docs: >-
-          Field for injecting additional context into the conversation, which is
-          appended to the end of user messages for the session.
+          List of user-defined tools to enable for the session.
 
 
-          When included in a Session Settings message, the provided context can
-          be used to remind the LLM of its role in every user message, prevent
-          it from forgetting important details, or add new relevant information
-          to the conversation.
+          Tools are resources used by EVI to perform various tasks, such as
+          searching the web or calling external APIs. Built-in tools, like web
+          search, are natively integrated, while user-defined tools are created
+          and invoked by the user. To learn more, see our [Tool Use
+          Guide](/docs/speech-to-speech-evi/features/tool-use).
+      type:
+        type: literal<"session_settings">
+        docs: >-
+          The type of message sent through the socket; must be
+          `session_settings` for our server to correctly identify and process it
+          as a Session Settings message.
 
 
-          Set to `null` to clear injected context.
-      audio:
-        type: optional<AudioConfiguration>
-        docs: >-
-          Configuration details for the audio input used during the session.
-          Ensures the audio is being correctly set up for processing.
+          Session settings are temporary and apply only to the current Chat
+          session. These settings can be adjusted dynamically based on the
+          requirements of each session to ensure optimal performance and user
+          experience.
 
 
-          This optional field is only required when the audio input is encoded
-          in PCM Linear 16 (16-bit, little-endian, signed PCM WAV data). For
-          detailed instructions on how to configure session settings for PCM
-          Linear 16 audio, please refer to the [Session Settings
+          For more information, please refer to the [Session Settings
           guide](/docs/speech-to-speech-evi/configuration/session-settings).
-      language_model_api_key:
-        type: optional<string>
-        docs: >-
-          Third party API key for the supplemental language model.
-
-
-          When provided, EVI will use this key instead of Hume's API key for the
-          supplemental LLM. This allows you to bypass rate limits and utilize
-          your own API key as needed.
-      tools:
-        type: optional<list<Tool>>
-        docs: >-
-          List of user-defined tools to enable for the session.
-
-
-          Tools are resources used by EVI to perform various tasks, such as
-          searching the web or calling external APIs. Built-in tools, like web
-          search, are natively integrated, while user-defined tools are created
-          and invoked by the user. To learn more, see our [Tool Use
-          Guide](/docs/speech-to-speech-evi/features/tool-use).
-      builtin_tools:
-        type: optional<list<BuiltinToolConfig>>
-        docs: >-
-          List of built-in tools to enable for the session.
-
-
-          Tools are resources used by EVI to perform various tasks, such as
-          searching the web or calling external APIs. Built-in tools, like web
-          search, are natively integrated, while user-defined tools are created
-          and invoked by the user. To learn more, see our [Tool Use
-          Guide](/docs/speech-to-speech-evi/features/tool-use).
-
-
-          Currently, the only built-in tool Hume provides is **Web Search**.
-          When enabled, Web Search equips EVI with the ability to search the web
-          for up-to-date information.
-      metadata:
-        type: optional<map<string, unknown>>
       variables:
         type: optional<map<string, SessionSettingsVariablesValue>>
         docs: >-
@@ -360,9 +678,17 @@ types:
       openapi: evi-asyncapi.json
   Tool:
     properties:
-      type:
-        type: ToolType
-        docs: Type of tool. Set to `function` for user-defined tools.
+      description:
+        type: optional<string>
+        docs: >-
+          An optional description of what the tool does, used by the
+          supplemental LLM to choose when and how to call the function.
+      fallback_content:
+        type: optional<string>
+        docs: >-
+          Optional text passed to the supplemental LLM if the tool call fails.
+          The LLM then uses this text to generate a response back to the user,
+          ensuring continuity in the conversation.
       name:
         type: string
         docs: Name of the user-defined tool to be enabled.
@@ -376,43 +702,40 @@ types:
           including the expected data type and description for each input field.
           Structured as a JSON schema, this format ensures the tool receives
           data in the expected format.
-      description:
-        type: optional<string>
-        docs: >-
-          An optional description of what the tool does, used by the
-          supplemental LLM to choose when and how to call the function.
-      fallback_content:
-        type: optional<string>
-        docs: >-
-          Optional text passed to the supplemental LLM if the tool call fails.
-          The LLM then uses this text to generate a response back to the user,
-          ensuring continuity in the conversation.
+      type:
+        type: ToolType
+        docs: Type of tool. Set to `function` for user-defined tools.
     source:
       openapi: evi-asyncapi.json
-  ToolErrorMessage:
-    docs: When provided, the output is a function call error.
+  ToolCallMessage:
+    docs: When provided, the output is a tool call.
     properties:
-      type:
-        type: literal<"tool_error">
-        docs: >-
-          The type of message sent through the socket; for a Tool Error message,
-          this must be `tool_error`.
-
-
-          Upon receiving a [Tool Call
-          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage)
-          and failing to invoke the function, this message is sent to notify EVI
-          of the tool's failure.
       custom_session_id:
         type: optional<string>
         docs: >-
           Used to manage conversational state, correlate frontend and backend
           data, and persist conversations across EVI sessions.
-      tool_type:
-        type: optional<ToolType>
+      name:
+        type: string
+        docs: Name of the tool called.
+      parameters:
+        type: string
         docs: >-
-          Type of tool called. Either `builtin` for natively implemented tools,
-          like web search, or `function` for user-defined tools.
+          Parameters of the tool.
+
+
+          These parameters define the inputs needed for the tool's execution,
+          including the expected data type and description for each input field.
+          Structured as a stringified JSON schema, this format ensures the tool
+          receives data in the expected format.
+      response_required:
+        type: boolean
+        docs: >-
+          Indicates whether a response to the tool call is required from the
+          developer, either in the form of a [Tool Response
+          message](/reference/speech-to-speech-evi/chat#send.ToolResponseMessage)
+          or a [Tool Error
+          message](/reference/speech-to-speech-evi/chat#send.ToolErrorMessage).
       tool_call_id:
         type: string
         docs: >-
@@ -420,48 +743,49 @@ types:
 
 
           This ID is used to track the request and response of a particular tool
-          invocation, ensuring that the Tool Error message is linked to the
-          appropriate tool call request. The specified `tool_call_id` must match
-          the one received in the [Tool Call
-          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage).
+          invocation, ensuring that the correct response is linked to the
+          appropriate request.
+      tool_type:
+        type: optional<ToolType>
+        docs: >-
+          Type of tool called. Either `builtin` for natively implemented tools,
+          like web search, or `function` for user-defined tools.
+      type:
+        type: literal<"tool_call">
+        docs: >-
+          The type of message sent through the socket; for a Tool Call message,
+          this must be `tool_call`.
+
+
+          This message indicates that the supplemental LLM has detected a need
+          to invoke the specified tool.
+    source:
+      openapi: evi-asyncapi.json
+  ToolErrorMessage:
+    docs: When provided, the output is a function call error.
+    properties:
+      code:
+        type: optional<string>
+        docs: Error code. Identifies the type of error encountered.
       content:
         type: optional<string>
         docs: >-
           Optional text passed to the supplemental LLM in place of the tool call
           result. The LLM then uses this text to generate a response back to the
           user, ensuring continuity in the conversation if the tool errors.
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
       error:
         type: string
         docs: Error message from the tool call, not exposed to the LLM or user.
-      code:
-        type: optional<string>
-        docs: Error code. Identifies the type of error encountered.
       level:
         type: optional<ErrorLevel>
         docs: >-
           Indicates the severity of an error; for a Tool Error message, this
           must be `warn` to signal an unexpected event.
-    source:
-      openapi: evi-asyncapi.json
-  ToolResponseMessage:
-    docs: When provided, the output is a function call response.
-    properties:
-      type:
-        type: literal<"tool_response">
-        docs: >-
-          The type of message sent through the socket; for a Tool Response
-          message, this must be `tool_response`.
-
-
-          Upon receiving a [Tool Call
-          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage)
-          and successfully invoking the function, this message is sent to convey
-          the result of the function call back to EVI.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
       tool_call_id:
         type: string
         docs: >-
@@ -469,406 +793,41 @@ types:
 
 
           This ID is used to track the request and response of a particular tool
-          invocation, ensuring that the correct response is linked to the
-          appropriate request. The specified `tool_call_id` must match the one
-          received in the [Tool Call
-          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage.tool_call_id).
-      content:
-        type: string
-        docs: >-
-          Return value of the tool call. Contains the output generated by the
-          tool to pass back to EVI.
-      tool_name:
-        type: optional<string>
-        docs: >-
-          Name of the tool.
-
-
-          Include this optional field to help the supplemental LLM identify
-          which tool generated the response. The specified `tool_name` must
-          match the one received in the [Tool Call
+          invocation, ensuring that the Tool Error message is linked to the
+          appropriate tool call request. The specified `tool_call_id` must match
+          the one received in the [Tool Call
           message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage).
       tool_type:
         type: optional<ToolType>
         docs: >-
           Type of tool called. Either `builtin` for natively implemented tools,
           like web search, or `function` for user-defined tools.
-    source:
-      openapi: evi-asyncapi.json
-  ToolType:
-    enum:
-      - builtin
-      - function
-    source:
-      openapi: evi-asyncapi.json
-  UserInput:
-    docs: >-
-      User text to insert into the conversation. Text sent through a User Input
-      message is treated as the user's speech to EVI. EVI processes this input
-      and provides a corresponding response.
-
-
-      Expression measurement results are not available for User Input messages,
-      as the prosody model relies on audio input and cannot process text alone.
-    properties:
-      type:
-        type: literal<"user_input">
-        docs: >-
-          The type of message sent through the socket; must be `user_input` for
-          our server to correctly identify and process it as a User Input
-          message.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      text:
-        type: string
-        docs: >-
-          User text to insert into the conversation. Text sent through a User
-          Input message is treated as the user's speech to EVI. EVI processes
-          this input and provides a corresponding response.
-
-
-          Expression measurement results are not available for User Input
-          messages, as the prosody model relies on audio input and cannot
-          process text alone.
-    source:
-      openapi: evi-asyncapi.json
-  AssistantEnd:
-    docs: When provided, the output is an assistant end message.
-    properties:
       type:
-        type: literal<"assistant_end">
+        type: literal<"tool_error">
         docs: >-
-          The type of message sent through the socket; for an Assistant End
-          message, this must be `assistant_end`.
+          The type of message sent through the socket; for a Tool Error message,
+          this must be `tool_error`.
 
 
-          This message indicates the conclusion of the assistant's response,
-          signaling that the assistant has finished speaking for the current
-          conversational turn.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-    source:
-      openapi: evi-asyncapi.json
-  AssistantMessage:
-    docs: When provided, the output is an assistant message.
-    properties:
-      type:
-        type: literal<"assistant_message">
-        docs: >-
-          The type of message sent through the socket; for an Assistant Message,
-          this must be `assistant_message`.
-
-
-          This message contains both a transcript of the assistant's response
-          and the expression measurement predictions of the assistant's audio
-          output.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      id:
-        type: optional<string>
-        docs: >-
-          ID of the assistant message. Allows the Assistant Message to be
-          tracked and referenced.
-      message:
-        type: ChatMessage
-        docs: Transcript of the message.
-      models:
-        type: Inference
-        docs: Inference model results.
-      from_text:
-        type: boolean
-        docs: >-
-          Indicates if this message was inserted into the conversation as text
-          from an [Assistant Input
-          message](/reference/speech-to-speech-evi/chat#send.AssistantInput.text).
-    source:
-      openapi: evi-asyncapi.json
-  AssistantProsody:
-    docs: When provided, the output is an Assistant Prosody message.
-    properties:
-      type:
-        type: literal<"assistant_prosody">
-        docs: >-
-          The type of message sent through the socket; for an Assistant Prosody
-          message, this must be `assistant_PROSODY`.
-
-
-          This message the expression measurement predictions of the assistant's
-          audio output.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      models:
-        type: Inference
-        docs: Inference model results.
-      id:
-        type: optional<string>
-        docs: Unique identifier for the segment.
-    source:
-      openapi: evi-asyncapi.json
-  AudioOutput:
-    docs: >-
-      The type of message sent through the socket; for an Audio Output message,
-      this must be `audio_output`.
-    properties:
-      type:
-        type: literal<"audio_output">
-        docs: >-
-          The type of message sent through the socket; for an Audio Output
-          message, this must be `audio_output`.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      id:
-        type: string
-        docs: >-
-          ID of the audio output. Allows the Audio Output message to be tracked
-          and referenced.
-      index:
-        type: integer
-        docs: Index of the chunk of audio relative to the whole audio segment.
-      data:
-        type: string
-        docs: >-
-          Base64 encoded audio output. This encoded audio is transmitted to the
-          client, where it can be decoded and played back as part of the user
-          interaction.
-    source:
-      openapi: evi-asyncapi.json
-  ChatMessageToolResult:
-    discriminated: false
-    docs: Function call response from client.
-    union:
-      - type: ToolResponseMessage
-      - type: ToolErrorMessage
-    source:
-      openapi: evi-asyncapi.json
-    inline: true
-  ChatMessage:
-    properties:
-      role:
-        type: Role
-        docs: Role of who is providing the message.
-      content:
-        type: optional<string>
-        docs: Transcript of the message.
-      tool_call:
-        type: optional<ToolCallMessage>
-        docs: Function call name and arguments.
-      tool_result:
-        type: optional<ChatMessageToolResult>
-        docs: Function call response from client.
-    source:
-      openapi: evi-asyncapi.json
-  ChatMetadata:
-    docs: When provided, the output is a chat metadata message.
-    properties:
-      type:
-        type: literal<"chat_metadata">
-        docs: >-
-          The type of message sent through the socket; for a Chat Metadata
-          message, this must be `chat_metadata`.
-
-
-          The Chat Metadata message is the first message you receive after
-          establishing a connection with EVI and contains important identifiers
-          for the current Chat session.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      chat_group_id:
-        type: string
-        docs: >-
-          ID of the Chat Group.
-
-
-          Used to resume a Chat when passed in the
-          [resumed_chat_group_id](/reference/speech-to-speech-evi/chat#request.query.resumed_chat_group_id)
-          query parameter of a subsequent connection request. This allows EVI to
-          continue the conversation from where it left off within the Chat
-          Group.
-
-
-          Learn more about [supporting chat
-          resumability](/docs/speech-to-speech-evi/faq#does-evi-support-chat-resumability)
-          from the EVI FAQ.
-      chat_id:
-        type: string
-        docs: >-
-          ID of the Chat session. Allows the Chat session to be tracked and
-          referenced.
-      request_id:
-        type: optional<string>
-        docs: ID of the initiating request.
-    source:
-      openapi: evi-asyncapi.json
-  EmotionScores:
-    properties:
-      Admiration: double
-      Adoration: double
-      Aesthetic Appreciation: double
-      Amusement: double
-      Anger: double
-      Anxiety: double
-      Awe: double
-      Awkwardness: double
-      Boredom: double
-      Calmness: double
-      Concentration: double
-      Confusion: double
-      Contemplation: double
-      Contempt: double
-      Contentment: double
-      Craving: double
-      Desire: double
-      Determination: double
-      Disappointment: double
-      Disgust: double
-      Distress: double
-      Doubt: double
-      Ecstasy: double
-      Embarrassment: double
-      Empathic Pain: double
-      Entrancement: double
-      Envy: double
-      Excitement: double
-      Fear: double
-      Guilt: double
-      Horror: double
-      Interest: double
-      Joy: double
-      Love: double
-      Nostalgia: double
-      Pain: double
-      Pride: double
-      Realization: double
-      Relief: double
-      Romance: double
-      Sadness: double
-      Satisfaction: double
-      Shame: double
-      Surprise (negative): double
-      Surprise (positive): double
-      Sympathy: double
-      Tiredness: double
-      Triumph: double
-    source:
-      openapi: evi-asyncapi.json
-  WebSocketError:
-    docs: When provided, the output is an error message.
-    properties:
-      type:
-        type: literal<"error">
-        docs: >-
-          The type of message sent through the socket; for a Web Socket Error
-          message, this must be `error`.
-
-
-          This message indicates a disruption in the WebSocket connection, such
-          as an unexpected disconnection, protocol error, or data transmission
-          issue.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      code:
-        type: string
-        docs: Error code. Identifies the type of error encountered.
-      slug:
-        type: string
-        docs: >-
-          Short, human-readable identifier and description for the error. See a
-          complete list of error slugs on the [Errors
-          page](/docs/resources/errors).
-      message:
-        type: string
-        docs: Detailed description of the error.
-      request_id:
-        type: optional<string>
-        docs: ID of the initiating request.
-    source:
-      openapi: evi-asyncapi.json
-  Inference:
-    properties:
-      prosody:
-        type: optional<ProsodyInference>
-        docs: >-
-          Prosody model inference results.
-
-
-          EVI uses the prosody model to measure 48 emotions related to speech
-          and vocal characteristics within a given expression.
-    source:
-      openapi: evi-asyncapi.json
-  MillisecondInterval:
-    properties:
-      begin:
-        type: integer
-        docs: Start time of the interval in milliseconds.
-      end:
-        type: integer
-        docs: End time of the interval in milliseconds.
-    source:
-      openapi: evi-asyncapi.json
-  ProsodyInference:
-    properties:
-      scores:
-        type: EmotionScores
-        docs: >-
-          The confidence scores for 48 emotions within the detected expression
-          of an audio sample.
-
-
-          Scores typically range from 0 to 1, with higher values indicating a
-          stronger confidence level in the measured attribute.
-
-
-          See our guide on [interpreting expression measurement
-          results](/docs/expression-measurement/faq#how-do-i-interpret-my-results)
-          to learn more.
-    source:
-      openapi: evi-asyncapi.json
-  Role:
-    enum:
-      - assistant
-      - system
-      - user
-      - all
-      - tool
+          Upon receiving a [Tool Call
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage)
+          and failing to invoke the function, this message is sent to notify EVI
+          of the tool's failure.
     source:
       openapi: evi-asyncapi.json
-  ToolCallMessage:
-    docs: When provided, the output is a tool call.
+  ToolResponseMessage:
+    docs: When provided, the output is a function call response.
     properties:
-      name:
-        type: string
-        docs: Name of the tool called.
-      parameters:
+      content:
         type: string
         docs: >-
-          Parameters of the tool.
-
-
-          These parameters define the inputs needed for the tool's execution,
-          including the expected data type and description for each input field.
-          Structured as a stringified JSON schema, this format ensures the tool
-          receives data in the expected format.
+          Return value of the tool call. Contains the output generated by the
+          tool to pass back to EVI.
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
       tool_call_id:
         type: string
         docs: >-
@@ -877,39 +836,88 @@ types:
 
           This ID is used to track the request and response of a particular tool
           invocation, ensuring that the correct response is linked to the
-          appropriate request.
+          appropriate request. The specified `tool_call_id` must match the one
+          received in the [Tool Call
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage.tool_call_id).
+      tool_name:
+        type: optional<string>
+        docs: >-
+          Name of the tool.
+
+
+          Include this optional field to help the supplemental LLM identify
+          which tool generated the response. The specified `tool_name` must
+          match the one received in the [Tool Call
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage).
+      tool_type:
+        type: optional<ToolType>
+        docs: >-
+          Type of tool called. Either `builtin` for natively implemented tools,
+          like web search, or `function` for user-defined tools.
       type:
-        type: literal<"tool_call">
+        type: literal<"tool_response">
         docs: >-
-          The type of message sent through the socket; for a Tool Call message,
-          this must be `tool_call`.
+          The type of message sent through the socket; for a Tool Response
+          message, this must be `tool_response`.
 
 
-          This message indicates that the supplemental LLM has detected a need
-          to invoke the specified tool.
+          Upon receiving a [Tool Call
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage)
+          and successfully invoking the function, this message is sent to convey
+          the result of the function call back to EVI.
+    source:
+      openapi: evi-asyncapi.json
+  ToolType:
+    enum:
+      - builtin
+      - function
+    source:
+      openapi: evi-asyncapi.json
+  UserInput:
+    docs: >-
+      User text to insert into the conversation. Text sent through a User Input
+      message is treated as the user's speech to EVI. EVI processes this input
+      and provides a corresponding response.
+
+
+      Expression measurement results are not available for User Input messages,
+      as the prosody model relies on audio input and cannot process text alone.
+    properties:
       custom_session_id:
         type: optional<string>
         docs: >-
           Used to manage conversational state, correlate frontend and backend
           data, and persist conversations across EVI sessions.
-      tool_type:
-        type: optional<ToolType>
+      text:
+        type: string
         docs: >-
-          Type of tool called. Either `builtin` for natively implemented tools,
-          like web search, or `function` for user-defined tools.
-      response_required:
-        type: boolean
+          User text to insert into the conversation. Text sent through a User
+          Input message is treated as the user's speech to EVI. EVI processes
+          this input and provides a corresponding response.
+
+
+          Expression measurement results are not available for User Input
+          messages, as the prosody model relies on audio input and cannot
+          process text alone.
+      type:
+        type: literal<"user_input">
         docs: >-
-          Indicates whether a response to the tool call is required from the
-          developer, either in the form of a [Tool Response
-          message](/reference/speech-to-speech-evi/chat#send.ToolResponseMessage)
-          or a [Tool Error
-          message](/reference/speech-to-speech-evi/chat#send.ToolErrorMessage).
+          The type of message sent through the socket; must be `user_input` for
+          our server to correctly identify and process it as a User Input
+          message.
     source:
       openapi: evi-asyncapi.json
   UserInterruption:
     docs: When provided, the output is an interruption.
     properties:
+      custom_session_id:
+        type: optional<string>
+        docs: >-
+          Used to manage conversational state, correlate frontend and backend
+          data, and persist conversations across EVI sessions.
+      time:
+        type: integer
+        docs: Unix timestamp of the detected user interruption.
       type:
         type: literal<"user_interruption">
         docs: >-
@@ -922,46 +930,16 @@ types:
           message to signal the interruption event. This message allows the
           system to stop the current audio playback, clear the audio queue, and
           prepare to handle new user input.
-      custom_session_id:
-        type: optional<string>
-        docs: >-
-          Used to manage conversational state, correlate frontend and backend
-          data, and persist conversations across EVI sessions.
-      time:
-        type: integer
-        docs: Unix timestamp of the detected user interruption.
     source:
       openapi: evi-asyncapi.json
   UserMessage:
     docs: When provided, the output is a user message.
     properties:
-      type:
-        type: literal<"user_message">
-        docs: >-
-          The type of message sent through the socket; for a User Message, this
-          must be `user_message`.
-
-
-          This message contains both a transcript of the user's input and the
-          expression measurement predictions if the input was sent as an [Audio
-          Input message](/reference/speech-to-speech-evi/chat#send.AudioInput).
-          Expression measurement predictions are not provided for a [User Input
-          message](/reference/speech-to-speech-evi/chat#send.UserInput), as the
-          prosody model relies on audio input and cannot process text alone.
       custom_session_id:
         type: optional<string>
         docs: >-
           Used to manage conversational state, correlate frontend and backend
           data, and persist conversations across EVI sessions.
-      message:
-        type: ChatMessage
-        docs: Transcript of the message.
-      models:
-        type: Inference
-        docs: Inference model results.
-      time:
-        type: MillisecondInterval
-        docs: Start and End time of user message.
       from_text:
         type: boolean
         docs: >-
@@ -986,6 +964,28 @@ types:
           Interim transcripts are only sent when the
           [`verbose_transcription`](/reference/speech-to-speech-evi/chat#request.query.verbose_transcription)
           query parameter is set to `true` in the initial handshake.
+      message:
+        type: ChatMessage
+        docs: Transcript of the message.
+      models:
+        type: Inference
+        docs: Inference model results.
+      time:
+        type: MillisecondInterval
+        docs: Start and End time of user message.
+      type:
+        type: literal<"user_message">
+        docs: >-
+          The type of message sent through the socket; for a User Message, this
+          must be `user_message`.
+
+
+          This message contains both a transcript of the user's input and the
+          expression measurement predictions if the input was sent as an [Audio
+          Input message](/reference/speech-to-speech-evi/chat#send.AudioInput).
+          Expression measurement predictions are not provided for a [User Input
+          message](/reference/speech-to-speech-evi/chat#send.UserInput), as the
+          prosody model relies on audio input and cannot process text alone.
     source:
       openapi: evi-asyncapi.json
   JsonMessage:
@@ -1075,6 +1075,18 @@ types:
         name: Gpt5Mini
       - value: gpt-5-nano
         name: Gpt5Nano
+      - value: gpt-4o-priority
+        name: Gpt4OPriority
+      - value: gpt-4o-mini-priority
+        name: Gpt4OMiniPriority
+      - value: gpt-4.1-priority
+        name: Gpt41Priority
+      - value: gpt-5-priority
+        name: Gpt5Priority
+      - value: gpt-5-mini-priority
+        name: Gpt5MiniPriority
+      - value: gpt-5-nano-priority
+        name: Gpt5NanoPriority
       - value: gemma-7b-it
         name: Gemma7BIt
       - value: llama3-8b-8192
@@ -1165,20 +1177,29 @@ types:
         docs: Model provider associated with this Voice Name.
     source:
       openapi: evi-openapi.json
+  WebhookEventBase:
+    docs: Represents the fields common to all webhook events.
+    properties:
+      chat_group_id:
+        type: string
+        docs: Unique ID of the **Chat Group** associated with the **Chat** session.
+      chat_id:
+        type: string
+        docs: Unique ID of the **Chat** session.
+      config_id:
+        type: optional<string>
+        docs: Unique ID of the EVI **Config** used for the session.
+    source:
+      openapi: evi-openapi.json
+  WebhookEvent:
+    discriminated: false
+    union:
+      - WebhookEventChatStarted
+      - WebhookEventChatEnded
+    source:
+      openapi: evi-openapi.json
   WebhookEventChatEnded:
     properties:
-      event_name:
-        type: optional<literal<"chat_ended">>
-        docs: Always `chat_ended`.
-      end_time:
-        type: integer
-        docs: Unix timestamp (in milliseconds) indicating when the session ended.
-      duration_seconds:
-        type: integer
-        docs: Total duration of the session in seconds.
-      end_reason:
-        type: WebhookEventChatStatus
-        docs: Reason for the session's termination.
       caller_number:
         type: optional<string>
         docs: >-
@@ -1193,6 +1214,18 @@ types:
           language
           model](/docs/empathic-voice-interface-evi/custom-language-model) in
           the EVI Config.
+      duration_seconds:
+        type: integer
+        docs: Total duration of the session in seconds.
+      end_reason:
+        type: WebhookEventChatStatus
+        docs: Reason for the session's termination.
+      end_time:
+        type: integer
+        docs: Unix timestamp (in milliseconds) indicating when the session ended.
+      event_name:
+        type: optional<literal<"chat_ended">>
+        docs: Always `chat_ended`.
     extends:
       - WebhookEventBase
     source:
@@ -1205,18 +1238,6 @@ types:
       openapi: evi-openapi.json
   WebhookEventChatStarted:
     properties:
-      event_name:
-        type: optional<literal<"chat_started">>
-        docs: Always `chat_started`.
-      start_time:
-        type: integer
-        docs: Unix timestamp (in milliseconds) indicating when the session started.
-      chat_start_type:
-        type: WebhookEventChatStartType
-        docs: >-
-          Indicates whether the chat is the first in a new Chat Group
-          (`new_chat_group`) or the continuation of an existing chat group
-          (`resumed_chat_group`).
       caller_number:
         type: optional<string>
         docs: >-
@@ -1224,6 +1245,12 @@ types:
           This field is included only if the Chat was created via the [Twilio
           phone calling](/docs/empathic-voice-interface-evi/phone-calling)
           integration.
+      chat_start_type:
+        type: WebhookEventChatStartType
+        docs: >-
+          Indicates whether the chat is the first in a new Chat Group
+          (`new_chat_group`) or the continuation of an existing chat group
+          (`resumed_chat_group`).
       custom_session_id:
         type: optional<string>
         docs: >-
@@ -1231,6 +1258,12 @@ types:
           language
           model](/docs/empathic-voice-interface-evi/custom-language-model) in
           the EVI Config.
+      event_name:
+        type: optional<literal<"chat_started">>
+        docs: Always `chat_started`.
+      start_time:
+        type: integer
+        docs: Unix timestamp (in milliseconds) indicating when the session started.
     extends:
       - WebhookEventBase
     source:
@@ -1246,27 +1279,6 @@ types:
       - ERROR
     source:
       openapi: evi-openapi.json
-  WebhookEvent:
-    discriminated: false
-    union:
-      - WebhookEventChatStarted
-      - WebhookEventChatEnded
-    source:
-      openapi: evi-openapi.json
-  WebhookEventBase:
-    docs: Represents the fields common to all webhook events.
-    properties:
-      chat_group_id:
-        type: string
-        docs: Unique ID of the **Chat Group** associated with the **Chat** session.
-      chat_id:
-        type: string
-        docs: Unique ID of the **Chat** session.
-      config_id:
-        type: optional<string>
-        docs: Unique ID of the EVI **Config** used for the session.
-    source:
-      openapi: evi-openapi.json
   ErrorResponse:
     properties:
       error: optional<string>
@@ -1531,12 +1543,12 @@ types:
           Version numbers are integer values representing different iterations
           of the Config. Each update to the Config increments its version
           number.
-      version_description:
-        type: optional<string>
-        docs: An optional description of the Config version.
       tools:
         type: optional<list<optional<ReturnUserDefinedTool>>>
         docs: List of user-defined tools associated with this Config.
+      version_description:
+        type: optional<string>
+        docs: An optional description of the Config version.
       language_model:
         type: optional<ReturnLanguageModel>
         docs: >-