hume 0.13.3 → 0.13.4

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

@@ -32,7 +32,7 @@ types:
           inflections and tones to the text based on the user's expressions and
           the context of the conversation. The synthesized audio is streamed
           back to the user as an [Assistant
-          Message](/reference/empathic-voice-interface-evi/chat/chat#receive.AssistantMessage.type).
+          Message](/reference/speech-to-speech-evi/chat#receive.AssistantMessage).
     source:
       openapi: evi-asyncapi.json
   AudioConfiguration:
@@ -165,7 +165,7 @@ types:
 
           Once this message is sent, EVI will not respond until a [Resume
           Assistant
-          message](/reference/empathic-voice-interface-evi/chat/chat#send.ResumeAssistantMessage.type)
+          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:
@@ -228,7 +228,7 @@ types:
 
 
           For more information, please refer to the [Session Settings
-          guide](/docs/empathic-voice-interface-evi/configuration/session-settings).
+          guide](/docs/speech-to-speech-evi/configuration/session-settings).
       custom_session_id:
         type: optional<string>
         docs: >-
@@ -245,8 +245,8 @@ types:
           It is recommended to pass a `custom_session_id` if you are using a
           Custom Language Model. Please see our guide to [using a custom
           language
-          model](/docs/empathic-voice-interface-evi/guides/custom-language-model)
-          with EVI to learn more.
+          model](/docs/speech-to-speech-evi/guides/custom-language-model) with
+          EVI to learn more.
       system_prompt:
         type: optional<string>
         docs: >-
@@ -268,7 +268,7 @@ types:
 
 
           For help writing a system prompt, see our [Prompting
-          Guide](/docs/empathic-voice-interface-evi/guides/prompting).
+          Guide](/docs/speech-to-speech-evi/guides/prompting).
       context:
         type: optional<Context>
         docs: >-
@@ -294,7 +294,7 @@ types:
           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/empathic-voice-interface-evi/configuration/session-settings).
+          guide](/docs/speech-to-speech-evi/configuration/session-settings).
       language_model_api_key:
         type: optional<string>
         docs: >-
@@ -314,7 +314,7 @@ types:
           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/empathic-voice-interface-evi/features/tool-use).
+          Guide](/docs/speech-to-speech-evi/features/tool-use).
       builtin_tools:
         type: optional<list<BuiltinToolConfig>>
         docs: >-
@@ -325,7 +325,7 @@ types:
           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/empathic-voice-interface-evi/features/tool-use).
+          Guide](/docs/speech-to-speech-evi/features/tool-use).
 
 
           Currently, the only built-in tool Hume provides is **Web Search**.
@@ -350,7 +350,7 @@ types:
           Using this field, you can personalize responses based on
           session-specific details. For more guidance, see our [guide on using
           dynamic
-          variables](/docs/empathic-voice-interface-evi/features/dynamic-variables).
+          variables](/docs/speech-to-speech-evi/features/dynamic-variables).
     source:
       openapi: evi-asyncapi.json
   Tool:
@@ -395,7 +395,7 @@ types:
 
 
           Upon receiving a [Tool Call
-          message](/reference/empathic-voice-interface-evi/chat/chat#receive.ToolCallMessage.type)
+          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:
@@ -418,7 +418,7 @@ types:
           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/empathic-voice-interface-evi/chat/chat#receive.ToolCallMessage.type).
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage).
       content:
         type: optional<string>
         docs: >-
@@ -449,7 +449,7 @@ types:
 
 
           Upon receiving a [Tool Call
-          message](/reference/empathic-voice-interface-evi/chat/chat#receive.ToolCallMessage.type)
+          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:
@@ -467,7 +467,7 @@ types:
           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/empathic-voice-interface-evi/chat/chat#receive.ToolCallMessage.tool_call_id).
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage.tool_call_id).
       content:
         type: string
         docs: >-
@@ -482,7 +482,7 @@ types:
           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/empathic-voice-interface-evi/chat/chat#receive.ToolCallMessage.type).
+          message](/reference/speech-to-speech-evi/chat#receive.ToolCallMessage).
       tool_type:
         type: optional<ToolType>
         docs: >-
@@ -584,7 +584,7 @@ types:
         docs: >-
           Indicates if this message was inserted into the conversation as text
           from an [Assistant Input
-          message](/reference/empathic-voice-interface-evi/chat/chat#send.AssistantInput.text).
+          message](/reference/speech-to-speech-evi/chat#send.AssistantInput.text).
     source:
       openapi: evi-asyncapi.json
   AssistantProsody:
@@ -693,14 +693,14 @@ types:
 
 
           Used to resume a Chat when passed in the
-          [resumed_chat_group_id](/reference/empathic-voice-interface-evi/chat/chat#request.query.resumed_chat_group_id)
+          [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/empathic-voice-interface-evi/faq#does-evi-support-chat-resumability)
+          resumability](/docs/speech-to-speech-evi/faq#does-evi-support-chat-resumability)
           from the EVI FAQ.
       chat_id:
         type: string
@@ -897,9 +897,9 @@ types:
         docs: >-
           Indicates whether a response to the tool call is required from the
           developer, either in the form of a [Tool Response
-          message](/reference/empathic-voice-interface-evi/chat/chat#send.ToolResponseMessage.type)
+          message](/reference/speech-to-speech-evi/chat#send.ToolResponseMessage)
           or a [Tool Error
-          message](/reference/empathic-voice-interface-evi/chat/chat#send.ToolErrorMessage.type).
+          message](/reference/speech-to-speech-evi/chat#send.ToolErrorMessage).
     source:
       openapi: evi-asyncapi.json
   UserInterruption:
@@ -939,12 +939,10 @@ types:
 
           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/empathic-voice-interface-evi/chat/chat#send.AudioInput.type).
+          Input message](/reference/speech-to-speech-evi/chat#send.AudioInput).
           Expression measurement predictions are not provided for a [User Input
-          message](/reference/empathic-voice-interface-evi/chat/chat#send.UserInput.type),
-          as the prosody model relies on audio input and cannot process text
-          alone.
+          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: >-
@@ -964,7 +962,7 @@ types:
         docs: >-
           Indicates if this message was inserted into the conversation as text
           from a [User
-          Input](/reference/empathic-voice-interface-evi/chat/chat#send.UserInput.text)
+          Input](/reference/speech-to-speech-evi/chat#send.UserInput.text)
           message.
       interim:
         type: boolean
@@ -981,7 +979,7 @@ types:
 
 
           Interim transcripts are only sent when the
-          [`verbose_transcription`](/reference/empathic-voice-interface-evi/chat/chat#request.query.verbose_transcription)
+          [`verbose_transcription`](/reference/speech-to-speech-evi/chat#request.query.verbose_transcription)
           query parameter is set to `true` in the initial handshake.
     source:
       openapi: evi-asyncapi.json

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

@@ -13,11 +13,11 @@ channel:
         Include this ID in your connection request to equip EVI with the Prompt,
         Language Model, Voice, and Tools associated with the specified
         configuration. If omitted, EVI will apply [default configuration
-        settings](/docs/empathic-voice-interface-evi/configuration/build-a-configuration#default-configuration).
+        settings](/docs/speech-to-speech-evi/configuration/build-a-configuration#default-configuration).
 
 
         For help obtaining this ID, see our [Configuration
-        Guide](/docs/empathic-voice-interface-evi/configuration).
+        Guide](/docs/speech-to-speech-evi/configuration).
     config_version:
       type: optional<integer>
       docs: >-
@@ -57,7 +57,7 @@ channel:
 
 
         - [Chat
-        Metadata](/reference/empathic-voice-interface-evi/chat/chat#receive.ChatMetadata.type):
+        Metadata](/reference/speech-to-speech-evi/chat#receive.ChatMetadata):
         Upon establishing a WebSocket connection with EVI, the user receives a
         Chat Metadata message. This message contains a `chat_group_id`, which
         can be used to resume conversations within this chat group in future
@@ -65,14 +65,14 @@ channel:
 
 
         - [List Chats
-        endpoint](/reference/empathic-voice-interface-evi/chats/list-chats): Use
-        the GET `/v0/evi/chats` endpoint to obtain the Chat Group ID of
-        individual Chat sessions. This endpoint lists all available Chat
-        sessions and their associated Chat Group ID.
+        endpoint](/reference/speech-to-speech-evi/chats/list-chats): Use the GET
+        `/v0/evi/chats` endpoint to obtain the Chat Group ID of individual Chat
+        sessions. This endpoint lists all available Chat sessions and their
+        associated Chat Group ID.
 
 
         - [List Chat Groups
-        endpoint](/reference/empathic-voice-interface-evi/chat-groups/list-chat-groups):
+        endpoint](/reference/speech-to-speech-evi/chat-groups/list-chat-groups):
         Use the GET `/v0/evi/chat_groups` endpoint to obtain the Chat Group IDs
         of all Chat Groups associated with an API key. This endpoint returns a
         list of all available chat groups.
@@ -89,9 +89,9 @@ channel:
         A flag to enable verbose transcription. Set this query parameter to
         `true` to have unfinalized user transcripts be sent to the client as
         interim UserMessage messages. The
-        [interim](/reference/empathic-voice-interface-evi/chat/chat#receive.UserMessage.interim)
+        [interim](/reference/speech-to-speech-evi/chat#receive.UserMessage.interim)
         field on a
-        [UserMessage](/reference/empathic-voice-interface-evi/chat/chat#receive.UserMessage.type)
+        [UserMessage](/reference/speech-to-speech-evi/chat#receive.UserMessage)
         denotes whether the message is "interim" or "final."
     event_limit:
       type: optional<integer>

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

@@ -140,17 +140,7 @@ service:
           properties:
             evi_version:
               type: string
-              docs: >-
-                Specifies the EVI version to use. See our [EVI Version 
-                Guide](/docs/speech-to-speech-evi/configuration/evi-version) for
-                differences between versions.
-
-
-                **We're officially sunsetting EVI versions 1 and 2 on August 30,
-                2025**. To keep things running smoothly, be sure to [migrate to
-                EVI
-                3](/docs/speech-to-speech-evi/configuration/evi-version#migrating-to-evi-3)
-                before then.
+              docs: EVI version to use. Only version `3` is supported.
             name:
               type: string
               docs: Name applied to all versions of a particular Config.

package/.mock/definition/tts/__package__.yml

@@ -189,6 +189,175 @@ service:
   source:
     openapi: tts-openapi.json
 types:
+  PublishTts:
+    docs: Input message type for the TTS stream.
+    properties:
+      text:
+        type: optional<string>
+        docs: The input text to be converted to speech output.
+        default: ''
+        validation:
+          maxLength: 5000
+      description:
+        type: optional<string>
+        docs: >-
+          Natural language instructions describing how the text should be spoken
+          by the model (e.g., `"a soft, gentle voice with a strong British
+          accent"`).
+        validation:
+          maxLength: 1000
+      voice:
+        type: optional<PostedUtteranceVoice>
+        docs: >-
+          The name or ID of the voice from the `Voice Library` to be used as the
+          speaker for this and all subsequent utterances, until the `"voice"`
+          field is updated again.
+      speed:
+        type: optional<double>
+        docs: A relative measure of how fast this utterance should be spoken.
+        default: 1
+        validation:
+          min: 0.25
+          max: 3
+      trailing_silence:
+        type: optional<double>
+        docs: Duration of trailing silence (in seconds) to add to this utterance
+        default: 0
+        validation:
+          min: 0
+          max: 5
+      flush:
+        type: optional<boolean>
+        docs: >-
+          Force the generation of audio regardless of how much text has been
+          supplied.
+        default: false
+      close:
+        type: optional<boolean>
+        docs: Force the generation of audio and close the stream.
+        default: false
+    source:
+      openapi: tts-asyncapi.json
+  PostedUtteranceVoiceWithId:
+    properties:
+      id:
+        type: string
+        docs: The unique ID associated with the **Voice**.
+      provider:
+        type: optional<VoiceProvider>
+        docs: >-
+          Specifies the source provider associated with the chosen voice.
+
+
+          - **`HUME_AI`**: Select voices from Hume's [Voice
+          Library](https://platform.hume.ai/tts/voice-library), containing a
+          variety of preset, shared voices.
+
+          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
+          and saved in your account. 
+
+
+          If no provider is explicitly set, the default provider is
+          `CUSTOM_VOICE`. When using voices from Hume's **Voice Library**, you
+          must explicitly set the provider to `HUME_AI`.
+
+
+          Preset voices from Hume's **Voice Library** are accessible by all
+          users. In contrast, your custom voices are private and accessible only
+          via requests authenticated with your API key.
+    source:
+      openapi: tts-openapi.json
+  PostedUtteranceVoiceWithName:
+    properties:
+      name:
+        type: string
+        docs: The name of a **Voice**.
+      provider:
+        type: optional<VoiceProvider>
+        docs: >-
+          Specifies the source provider associated with the chosen voice.
+
+
+          - **`HUME_AI`**: Select voices from Hume's [Voice
+          Library](https://platform.hume.ai/tts/voice-library), containing a
+          variety of preset, shared voices.
+
+          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
+          and saved in your account. 
+
+
+          If no provider is explicitly set, the default provider is
+          `CUSTOM_VOICE`. When using voices from Hume's **Voice Library**, you
+          must explicitly set the provider to `HUME_AI`.
+
+
+          Preset voices from Hume's **Voice Library** are accessible by all
+          users. In contrast, your custom voices are private and accessible only
+          via requests authenticated with your API key.
+    source:
+      openapi: tts-openapi.json
+  VoiceProvider:
+    enum:
+      - HUME_AI
+      - CUSTOM_VOICE
+    source:
+      openapi: tts-openapi.json
+  PostedUtteranceVoice:
+    discriminated: false
+    union:
+      - type: PostedUtteranceVoiceWithId
+      - type: PostedUtteranceVoiceWithName
+    source:
+      openapi: tts-openapi.json
+  AudioFormatType:
+    enum:
+      - mp3
+      - pcm
+      - wav
+    source:
+      openapi: tts-openapi.json
+  SnippetAudioChunk:
+    properties:
+      generation_id:
+        type: string
+        docs: >-
+          The generation ID of the parent snippet that this chunk corresponds
+          to.
+      snippet_id:
+        type: string
+        docs: The ID of the parent snippet that this chunk corresponds to.
+      text:
+        type: string
+        docs: The text of the parent snippet that this chunk corresponds to.
+      transcribed_text:
+        type: optional<string>
+        docs: >-
+          The transcribed text of the generated audio of the parent snippet that
+          this chunk corresponds to. It is only present if `instant_mode` is set
+          to `false`.
+      chunk_index:
+        type: integer
+        docs: The index of the audio chunk in the snippet.
+      audio:
+        type: string
+        docs: The generated audio output chunk in the requested format.
+      audio_format:
+        type: AudioFormatType
+        docs: The generated audio output format.
+      is_last_chunk:
+        type: boolean
+        docs: >-
+          Whether or not this is the last chunk streamed back from the decoder
+          for one input snippet.
+      utterance_index:
+        type: optional<integer>
+        docs: >-
+          The index of the utterance in the request that the parent snippet of
+          this chunk corresponds to.
+      snippet:
+        type: optional<Snippet>
+    source:
+      openapi: tts-openapi.json
   PostedContextWithGenerationId:
     properties:
       generation_id:
@@ -220,13 +389,6 @@ types:
           is `48000 Hz`.
     source:
       openapi: tts-openapi.json
-  AudioFormatType:
-    enum:
-      - mp3
-      - pcm
-      - wav
-    source:
-      openapi: tts-openapi.json
   ReturnGeneration:
     properties:
       generation_id:
@@ -435,48 +597,6 @@ types:
           base64 string.
     source:
       openapi: tts-openapi.json
-  SnippetAudioChunk:
-    properties:
-      generation_id:
-        type: string
-        docs: >-
-          The generation ID of the parent snippet that this chunk corresponds
-          to.
-      snippet_id:
-        type: string
-        docs: The ID of the parent snippet that this chunk corresponds to.
-      text:
-        type: string
-        docs: The text of the parent snippet that this chunk corresponds to.
-      transcribed_text:
-        type: optional<string>
-        docs: >-
-          The transcribed text of the generated audio of the parent snippet that
-          this chunk corresponds to. It is only present if `instant_mode` is set
-          to `false`.
-      chunk_index:
-        type: integer
-        docs: The index of the audio chunk in the snippet.
-      audio:
-        type: string
-        docs: The generated audio output chunk in the requested format.
-      audio_format:
-        type: AudioFormatType
-        docs: The generated audio output format.
-      is_last_chunk:
-        type: boolean
-        docs: >-
-          Whether or not this is the last chunk streamed back from the decoder
-          for one input snippet.
-      utterance_index:
-        type: optional<integer>
-        docs: >-
-          The index of the utterance in the request that the parent snippet of
-          this chunk corresponds to.
-      snippet:
-        type: Snippet
-    source:
-      openapi: tts-openapi.json
   PostedUtterance:
     properties:
       text:
@@ -547,77 +667,6 @@ types:
       type: string
     source:
       openapi: tts-openapi.json
-  PostedUtteranceVoiceWithId:
-    properties:
-      id:
-        type: string
-        docs: The unique ID associated with the **Voice**.
-      provider:
-        type: optional<VoiceProvider>
-        docs: >-
-          Specifies the source provider associated with the chosen voice.
-
-
-          - **`HUME_AI`**: Select voices from Hume's [Voice
-          Library](https://platform.hume.ai/tts/voice-library), containing a
-          variety of preset, shared voices.
-
-          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
-          and saved in your account. 
-
-
-          If no provider is explicitly set, the default provider is
-          `CUSTOM_VOICE`. When using voices from Hume's **Voice Library**, you
-          must explicitly set the provider to `HUME_AI`.
-
-
-          Preset voices from Hume's **Voice Library** are accessible by all
-          users. In contrast, your custom voices are private and accessible only
-          via requests authenticated with your API key.
-    source:
-      openapi: tts-openapi.json
-  PostedUtteranceVoiceWithName:
-    properties:
-      name:
-        type: string
-        docs: The name of a **Voice**.
-      provider:
-        type: optional<VoiceProvider>
-        docs: >-
-          Specifies the source provider associated with the chosen voice.
-
-
-          - **`HUME_AI`**: Select voices from Hume's [Voice
-          Library](https://platform.hume.ai/tts/voice-library), containing a
-          variety of preset, shared voices.
-
-          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
-          and saved in your account. 
-
-
-          If no provider is explicitly set, the default provider is
-          `CUSTOM_VOICE`. When using voices from Hume's **Voice Library**, you
-          must explicitly set the provider to `HUME_AI`.
-
-
-          Preset voices from Hume's **Voice Library** are accessible by all
-          users. In contrast, your custom voices are private and accessible only
-          via requests authenticated with your API key.
-    source:
-      openapi: tts-openapi.json
-  VoiceProvider:
-    enum:
-      - HUME_AI
-      - CUSTOM_VOICE
-    source:
-      openapi: tts-openapi.json
-  PostedUtteranceVoice:
-    discriminated: false
-    union:
-      - type: PostedUtteranceVoiceWithId
-      - type: PostedUtteranceVoiceWithName
-    source:
-      openapi: tts-openapi.json
   FormatWav:
     properties: {}
     source:

package/.mock/definition/tts/streamInput.yml

@@ -0,0 +1,56 @@
+imports:
+  root: __package__.yml
+channel:
+  path: /stream/input
+  url: prod
+  auth: false
+  docs: Generate emotionally expressive speech.
+  query-parameters:
+    context_generation_id:
+      type: optional<string>
+      docs: >-
+        The ID of a prior TTS generation to use as context for generating
+        consistent speech style and prosody across multiple requests. Including
+        context may increase audio generation times.
+    format_type: root.AudioFormatType
+    strip_headers:
+      type: optional<boolean>
+      default: false
+      docs: >-
+        If enabled, the audio for all the chunks of a generation, once
+        concatenated together, will constitute a single audio file. Otherwise,
+        if disabled, each chunk's audio will be its own audio file, each with
+        its own headers (if applicable).
+    instant_mode:
+      type: optional<boolean>
+      default: true
+      docs: >-
+        Accelerates processing to reduce streaming latency.Incurs approximately
+        10% additional cost while preserving full voice quality.
+    no_binary:
+      type: optional<boolean>
+      default: false
+      docs: If enabled, no binary websocket messages will be sent to the client.
+  messages:
+    publish:
+      origin: client
+      body:
+        type: root.PublishTts
+    subscribe:
+      origin: server
+      body:
+        type: root.SnippetAudioChunk
+  examples:
+    - messages:
+        - type: publish
+          body: {}
+        - type: subscribe
+          body:
+            request_id: request_id
+            generation_id: generation_id
+            snippet_id: snippet_id
+            text: text
+            chunk_index: 1
+            audio: audio
+            audio_format: mp3
+            is_last_chunk: true

package/.mock/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization" : "hume",
-  "version" : "0.65.42"
+  "version" : "0.66.15"
 }

package/api/resources/empathicVoice/resources/configs/client/requests/PostedConfig.d.ts

@@ -37,11 +37,7 @@ import * as Hume from "../../../../../../index";
  *     }
  */
 export interface PostedConfig {
-    /**
-     * Specifies the EVI version to use. See our [EVI Version  Guide](/docs/speech-to-speech-evi/configuration/evi-version) for differences between versions.
-     *
-     * **We're officially sunsetting EVI versions 1 and 2 on August 30, 2025**. To keep things running smoothly, be sure to [migrate to EVI 3](/docs/speech-to-speech-evi/configuration/evi-version#migrating-to-evi-3) before then.
-     */
+    /** EVI version to use. Only version `3` is supported. */
     eviVersion: string;
     /** Name applied to all versions of a particular Config. */
     name: string;

package/api/resources/empathicVoice/types/AssistantInput.d.ts

@@ -12,7 +12,7 @@ export interface AssistantInput {
     /**
      * Assistant text to synthesize into spoken audio and insert into the conversation.
      *
-     * EVI uses this text to generate spoken audio using our proprietary expressive text-to-speech model. Our model adds appropriate emotional inflections and tones to the text based on the user's expressions and the context of the conversation. The synthesized audio is streamed back to the user as an [Assistant Message](/reference/empathic-voice-interface-evi/chat/chat#receive.AssistantMessage.type).
+     * EVI uses this text to generate spoken audio using our proprietary expressive text-to-speech model. Our model adds appropriate emotional inflections and tones to the text based on the user's expressions and 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).
      */
     text: string;
 }