hume 0.13.8 → 0.14.1

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

@@ -1027,6 +1027,8 @@ types:
         name: Claude3Haiku20240307
       - value: claude-sonnet-4-20250514
         name: ClaudeSonnet420250514
+      - value: claude-sonnet-4-5-20250929
+        name: ClaudeSonnet4520250929
       - value: us.anthropic.claude-3-5-haiku-20241022-v1:0
         name: UsAnthropicClaude35Haiku20241022V10
       - value: us.anthropic.claude-3-5-sonnet-20240620-v1:0
@@ -1119,6 +1121,8 @@ types:
         name: Llama4Maverick17B128EInstruct
       - value: Qwen3-32B
         name: Qwen332B
+      - value: grok-4-fast-non-reasoning-latest
+        name: Grok4FastNonReasoningLatest
       - ellm
       - value: custom-language-model
         name: CustomLanguageModel
@@ -1470,9 +1474,6 @@ types:
           Version numbers are integer values representing different iterations
           of the Prompt. Each update to the Prompt increments its version
           number.
-      version_description:
-        type: optional<string>
-        docs: An optional description of the Prompt version.
       version_type:
         type: ReturnPromptVersionType
         docs: >-
@@ -1488,6 +1489,9 @@ types:
         docs: >-
           Time at which the Prompt was last modified. Measured in seconds since
           the Unix epoch.
+      version_description:
+        type: optional<string>
+        docs: An optional description of the Prompt version.
     source:
       openapi: evi-openapi.json
   ReturnPagedConfigs:
@@ -1543,12 +1547,6 @@ types:
           Version numbers are integer values representing different iterations
           of the Config. Each update to the Config increments its version
           number.
-      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: >-
@@ -1603,6 +1601,12 @@ types:
         docs: >-
           Time at which the Config was last modified. Measured in seconds since
           the Unix epoch.
+      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.
     source:
       openapi: evi-openapi.json
   ReturnPagedChatsPaginationDirection:

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

@@ -98,6 +98,111 @@ channel:
         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.
+    session_settings[audio][channels]:
+      type: optional<integer>
+      docs: Sets number of audio channels for audio input.
+    session_settings[audio][encoding]:
+      type: optional<string>
+      docs: Sets encoding format of the audio input, such as `linear16`.
+    session_settings[audio][sample_rate]:
+      type: optional<integer>
+      docs: >-
+        Sets the sample rate for audio input. (Number of samples per second in
+        the audio input, measured in Hertz.)
+    session_settings[context][text]:
+      type: optional<string>
+      docs: >-
+        The context to be injected into the conversation. Helps inform the LLM's
+        response by providing relevant information about the ongoing
+        conversation.
+
+
+        This text will be appended to the end of
+        [user_messages](/reference/speech-to-speech-evi/chat#receive.UserMessage.message.content)
+        based on the chosen persistence level. For example, if you want to
+        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}`.
+    session_settings[context][type]:
+      type: optional<string>
+      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.
+    session_settings[custom_session_id]:
+      type: optional<string>
+      docs: >-
+        Used to manage conversational state, correlate frontend and backend
+        data, and persist conversations across EVI sessions.
+    session_settings[event_limit]:
+      type: optional<integer>
+      docs: >-
+        The maximum number of chat events to return from chat history. By
+        default, the system returns up to 300 events (100 events per page × 3
+        pages). Set this parameter to a smaller value to limit the number of
+        events returned.
+    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.
+    session_settings[system_prompt]:
+      type: optional<string>
+      docs: >-
+        Instructions used to shape EVI's behavior, responses, and style for the
+        session.
+
+
+        When included in a Session Settings message, the provided Prompt
+        overrides the existing one specified in the EVI configuration. If no
+        Prompt was defined in the configuration, this Prompt will be the one
+        used for the session.
+
+
+        You can use the Prompt to define a specific goal or role for EVI,
+        specifying how it should act or what it should focus on during the
+        conversation. For example, EVI can be instructed to act as a customer
+        support representative, a fitness coach, or a travel advisor, each with
+        its own set of behaviors and response styles.
+
+
+        For help writing a system prompt, see our [Prompting
+        Guide](/docs/speech-to-speech-evi/guides/prompting).
+    session_settings[variables]:
+      type: optional<string>
+      docs: >-
+        This field allows you to assign values to dynamic variables referenced
+        in your system prompt.
+
+
+        Each key represents the variable name, and the corresponding value is
+        the specific content you wish to assign to that variable within the
+        session. While the values for variables can be strings, numbers, or
+        booleans, the value will ultimately be converted to a string when
+        injected into your system prompt.
+
+
+        Using this field, you can personalize responses based on
+        session-specific details. For more guidance, see our [guide on using
+        dynamic
+        variables](/docs/speech-to-speech-evi/features/dynamic-variables).
+    session_settings[voice_id]:
+      type: optional<string>
+      docs: >-
+        The name or ID of the voice from the `Voice Library` to be used as the
+        speaker for this EVI session. This will override the speaker set in the
+        selected configuration.
     verbose_transcription:
       type: optional<boolean>
       default: false

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

@@ -140,7 +140,9 @@ service:
           properties:
             evi_version:
               type: string
-              docs: EVI version to use. Only version `3` is supported.
+              docs: >-
+                EVI version to use. Only versions `3` and `4-mini` are
+                supported.
             name:
               type: string
               docs: Name applied to all versions of a particular Config.

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

@@ -30,7 +30,7 @@ service:
         format.
       source:
         openapi: tts-openapi.json
-      display-name: Text-to-speech (Json)
+      display-name: Text-to-Speech (Json)
       request:
         body:
           type: PostedTts
@@ -79,6 +79,7 @@ service:
                           Beauty is no quality in things themselves: It exists
                           merely in the mind which contemplates them.
                         utterance_index: 0
+                        timestamps: []
               request_id: 66e01f90-4501-4aa0-bbaf-74f45dc15aa725906
     synthesize-file:
       path: /v0/tts/file
@@ -94,7 +95,7 @@ service:
         The response contains the generated audio file in the requested format.
       source:
         openapi: tts-openapi.json
-      display-name: Text-to-speech (File)
+      display-name: Text-to-Speech (File)
       request:
         body:
           type: PostedTts
@@ -131,7 +132,7 @@ service:
         prosody.
       source:
         openapi: tts-openapi.json
-      display-name: Text-to-speech (Streamed File)
+      display-name: Text-to-Speech (Streamed File)
       request:
         body:
           type: PostedTts
@@ -166,14 +167,14 @@ service:
         base64.
       source:
         openapi: tts-openapi.json
-      display-name: Text-to-speech (Streamed JSON)
+      display-name: Text-to-Speech (Streamed JSON)
       request:
         body:
           type: PostedTts
         content-type: application/json
       response-stream:
         docs: Successful Response
-        type: SnippetAudioChunk
+        type: TtsOutput
         format: json
       errors:
         - UnprocessableEntityError
@@ -189,15 +190,30 @@ service:
   source:
     openapi: tts-openapi.json
 types:
+  TtsOutput:
+    discriminant: type
+    base-properties: {}
+    union:
+      timestamp:
+        type: TimestampMessage
+      audio:
+        type: SnippetAudioChunk
+    source:
+      openapi: tts-openapi.json
+  AudioFormatType:
+    enum:
+      - mp3
+      - pcm
+      - wav
+    source:
+      openapi: tts-openapi.json
   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
+      close:
+        type: optional<boolean>
+        docs: Force the generation of audio and close the stream.
+        default: false
       description:
         type: optional<string>
         docs: >-
@@ -206,12 +222,12 @@ types:
           accent"`).
         validation:
           maxLength: 1000
-      voice:
-        type: optional<PostedUtteranceVoice>
+      flush:
+        type: optional<boolean>
         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.
+          Force the generation of audio regardless of how much text has been
+          supplied.
+        default: false
       speed:
         type: optional<double>
         docs: A relative measure of how fast this utterance should be spoken.
@@ -219,6 +235,12 @@ types:
         validation:
           min: 0.25
           max: 3
+      text:
+        type: optional<string>
+        docs: The input text to be converted to speech output.
+        default: ''
+        validation:
+          maxLength: 5000
       trailing_silence:
         type: optional<double>
         docs: Duration of trailing silence (in seconds) to add to this utterance
@@ -226,18 +248,104 @@ types:
         validation:
           min: 0
           max: 5
-      flush:
-        type: optional<boolean>
+      voice:
+        type: optional<PostedUtteranceVoice>
         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
+          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.
     source:
       openapi: tts-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: tts-openapi.json
+  TimestampMessage:
+    docs: A word or phoneme level timestamp for the generated audio.
+    properties:
+      generation_id:
+        type: string
+        docs: >-
+          The generation ID of the parent snippet that this chunk corresponds
+          to.
+      request_id:
+        type: string
+        docs: ID of the initiating request.
+      snippet_id:
+        type: string
+        docs: The ID of the parent snippet that this chunk corresponds to.
+      timestamp:
+        type: Timestamp
+        docs: A word or phoneme level timestamp for the generated audio.
+    source:
+      openapi: tts-openapi.json
+  SnippetAudioChunk:
+    docs: Metadata for a chunk of generated audio.
+    properties:
+      audio:
+        type: string
+        docs: The generated audio output chunk in the requested format.
+      audio_format:
+        type: AudioFormatType
+        docs: The generated audio output format.
+      chunk_index:
+        type: integer
+        docs: The index of the audio chunk in the snippet.
+      generation_id:
+        type: string
+        docs: >-
+          The generation ID of the parent snippet that this chunk corresponds
+          to.
+      is_last_chunk:
+        type: boolean
+        docs: >-
+          Whether or not this is the last chunk streamed back from the decoder
+          for one input snippet.
+      request_id:
+        type: string
+        docs: ID of the initiating request.
+      snippet:
+        type: optional<Snippet>
+      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`.
+      utterance_index:
+        type: optional<integer>
+        docs: >-
+          The index of the utterance in the request that the parent snippet of
+          this chunk corresponds to.
+    source:
+      openapi: tts-openapi.json
+  Timestamp:
+    properties:
+      text: string
+      time:
+        type: MillisecondInterval
+      type:
+        type: TimestampType
+    source:
+      openapi: tts-openapi.json
+  TimestampType:
+    enum:
+      - word
+      - phoneme
+    source:
+      openapi: tts-openapi.json
   PostedUtteranceVoiceWithId:
     properties:
       id:
@@ -309,59 +417,12 @@ types:
       - type: PostedUtteranceVoiceWithName
     source:
       openapi: tts-openapi.json
-  AudioFormatType:
+  OctaveVersion:
     enum:
-      - mp3
-      - pcm
-      - wav
-    source:
-      openapi: tts-openapi.json
-  SnippetAudioChunk:
-    docs: Metadata for a chunk of generated audio.
-    properties:
-      audio:
-        type: string
-        docs: The generated audio output chunk in the requested format.
-      audio_format:
-        type: AudioFormatType
-        docs: The generated audio output format.
-      chunk_index:
-        type: integer
-        docs: The index of the audio chunk in the snippet.
-      generation_id:
-        type: string
-        docs: >-
-          The generation ID of the parent snippet that this chunk corresponds
-          to.
-      is_last_chunk:
-        type: boolean
-        docs: >-
-          Whether or not this is the last chunk streamed back from the decoder
-          for one input snippet.
-      request_id:
-        type: string
-        docs: ID of the initiating request.
-      snippet:
-        type: optional<Snippet>
-      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`.
-      type:
-        type: optional<literal<"audio">>
-      utterance_index:
-        type: optional<integer>
-        docs: >-
-          The index of the utterance in the request that the parent snippet of
-          this chunk corresponds to.
+      - value: '1'
+        name: One
+      - value: '2'
+        name: Two
     source:
       openapi: tts-openapi.json
   PostedContextWithGenerationId:
@@ -471,6 +532,9 @@ types:
       format:
         type: optional<Format>
         docs: Specifies the output audio file format.
+      include_timestamp_types:
+        type: optional<list<TimestampType>>
+        docs: The set of timestamp types to include in the response.
       num_generations:
         type: optional<integer>
         docs: Number of generations of the audio to produce.
@@ -520,6 +584,9 @@ types:
         type: list<PostedUtterance>
       version:
         type: optional<OctaveVersion>
+        docs: >-
+          The version of the Octave Model to use. 1 for the legacy model, 2 for
+          the new model.
       instant_mode:
         type: optional<boolean>
         docs: >-
@@ -556,7 +623,6 @@ types:
           troubleshooting assistance.
     source:
       openapi: tts-openapi.json
-  OctaveVersion: string
   ReturnVoice:
     docs: An Octave voice available for text-to-speech
     properties:
@@ -596,6 +662,9 @@ types:
       text:
         type: string
         docs: The text for this **Snippet**.
+      timestamps:
+        docs: A list of word or phoneme level timestamps for the generated audio.
+        type: list<Timestamp>
       transcribed_text:
         type: optional<string>
         docs: >-

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

@@ -6,6 +6,21 @@ channel:
   auth: false
   docs: Generate emotionally expressive speech.
   query-parameters:
+    access_token:
+      type: optional<string>
+      default: ''
+      docs: >-
+        Access token used for authenticating the client. If not provided, an
+        `api_key` must be provided to authenticate.
+
+
+        The access token is generated using both an API key and a Secret key,
+        which provides an additional layer of security compared to using just an
+        API key.
+
+
+        For more details, refer to the [Authentication Strategies
+        Guide](/docs/introduction/api-key#authentication-strategies).
     context_generation_id:
       type: optional<string>
       docs: >-
@@ -13,14 +28,10 @@ channel:
         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).
+    include_timestamp_types:
+      type: optional<root.TimestampType>
+      allow-multiple: true
+      docs: The set of timestamp types to include in the response.
     instant_mode:
       type: optional<boolean>
       default: true
@@ -34,21 +45,15 @@ channel:
       type: optional<boolean>
       default: false
       docs: If enabled, no binary websocket messages will be sent to the client.
-    access_token:
-      type: optional<string>
-      default: ''
+    strip_headers:
+      type: optional<boolean>
+      default: false
       docs: >-
-        Access token used for authenticating the client. If not provided, an
-        `api_key` must be provided to authenticate.
-
-
-        The access token is generated using both an API key and a Secret key,
-        which provides an additional layer of security compared to using just an
-        API key.
-
-
-        For more details, refer to the [Authentication Strategies
-        Guide](/docs/introduction/api-key#authentication-strategies).
+        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).
+    version: root.OctaveVersion
     api_key:
       type: optional<string>
       default: ''
@@ -64,21 +69,7 @@ channel:
       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/api/resources/empathicVoice/resources/chat/client/Client.d.ts

@@ -2,6 +2,7 @@
 import * as environments from "../../../../../../environments";
 import * as core from "../../../../../../core";
 import { ChatSocket } from "./Socket";
+import { SessionSettings } from "../../../types/SessionSettings";
 export declare function createHostnameWithProtocol(environment: string): string;
 export declare namespace Chat {
     interface Options {
@@ -24,6 +25,9 @@ export declare namespace Chat {
         verboseTranscription?: boolean;
         /** ID of the Voice to use for this chat. If specified, will override the voice set in the Config */
         voiceId?: string;
+        sessionSettings?: Pick<SessionSettings, Exclude<keyof SessionSettings, "builtinTools" | "type" | "metadata" | "tools">> & {
+            eventLimit?: number;
+        };
         /** Extra query parameters sent at WebSocket connection */
         queryParams?: Record<string, string | string[] | object | object[]>;
     }