hume 0.12.1 → 0.13.0

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

@@ -4,21 +4,6 @@ channel:
   auth: false
   docs: Chat with Empathic Voice Interface (EVI)
   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).
     config_id:
       type: optional<string>
       docs: >-
@@ -47,13 +32,6 @@ channel:
 
         Include this parameter to apply a specific version of an EVI
         configuration. If omitted, the latest version will be applied.
-    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.
     resumed_chat_group_id:
       type: optional<string>
       docs: >-
@@ -98,6 +76,12 @@ 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.
+    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
@@ -109,6 +93,28 @@ channel:
         field on a
         [UserMessage](/reference/empathic-voice-interface-evi/chat/chat#receive.UserMessage.type)
         denotes whether the message is "interim" or "final."
+    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.
+    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).
     api_key:
       type: optional<string>
       default: ''
@@ -130,8 +136,8 @@ channel:
     - messages:
         - type: publish
           body:
-            data: data
             type: audio_input
+            data: data
         - type: subscribe
           body:
             type: assistant_end

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

@@ -12,10 +12,10 @@ webhooks:
           chat_group_id: 9fc18597-3567-42d5-94d6-935bde84bf2f
           chat_id: 470a49f6-1dec-4afe-8b61-035d3b2d63b0
           config_id: 1b60e1a0-cc59-424a-8d2c-189d354db3f3
+          event_name: chat_ended
+          end_time: 1716244958546
           duration_seconds: 180
           end_reason: USER_ENDED
-          end_time: 1716244958546
-          event_name: chat_ended
     docs: Sent when an EVI chat ends.
   chatStarted:
     audiences: []
@@ -28,7 +28,7 @@ webhooks:
           chat_group_id: 9fc18597-3567-42d5-94d6-935bde84bf2f
           chat_id: 470a49f6-1dec-4afe-8b61-035d3b2d63b0
           config_id: 1b60e1a0-cc59-424a-8d2c-189d354db3f3
-          chat_start_type: new_chat_group
           event_name: chat_started
           start_time: 1716244940648
+          chat_start_type: new_chat_group
     docs: Sent when an EVI chat is started.

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

@@ -141,10 +141,16 @@ service:
             evi_version:
               type: string
               docs: >-
-                Specifies the EVI version to use. Use `"1"` for version 1, or
-                `"2"` for the latest enhanced version. For a detailed comparison
-                of the two versions, refer to our
-                [guide](/docs/speech-to-speech-evi/configuration/evi-version).
+                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.
             name:
               type: string
               docs: Name applied to all versions of a particular Config.

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

@@ -34,23 +34,6 @@ service:
       request:
         body:
           type: PostedTts
-        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).
-        name: SynthesizeJsonRequest
         content-type: application/json
       response:
         docs: Successful Response
@@ -137,26 +120,30 @@ service:
             format:
               type: mp3
             num_generations: 1
-    synthesize-file-streaming:
-      path: /v0/tts/stream/file
+    synthesize-json-streaming:
+      path: /v0/tts/stream/json
       method: POST
       auth: true
       docs: >-
         Streams synthesized speech using the specified voice. If no voice is
         provided, a novel voice will be generated dynamically. Optionally,
         additional context can be included to influence the speech's style and
-        prosody.
+        prosody. 
+
+
+        The response is a stream of JSON objects including audio encoded in
+        base64.
       source:
         openapi: tts-openapi.yml
-      display-name: Text-to-speech (Streamed File)
+      display-name: Text-to-speech (Streamed JSON)
       request:
         body:
           type: PostedTts
         content-type: application/json
-      response:
-        docs: OK
-        type: file
-        status-code: 200
+      response-stream:
+        docs: Successful Response
+        type: SnippetAudioChunk
+        format: json
       errors:
         - UnprocessableEntityError
       examples:
@@ -168,30 +155,26 @@ service:
                 voice:
                   name: Male English Actor
                   provider: HUME_AI
-    synthesize-json-streaming:
-      path: /v0/tts/stream/json
+    synthesize-file-streaming:
+      path: /v0/tts/stream/file
       method: POST
       auth: true
       docs: >-
         Streams synthesized speech using the specified voice. If no voice is
         provided, a novel voice will be generated dynamically. Optionally,
         additional context can be included to influence the speech's style and
-        prosody. 
-
-
-        The response is a stream of JSON objects including audio encoded in
-        base64.
+        prosody.
       source:
         openapi: tts-openapi.yml
-      display-name: Text-to-speech (Streamed JSON)
+      display-name: Text-to-speech (Streamed File)
       request:
         body:
           type: PostedTts
         content-type: application/json
-      response-stream:
-        docs: Successful Response
-        type: SnippetAudioChunk
-        format: json
+      response:
+        docs: OK
+        type: file
+        status-code: 200
       errors:
         - UnprocessableEntityError
       examples:
@@ -246,25 +229,25 @@ types:
       openapi: tts-openapi.yml
   ReturnGeneration:
     properties:
-      audio:
+      generation_id:
         type: string
         docs: >-
-          The generated audio output in the requested format, encoded as a
-          base64 string.
+          A unique ID associated with this TTS generation that can be used as
+          context for generating consistent speech style and prosody across
+          multiple requests.
       duration:
         type: double
         docs: Duration of the generated audio in seconds.
-      encoding:
-        type: AudioEncoding
       file_size:
         type: integer
         docs: Size of the generated audio in bytes.
-      generation_id:
+      encoding:
+        type: AudioEncoding
+      audio:
         type: string
         docs: >-
-          A unique ID associated with this TTS generation that can be used as
-          context for generating consistent speech style and prosody across
-          multiple requests.
+          The generated audio output in the requested format, encoded as a
+          base64 string.
       snippets:
         docs: >-
           A list of snippet groups where each group corresponds to an utterance
@@ -317,9 +300,18 @@ types:
           Utterances to use as context for generating consistent speech style
           and prosody across multiple requests. These will not be converted to
           speech output.
-      format:
-        type: optional<Format>
-        docs: Specifies the output audio file format.
+      utterances:
+        docs: >-
+          A list of **Utterances** to be converted to speech output.
+
+
+          An **Utterance** is a unit of input for
+          [Octave](/docs/text-to-speech-tts/overview), and includes input
+          `text`, an optional `description` to serve as the prompt for how the
+          speech should be delivered, an optional `voice` specification, and
+          additional controls to guide delivery for `speed` and
+          `trailing_silence`.
+        type: list<PostedUtterance>
       num_generations:
         type: optional<integer>
         docs: Number of generations of the audio to produce.
@@ -327,6 +319,9 @@ types:
         validation:
           min: 1
           max: 5
+      format:
+        type: optional<Format>
+        docs: Specifies the output audio file format.
       split_utterances:
         type: optional<boolean>
         docs: >-
@@ -355,18 +350,6 @@ types:
           if disabled, each chunk's audio will be its own audio file, each with
           its own headers (if applicable).
         default: false
-      utterances:
-        docs: >-
-          A list of **Utterances** to be converted to speech output.
-
-
-          An **Utterance** is a unit of input for
-          [Octave](/docs/text-to-speech-tts/overview), and includes input
-          `text`, an optional `description` to serve as the prompt for how the
-          speech should be delivered, an optional `voice` specification, and
-          additional controls to guide delivery for `speed` and
-          `trailing_silence`.
-        type: list<PostedUtterance>
       instant_mode:
         type: optional<boolean>
         docs: >-
@@ -393,14 +376,14 @@ types:
       openapi: tts-openapi.yml
   ReturnTts:
     properties:
-      generations:
-        type: list<ReturnGeneration>
       request_id:
         type: optional<string>
         docs: >-
           A unique ID associated with this request for tracking and
           troubleshooting. Use this ID when contacting [support](/support) for
           troubleshooting assistance.
+      generations:
+        type: list<ReturnGeneration>
     source:
       openapi: tts-openapi.yml
   ReturnVoice:
@@ -428,69 +411,41 @@ types:
       openapi: tts-openapi.yml
   Snippet:
     properties:
-      audio:
-        type: string
-        docs: >-
-          The segmented audio output in the requested format, encoded as a
-          base64 string.
-      generation_id:
-        type: string
-        docs: The generation ID this snippet corresponds to.
       id:
         type: string
         docs: A unique ID associated with this **Snippet**.
       text:
         type: string
         docs: The text for this **Snippet**.
+      generation_id:
+        type: string
+        docs: The generation ID this snippet corresponds to.
+      utterance_index:
+        type: optional<integer>
+        docs: The index of the utterance in the request this snippet corresponds to.
       transcribed_text:
         type: optional<string>
         docs: >-
           The transcribed text of the generated audio. 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 this snippet corresponds to.
-    source:
-      openapi: tts-openapi.yml
-  SnippetAudioChunk:
-    properties:
       audio:
         type: string
-        docs: The generated audio output chunk in the requested 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.
-      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.
+          The segmented audio output in the requested format, encoded as a
+          base64 string.
+    source:
+      openapi: tts-openapi.yml
+  SnippetAudioChunk:
+    properties: {}
     source:
       openapi: tts-openapi.yml
   PostedUtterance:
     properties:
+      text:
+        type: string
+        docs: The input text to be synthesized into speech.
+        validation:
+          maxLength: 5000
       description:
         type: optional<string>
         docs: >-
@@ -512,33 +467,30 @@ types:
           guide](/docs/text-to-speech-tts/prompting) for design tips.
         validation:
           maxLength: 1000
+      voice:
+        type: optional<PostedUtteranceVoice>
+        docs: >-
+          The `name` or `id` associated with a **Voice** from the **Voice
+          Library** to be used as the speaker for this and all subsequent
+          `utterances`, until the `voice` field is updated again.
+
+           See our [voices guide](/docs/text-to-speech-tts/voices) for more details on generating and specifying **Voices**.
       speed:
         type: optional<double>
-        docs: Speed multiplier for the synthesized speech.
+        docs: >-
+          Speed multiplier for the synthesized speech. Extreme values below 0.75
+          and above 1.5 may sometimes cause instability to the generated output.
         default: 1
         validation:
-          min: 0.25
-          max: 3
-      text:
-        type: string
-        docs: The input text to be synthesized into speech.
-        validation:
-          maxLength: 5000
+          min: 0.5
+          max: 2
       trailing_silence:
         type: optional<double>
         docs: Duration of trailing silence (in seconds) to add to this utterance
-        default: 0.35
+        default: 0
         validation:
           min: 0
           max: 5
-      voice:
-        type: optional<PostedUtteranceVoice>
-        docs: >-
-          The `name` or `id` associated with a **Voice** from the **Voice
-          Library** to be used as the speaker for this and all subsequent
-          `utterances`, until the `voice` field is updated again.
-
-           See our [voices guide](/docs/text-to-speech-tts/voices) for more details on generating and specifying **Voices**.
     source:
       openapi: tts-openapi.yml
   ValidationErrorLocItem:

package/.mock/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization" : "hume",
-  "version" : "0.64.10"
+  "version" : "0.65.42"
 }

package/api/resources/empathicVoice/resources/chatGroups/client/index.d.ts

@@ -1 +1,2 @@
+export {};
 export * from "./requests";

package/api/resources/empathicVoice/resources/chats/client/index.d.ts

@@ -1 +1,2 @@
+export {};
 export * from "./requests";

package/api/resources/empathicVoice/resources/configs/client/index.d.ts

@@ -1 +1,2 @@
+export {};
 export * from "./requests";

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

@@ -37,7 +37,11 @@ import * as Hume from "../../../../../../index";
  *     }
  */
 export interface PostedConfig {
-    /** Specifies the EVI version to use. Use `"1"` for version 1, or `"2"` for the latest enhanced version. For a detailed comparison of the two versions, refer to our [guide](/docs/speech-to-speech-evi/configuration/evi-version). */
+    /**
+     * 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.
+     */
     eviVersion: string;
     /** Name applied to all versions of a particular Config. */
     name: string;

package/api/resources/empathicVoice/resources/prompts/client/index.d.ts

@@ -1 +1,2 @@
+export {};
 export * from "./requests";

package/api/resources/empathicVoice/resources/tools/client/index.d.ts

@@ -1 +1,2 @@
+export {};
 export * from "./requests";

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

@@ -5,12 +5,12 @@
  * When provided, the output is an assistant end message.
  */
 export interface AssistantEnd {
-    /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
-    customSessionId?: string;
     /**
      * 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.
      */
     type: "assistant_end";
+    /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
+    customSessionId?: string;
 }

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

@@ -5,6 +5,8 @@
  * When provided, the input is spoken by EVI.
  */
 export interface AssistantInput {
+    /** 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. */
+    type: "assistant_input";
     /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
     customSessionId?: string;
     /**
@@ -13,6 +15,4 @@ export interface AssistantInput {
      * 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).
      */
     text: string;
-    /** 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. */
-    type: "assistant_input";
 }

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

@@ -6,20 +6,20 @@ import * as Hume from "../../../index";
  * When provided, the output is an assistant message.
  */
 export interface AssistantMessage {
+    /**
+     * 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.
+     */
+    type: "assistant_message";
     /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
     customSessionId?: string;
-    /** 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). */
-    fromText: boolean;
     /** ID of the assistant message. Allows the Assistant Message to be tracked and referenced. */
     id?: string;
     /** Transcript of the message. */
     message: Hume.empathicVoice.ChatMessage;
     /** Inference model results. */
     models: Hume.empathicVoice.Inference;
-    /**
-     * 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.
-     */
-    type: "assistant_message";
+    /** 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). */
+    fromText: boolean;
 }

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

@@ -6,16 +6,16 @@ import * as Hume from "../../../index";
  * When provided, the output is an Assistant Prosody message.
  */
 export interface AssistantProsody {
-    /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
-    customSessionId?: string;
-    /** Unique identifier for the segment. */
-    id?: string;
-    /** Inference model results. */
-    models: Hume.empathicVoice.Inference;
     /**
      * 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.
      */
     type: "assistant_prosody";
+    /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
+    customSessionId?: string;
+    /** Inference model results. */
+    models: Hume.empathicVoice.Inference;
+    /** Unique identifier for the segment. */
+    id?: string;
 }

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

@@ -3,10 +3,10 @@
  */
 import * as Hume from "../../../index";
 export interface AudioConfiguration {
-    /** Number of audio channels. */
-    channels: number;
     /** Encoding format of the audio input, such as `linear16`. */
     encoding: Hume.empathicVoice.Encoding;
+    /** Number of audio channels. */
+    channels: number;
     /** Audio sample rate. Number of samples per second in the audio input, measured in Hertz. */
     sampleRate: number;
 }

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

@@ -5,6 +5,12 @@
  * When provided, the input is audio.
  */
 export interface AudioInput {
+    /**
+     * 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.
+     */
+    type: "audio_input";
     /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
     customSessionId?: string;
     /**
@@ -17,10 +23,4 @@ export interface AudioInput {
      * Hume recommends streaming audio with a buffer window of 20 milliseconds (ms), or 100 milliseconds (ms) for web applications.
      */
     data: string;
-    /**
-     * 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.
-     */
-    type: "audio_input";
 }

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

@@ -5,14 +5,14 @@
  * The type of message sent through the socket; for an Audio Output message, this must be `audio_output`.
  */
 export interface AudioOutput {
+    /** The type of message sent through the socket; for an Audio Output message, this must be `audio_output`. */
+    type: "audio_output";
     /** Used to manage conversational state, correlate frontend and backend data, and persist conversations across EVI sessions. */
     customSessionId?: string;
-    /** 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. */
-    data: string;
     /** ID of the audio output. Allows the Audio Output message to be tracked and referenced. */
     id: string;
     /** Index of the chunk of audio relative to the whole audio segment. */
     index: number;
-    /** The type of message sent through the socket; for an Audio Output message, this must be `audio_output`. */
-    type: "audio_output";
+    /** 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. */
+    data: string;
 }

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

@@ -3,7 +3,7 @@
  */
 import * as Hume from "../../../index";
 export interface BuiltinToolConfig {
+    name: Hume.empathicVoice.BuiltInTool;
     /** 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. */
     fallbackContent?: string;
-    name: Hume.empathicVoice.BuiltInTool;
 }