hume 0.9.17 → 0.9.18

package/.mock/definition/expression-measurement/stream/stream.yml

@@ -7,14 +7,14 @@ channel:
       type: string
       name: humeApiKey
   messages:
+    subscribe:
+      origin: server
+      body: SubscribeEvent
     publish:
       origin: client
       body:
         type: StreamModelsEndpointPayload
         docs: Models endpoint payload
-    subscribe:
-      origin: server
-      body: SubscribeEvent
   examples:
     - messages:
         - type: publish
@@ -22,209 +22,6 @@ channel:
         - type: subscribe
           body: {}
 types:
-  StreamFace:
-    docs: >
-      Configuration for the facial expression emotion model.
-
-
-      Note: Using the `reset_stream` parameter does not have any effect on face
-      identification. A single face identifier cache is maintained over a full
-      session whether `reset_stream` is used or not.
-    properties:
-      facs:
-        type: optional<map<string, unknown>>
-        docs: >-
-          Configuration for FACS predictions. If missing or null, no FACS
-          predictions will be generated.
-      descriptions:
-        type: optional<map<string, unknown>>
-        docs: >-
-          Configuration for Descriptions predictions. If missing or null, no
-          Descriptions predictions will be generated.
-      identify_faces:
-        type: optional<boolean>
-        docs: >
-          Whether to return identifiers for faces across frames. If true, unique
-          identifiers will be assigned to face bounding boxes to differentiate
-          different faces. If false, all faces will be tagged with an "unknown"
-          ID.
-        default: false
-      fps_pred:
-        type: optional<double>
-        docs: >
-          Number of frames per second to process. Other frames will be omitted
-          from the response.
-        default: 3
-      prob_threshold:
-        type: optional<double>
-        docs: >
-          Face detection probability threshold. Faces detected with a
-          probability less than this threshold will be omitted from the
-          response.
-        default: 3
-      min_face_size:
-        type: optional<double>
-        docs: >
-          Minimum bounding box side length in pixels to treat as a face. Faces
-          detected with a bounding box side length in pixels less than this
-          threshold will be omitted from the response.
-        default: 3
-    source:
-      openapi: streaming-asyncapi.yml
-    inline: true
-  StreamLanguage:
-    docs: Configuration for the language emotion model.
-    properties:
-      sentiment:
-        type: optional<map<string, unknown>>
-        docs: >-
-          Configuration for sentiment predictions. If missing or null, no
-          sentiment predictions will be generated.
-      toxicity:
-        type: optional<map<string, unknown>>
-        docs: >-
-          Configuration for toxicity predictions. If missing or null, no
-          toxicity predictions will be generated.
-      granularity:
-        type: optional<string>
-        docs: >-
-          The granularity at which to generate predictions. Values are `word`,
-          `sentence`, `utterance`, or `passage`. To get a single prediction for
-          the entire text of your streaming payload use `passage`. Default value
-          is `word`.
-    source:
-      openapi: streaming-asyncapi.yml
-    inline: true
-  Config:
-    docs: >
-      Configuration used to specify which models should be used and with what
-      settings.
-    properties:
-      burst:
-        type: optional<map<string, unknown>>
-        docs: |
-          Configuration for the vocal burst emotion model.
-
-          Note: Model configuration is not currently available in streaming.
-
-          Please use the default configuration by passing an empty object `{}`.
-      face:
-        type: optional<StreamFace>
-        docs: >
-          Configuration for the facial expression emotion model.
-
-
-          Note: Using the `reset_stream` parameter does not have any effect on
-          face identification. A single face identifier cache is maintained over
-          a full session whether `reset_stream` is used or not.
-      facemesh:
-        type: optional<map<string, unknown>>
-        docs: |
-          Configuration for the facemesh emotion model.
-
-          Note: Model configuration is not currently available in streaming.
-
-          Please use the default configuration by passing an empty object `{}`.
-      language:
-        type: optional<StreamLanguage>
-        docs: Configuration for the language emotion model.
-      prosody:
-        type: optional<map<string, unknown>>
-        docs: |
-          Configuration for the speech prosody emotion model.
-
-          Note: Model configuration is not currently available in streaming.
-
-          Please use the default configuration by passing an empty object `{}`.
-    source:
-      openapi: streaming-asyncapi.yml
-    inline: true
-  StreamModelsEndpointPayload:
-    docs: Models endpoint payload
-    properties:
-      data:
-        type: optional<string>
-      models:
-        type: optional<Config>
-        docs: >
-          Configuration used to specify which models should be used and with
-          what settings.
-      stream_window_ms:
-        type: optional<double>
-        docs: >
-          Length in milliseconds of streaming sliding window.
-
-
-          Extending the length of this window will prepend media context from
-          past payloads into the current payload.
-
-
-          For example, if on the first payload you send 500ms of data and on the
-          second payload you send an additional 500ms of data, a window of at
-          least 1000ms will allow the model to process all 1000ms of stream
-          data.
-
-
-          A window of 600ms would append the full 500ms of the second payload to
-          the last 100ms of the first payload.
-
-
-          Note: This feature is currently only supported for audio data and
-          audio models. For other file types and models this parameter will be
-          ignored.
-        default: 5000
-        validation:
-          min: 500
-          max: 10000
-      reset_stream:
-        type: optional<boolean>
-        docs: >
-          Whether to reset the streaming sliding window before processing the
-          current payload.
-
-
-          If this parameter is set to `true` then past context will be deleted
-          before processing the current payload.
-
-
-          Use reset_stream when one audio file is done being processed and you
-          do not want context to leak across files.
-        default: false
-      raw_text:
-        type: optional<boolean>
-        docs: >
-          Set to `true` to enable the data parameter to be parsed as raw text
-          rather than base64 encoded bytes.
-
-          This parameter is useful if you want to send text to be processed by
-          the language model, but it cannot be used with other file types like
-          audio, image, or video.
-        default: false
-      job_details:
-        type: optional<boolean>
-        docs: >
-          Set to `true` to get details about the job.
-
-
-          This parameter can be set in the same payload as data or it can be set
-          without data and models configuration to get the job details between
-          payloads.
-
-
-          This parameter is useful to get the unique job ID.
-        default: false
-      payload_id:
-        type: optional<string>
-        docs: >
-          Pass an arbitrary string as the payload ID and get it back at the top
-          level of the socket response.
-
-
-          This can be useful if you have multiple requests running
-          asynchronously and want to disambiguate responses as they are
-          received.
-    source:
-      openapi: streaming-asyncapi.yml
   StreamModelPredictionsJobDetails:
     docs: >
       If the job_details flag was set in the request, details about the current
@@ -434,5 +231,208 @@ types:
         docs: Warning message
     source:
       openapi: streaming-asyncapi.yml
+  StreamFace:
+    docs: >
+      Configuration for the facial expression emotion model.
+
+
+      Note: Using the `reset_stream` parameter does not have any effect on face
+      identification. A single face identifier cache is maintained over a full
+      session whether `reset_stream` is used or not.
+    properties:
+      facs:
+        type: optional<map<string, unknown>>
+        docs: >-
+          Configuration for FACS predictions. If missing or null, no FACS
+          predictions will be generated.
+      descriptions:
+        type: optional<map<string, unknown>>
+        docs: >-
+          Configuration for Descriptions predictions. If missing or null, no
+          Descriptions predictions will be generated.
+      identify_faces:
+        type: optional<boolean>
+        docs: >
+          Whether to return identifiers for faces across frames. If true, unique
+          identifiers will be assigned to face bounding boxes to differentiate
+          different faces. If false, all faces will be tagged with an "unknown"
+          ID.
+        default: false
+      fps_pred:
+        type: optional<double>
+        docs: >
+          Number of frames per second to process. Other frames will be omitted
+          from the response.
+        default: 3
+      prob_threshold:
+        type: optional<double>
+        docs: >
+          Face detection probability threshold. Faces detected with a
+          probability less than this threshold will be omitted from the
+          response.
+        default: 3
+      min_face_size:
+        type: optional<double>
+        docs: >
+          Minimum bounding box side length in pixels to treat as a face. Faces
+          detected with a bounding box side length in pixels less than this
+          threshold will be omitted from the response.
+        default: 3
+    source:
+      openapi: streaming-asyncapi.yml
+    inline: true
+  StreamLanguage:
+    docs: Configuration for the language emotion model.
+    properties:
+      sentiment:
+        type: optional<map<string, unknown>>
+        docs: >-
+          Configuration for sentiment predictions. If missing or null, no
+          sentiment predictions will be generated.
+      toxicity:
+        type: optional<map<string, unknown>>
+        docs: >-
+          Configuration for toxicity predictions. If missing or null, no
+          toxicity predictions will be generated.
+      granularity:
+        type: optional<string>
+        docs: >-
+          The granularity at which to generate predictions. Values are `word`,
+          `sentence`, `utterance`, or `passage`. To get a single prediction for
+          the entire text of your streaming payload use `passage`. Default value
+          is `word`.
+    source:
+      openapi: streaming-asyncapi.yml
+    inline: true
+  Config:
+    docs: >
+      Configuration used to specify which models should be used and with what
+      settings.
+    properties:
+      burst:
+        type: optional<map<string, unknown>>
+        docs: |
+          Configuration for the vocal burst emotion model.
+
+          Note: Model configuration is not currently available in streaming.
+
+          Please use the default configuration by passing an empty object `{}`.
+      face:
+        type: optional<StreamFace>
+        docs: >
+          Configuration for the facial expression emotion model.
+
+
+          Note: Using the `reset_stream` parameter does not have any effect on
+          face identification. A single face identifier cache is maintained over
+          a full session whether `reset_stream` is used or not.
+      facemesh:
+        type: optional<map<string, unknown>>
+        docs: |
+          Configuration for the facemesh emotion model.
+
+          Note: Model configuration is not currently available in streaming.
+
+          Please use the default configuration by passing an empty object `{}`.
+      language:
+        type: optional<StreamLanguage>
+        docs: Configuration for the language emotion model.
+      prosody:
+        type: optional<map<string, unknown>>
+        docs: |
+          Configuration for the speech prosody emotion model.
+
+          Note: Model configuration is not currently available in streaming.
+
+          Please use the default configuration by passing an empty object `{}`.
+    source:
+      openapi: streaming-asyncapi.yml
+    inline: true
+  StreamModelsEndpointPayload:
+    docs: Models endpoint payload
+    properties:
+      data:
+        type: optional<string>
+      models:
+        type: optional<Config>
+        docs: >
+          Configuration used to specify which models should be used and with
+          what settings.
+      stream_window_ms:
+        type: optional<double>
+        docs: >
+          Length in milliseconds of streaming sliding window.
+
+
+          Extending the length of this window will prepend media context from
+          past payloads into the current payload.
+
+
+          For example, if on the first payload you send 500ms of data and on the
+          second payload you send an additional 500ms of data, a window of at
+          least 1000ms will allow the model to process all 1000ms of stream
+          data.
+
+
+          A window of 600ms would append the full 500ms of the second payload to
+          the last 100ms of the first payload.
+
+
+          Note: This feature is currently only supported for audio data and
+          audio models. For other file types and models this parameter will be
+          ignored.
+        default: 5000
+        validation:
+          min: 500
+          max: 10000
+      reset_stream:
+        type: optional<boolean>
+        docs: >
+          Whether to reset the streaming sliding window before processing the
+          current payload.
+
+
+          If this parameter is set to `true` then past context will be deleted
+          before processing the current payload.
+
+
+          Use reset_stream when one audio file is done being processed and you
+          do not want context to leak across files.
+        default: false
+      raw_text:
+        type: optional<boolean>
+        docs: >
+          Set to `true` to enable the data parameter to be parsed as raw text
+          rather than base64 encoded bytes.
+
+          This parameter is useful if you want to send text to be processed by
+          the language model, but it cannot be used with other file types like
+          audio, image, or video.
+        default: false
+      job_details:
+        type: optional<boolean>
+        docs: >
+          Set to `true` to get details about the job.
+
+
+          This parameter can be set in the same payload as data or it can be set
+          without data and models configuration to get the job details between
+          payloads.
+
+
+          This parameter is useful to get the unique job ID.
+        default: false
+      payload_id:
+        type: optional<string>
+        docs: >
+          Pass an arbitrary string as the payload ID and get it back at the top
+          level of the socket response.
+
+
+          This can be useful if you have multiple requests running
+          asynchronously and want to disambiguate responses as they are
+          received.
+    source:
+      openapi: streaming-asyncapi.yml
 imports:
   streamRoot: __package__.yml

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

@@ -69,15 +69,16 @@ service:
                   file_size: 120192
                   encoding:
                     format: mp3
-                    sample_rate: 24000
+                    sample_rate: 48000
                   audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
                   snippets:
                     - - audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
+                        generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
                         id: 37b1b1b1-1b1b-1b1b-1b1b-1b1b1b1b1b1b
                         text: >-
                           Beauty is no quality in things themselves: It exists
                           merely in the mind which contemplates them.
-                        generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
+                        utterance_index: 0
               request_id: 66e01f90-4501-4aa0-bbaf-74f45dc15aa725906
     synthesize-file:
       path: /v0/tts/file
@@ -221,13 +222,18 @@ types:
     source:
       openapi: tts-openapi.yml
   AudioEncoding:
+    docs: >-
+      Encoding information about the generated audio, including the `format` and
+      `sample_rate`.
     properties:
       format:
         type: AudioFormatType
         docs: Format for the output audio.
       sample_rate:
         type: integer
-        docs: Sample rate of the generated audio.
+        docs: >-
+          The sample rate (`Hz`) of the generated audio. The default sample rate
+          is `48000 Hz`.
     source:
       openapi: tts-openapi.yml
   AudioFormatType:
@@ -260,9 +266,10 @@ types:
           multiple requests.
       snippets:
         docs: >-
-          A list of speech segments, each containing a portion of the original
-          text optimized for  natural speech delivery. These segments represent
-          the input text divided into more natural-sounding units.
+          A list of snippet groups where each group corresponds to an utterance
+          in the request. Each  group contains segmented snippets that represent
+          the original utterance divided into more natural-sounding units
+          optimized for speech delivery.
         type: list<list<Snippet>>
     source:
       openapi: tts-openapi.yml
@@ -340,7 +347,16 @@ types:
           as this can result in distorted output.
         default: true
       utterances:
-        docs: Utterances to be converted to speech output.
+        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>
     source:
       openapi: tts-openapi.yml
@@ -439,12 +455,10 @@ types:
           accent').
 
           - If a Voice is specified in the request, this description serves as
-          acting instructions.
-
-          - If  no Voice is specified, a new voice is generated based on this
-          description.
-
-           See our  [prompting guide](/docs/text-to-speech-tts/prompting) for tips on crafting your descriptions.
+          acting instructions. For  tips on how to effectively guide speech
+          delivery, see our guide on [Acting
+          instructions](/docs/text-to-speech-tts/acting-instructions).
+           - If no Voice is specified, a new voice is generated based on this description. See our [prompting guide](/docs/text-to-speech-tts/prompting)  for tips on designing a voice.
         validation:
           maxLength: 1000
       speed:
@@ -557,9 +571,29 @@ types:
   ReturnPagedVoices:
     docs: A paginated list Octave voices available for text-to-speech
     properties:
-      page_number: optional<integer>
-      page_size: optional<integer>
-      total_pages: optional<integer>
-      voices_page: optional<list<ReturnVoice>>
+      page_number:
+        type: optional<integer>
+        docs: >-
+          The page number of the returned list.
+
+
+          This value corresponds to the `page_number` parameter specified in the
+          request. Pagination uses zero-based indexing.
+      page_size:
+        type: optional<integer>
+        docs: >-
+          The maximum number of items returned per page.
+
+
+          This value corresponds to the `page_size` parameter specified in the
+          request.
+      total_pages:
+        type: optional<integer>
+        docs: The total number of pages in the collection.
+      voices_page:
+        type: optional<list<ReturnVoice>>
+        docs: >-
+          List of voices returned for the specified `page_number` and
+          `page_size`.
     source:
       openapi: tts-openapi.yml

package/.mock/definition/tts/voices.yml

@@ -44,7 +44,8 @@ service:
 
               For example, if `page_size` is set to 10, each page will include
               up to 10 items. Defaults to 10.
-          ascending_order: optional<boolean>
+          ascending_order:
+            type: optional<boolean>
       response:
         docs: Success
         type: root.ReturnPagedVoices
@@ -56,11 +57,16 @@ service:
             provider: CUSTOM_VOICE
           response:
             body:
+              page_number: 0
+              page_size: 10
+              total_pages: 1
               voices_page:
                 - name: David Hume
                   id: c42352c0-4566-455d-b180-0f654b65b525
+                  provider: CUSTOM_VOICE
                 - name: Goliath Hume
                   id: d87352b0-26a3-4b11-081b-d157a5674d19
+                  provider: CUSTOM_VOICE
     create:
       path: /v0/tts/voices
       method: POST
@@ -100,6 +106,7 @@ service:
             body:
               name: David Hume
               id: c42352c0-4566-455d-b180-0f654b65b525
+              provider: CUSTOM_VOICE
     delete:
       path: /v0/tts/voices
       method: DELETE

package/.mock/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization" : "hume",
-  "version" : "0.57.14"
+  "version" : "0.56.23"
 }

package/api/resources/empathicVoice/errors/BadRequestError.js

@@ -18,13 +18,23 @@ var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (
 }) : function(o, v) {
     o["default"] = v;
 });
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.BadRequestError = void 0;
 const errors = __importStar(require("../../../../errors/index"));

package/api/resources/empathicVoice/resources/chat/client/Client.js

@@ -15,13 +15,23 @@ var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (
 }) : function(o, v) {
     o["default"] = v;
 });
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
 var __importDefault = (this && this.__importDefault) || function (mod) {
     return (mod && mod.__esModule) ? mod : { "default": mod };
 };

package/api/resources/empathicVoice/resources/chat/client/Socket.js

@@ -15,13 +15,23 @@ var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (
 }) : function(o, v) {
     o["default"] = v;
 });
-var __importStar = (this && this.__importStar) || function (mod) {
-    if (mod && mod.__esModule) return mod;
-    var result = {};
-    if (mod != null) for (var k in mod) if (k !== "default" && Object.prototype.hasOwnProperty.call(mod, k)) __createBinding(result, mod, k);
-    __setModuleDefault(result, mod);
-    return result;
-};
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
 var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
     function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
     return new (P || (P = Promise))(function (resolve, reject) {