hume 0.11.0 → 0.11.2

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

@@ -21,9 +21,9 @@ service:
       auth: true
       docs: >-
         Synthesizes one or more input texts into speech using the specified
-        voice. If no voice is provided,  a novel voice will be generated
+        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 speech's style and prosody.
 
 
         The response includes the base64-encoded audio and metadata in JSON
@@ -34,6 +34,23 @@ 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
@@ -49,14 +66,14 @@ service:
                   the mind which contemplates them.
                 description: >-
                   Middle-aged masculine voice with a clear, rhythmic Scots lilt,
-                  rounded vowels, and a warm,  steady tone with an articulate,
+                  rounded vowels, and a warm, steady tone with an articulate,
                   academic quality.
             context:
               utterances:
                 - text: How can people see beauty so differently?
                   description: >-
                     A curious student with a clear and respectful tone, seeking
-                    clarification on Hume's  ideas with a straightforward
+                    clarification on Hume's ideas with a straightforward
                     question.
             format:
               type: mp3
@@ -86,9 +103,9 @@ service:
       auth: true
       docs: >-
         Synthesizes one or more input texts into speech using the specified
-        voice. If no voice is provided,  a novel voice will be generated
+        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 speech's style and prosody. 
 
 
         The response contains the generated audio file in the requested format.
@@ -113,7 +130,7 @@ service:
                   the mind which contemplates them.
                 description: >-
                   Middle-aged masculine voice with a clear, rhythmic Scots lilt,
-                  rounded vowels, and a warm,  steady tone with an articulate,
+                  rounded vowels, and a warm, steady tone with an articulate,
                   academic quality.
             context:
               generation_id: 09ad914d-8e7f-40f8-a279-e34f07f7dab2
@@ -126,7 +143,7 @@ service:
       auth: true
       docs: >-
         Streams synthesized speech using the specified voice. If no voice is
-        provided, a novel voice will be  generated dynamically. Optionally,
+        provided, a novel voice will be generated dynamically. Optionally,
         additional context can be included to influence the speech's style and
         prosody.
       source:
@@ -150,7 +167,7 @@ service:
                   the mind which contemplates them.
                 description: >-
                   Middle-aged masculine voice with a clear, rhythmic Scots lilt,
-                  rounded vowels, and a warm,  steady tone with an articulate,
+                  rounded vowels, and a warm, steady tone with an articulate,
                   academic quality.
             context:
               generation_id: 09ad914d-8e7f-40f8-a279-e34f07f7dab2
@@ -163,8 +180,8 @@ service:
       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
+        provided, a novel voice will be generated dynamically. Optionally,
+        additional context can be included to influence the speech's style and
         prosody. 
 
 
@@ -191,14 +208,14 @@ service:
                   the mind which contemplates them.
                 description: >-
                   Middle-aged masculine voice with a clear, rhythmic Scots lilt,
-                  rounded vowels, and a warm,  steady tone with an articulate,
+                  rounded vowels, and a warm, steady tone with an articulate,
                   academic quality.
             context:
               utterances:
                 - text: How can people see beauty so differently?
                   description: >-
                     A curious student with a clear and respectful tone, seeking
-                    clarification on Hume's  ideas with a straightforward
+                    clarification on Hume's ideas with a straightforward
                     question.
             format:
               type: mp3
@@ -267,7 +284,7 @@ types:
       snippets:
         docs: >-
           A list of snippet groups where each group corresponds to an utterance
-          in the request. Each  group contains segmented snippets that represent
+          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>>
@@ -332,19 +349,19 @@ types:
           Controls how audio output is segmented in the response.
 
 
-          - When **enabled** (`true`),  input utterances are automatically split
+          - When **enabled** (`true`), input utterances are automatically split
           into natural-sounding speech segments.
 
 
-          - When **disabled**  (`false`), the response maintains a strict
+          - When **disabled** (`false`), the response maintains a strict
           one-to-one mapping between input utterances and output snippets. 
 
 
           This setting affects how the `snippets` array is structured in the
-          response, which may be important  for applications that need to track
-          the relationship between input text and generated audio segments.
-          When  setting to `false`, avoid including utterances with long `text`,
-          as this can result in distorted output.
+          response, which may be important for applications that need to track
+          the relationship between input text and generated audio segments. When
+          setting to `false`, avoid including utterances with long `text`, as
+          this can result in distorted output.
         default: true
       strip_headers:
         type: optional<boolean>
@@ -359,9 +376,9 @@ types:
           A list of **Utterances** to be converted to speech output.
 
 
-          An **Utterance** is a unit of  input for
+          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
+          `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`.
@@ -376,11 +393,11 @@ types:
           mode](/docs/text-to-speech-tts/overview#ultra-low-latency-streaming-instant-mode). 
 
           - Dynamic voice generation is not supported with this mode; a
-          predefined 
-          [voice](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.utterances.voice) 
+          predefined
+          [voice](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.utterances.voice)
           must be specified in your request.
 
-          - This mode is only supported for streaming endpoints (e.g., 
+          - This mode is only supported for streaming endpoints (e.g.,
           [/v0/tts/stream/json](/reference/text-to-speech-tts/synthesize-json-streaming),
           [/v0/tts/stream/file](/reference/text-to-speech-tts/synthesize-file-streaming)).
 
@@ -401,7 +418,7 @@ types:
         type: optional<string>
         docs: >-
           A unique ID associated with this request for tracking and
-          troubleshooting. Use this ID when  contacting [support](/support) for
+          troubleshooting. Use this ID when contacting [support](/support) for
           troubleshooting assistance.
     source:
       openapi: tts-openapi.yml
@@ -416,16 +433,12 @@ types:
         docs: Name of the voice in the `Voice Library`.
       provider:
         type: optional<VoiceProvider>
-        docs: |-
-          Specifies the provider of the voice.
-
-           - **HUME_AI**:  Preset voices generated by Hume. 
-
-           - **CUSTOM_VOICE**: Voices you have generated and saved to your  `Voice library`.
+        docs: >-
+          The provider associated with the created voice.
 
-           If a provider is not specified, the provider will default to `CUSTOM_VOICE`. 
 
-            While Hume's preset voices are shared and usable by anyone, your custom voices are only available to calls  made with your API key.
+          Voices created through this endpoint will always have the provider set
+          to `CUSTOM_VOICE`, indicating a custom voice stored in your account.
     source:
       openapi: tts-openapi.yml
   FormatPcm:
@@ -439,7 +452,6 @@ types:
         docs: >-
           The segmented audio output in the requested format, encoded as a
           base64 string.
-        access: read-only
       generation_id:
         type: string
         docs: The generation ID this snippet corresponds to.
@@ -449,6 +461,11 @@ types:
       text:
         type: string
         docs: The text for this **Snippet**.
+      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.
@@ -478,6 +495,12 @@ types:
       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: >-
@@ -491,15 +514,15 @@ types:
         type: optional<string>
         docs: >-
           Natural language instructions describing how the synthesized speech
-          should sound, including  but not limited to tone, intonation, pacing,
-          and accent (e.g., 'a soft, gentle voice with a strong British 
+          should sound, including but not limited to tone, intonation, pacing,
+          and accent (e.g., 'a soft, gentle voice with a strong British
           accent').
 
           - If a Voice is specified in the request, this description serves as
-          acting instructions. For  tips on how to effectively guide speech
+          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.
+           - 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:
@@ -525,10 +548,10 @@ types:
         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
+          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**.
+           See our [voices guide](/docs/text-to-speech-tts/voices) for more details on generating and specifying **Voices**.
     source:
       openapi: tts-openapi.yml
   ValidationErrorLocItem:
@@ -551,38 +574,58 @@ types:
     properties:
       id:
         type: string
-        docs: The ID of a **Voice** within the **Voice Library**.
+        docs: The unique ID associated with the **Voice**.
       provider:
         type: optional<VoiceProvider>
-        docs: |-
-          Specifies the provider of the voice associated with this voice ID.
+        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.
 
-           - **HUME_AI**:  Preset voices generated by Hume. 
+          - **`CUSTOM_VOICE`**: Select from voices you've personally generated
+          and saved in your account. 
 
-           - **CUSTOM_VOICE**: Voices you have generated and saved to your  `Voice library`.
 
-           If a provider is not specified, the provider will default to `CUSTOM_VOICE`. 
+          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`.
 
-            While Hume's preset voices are shared and usable by anyone, your custom voices are only available to calls  made with your API key.
+
+          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.yml
   PostedUtteranceVoiceWithName:
     properties:
       name:
         type: string
-        docs: The name of a **Voice** within the **Voice Library**.
+        docs: The name of a **Voice**.
       provider:
         type: optional<VoiceProvider>
-        docs: |-
-          Specifies the provider of the voice associated with this voice name.
+        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. 
 
-           - **HUME_AI**:  Preset voices generated by Hume. 
 
-           - **CUSTOM_VOICE**: Voices you have generated and saved to your  `Voice library`.
+          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`.
 
-           If a provider is not specified, the provider will default to `CUSTOM_VOICE`. 
 
-            While Hume's preset voices are shared and usable by anyone, your custom voices are only available to calls  made with your API key.
+          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.yml
   VoiceProvider:

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

@@ -9,9 +9,8 @@ service:
       method: GET
       auth: true
       docs: >-
-        Lists voices in your **Voice Library**. Set provider to `HUME_AI` to
-        list Hume's preset voices, or to `CUSTOM_VOICE` to a custom voice
-        created in your account.
+        Lists voices you have saved in your account, or voices from the [Voice
+        Library](https://platform.hume.ai/tts/voice-library).
       pagination:
         offset: $request.page_number
         results: $response.voices_page
@@ -24,10 +23,18 @@ service:
           provider:
             type: root.VoiceProvider
             docs: >-
-              Specifies whether to return custom voices created in your account
-              or shared voices provided by Hume
+              Specify the voice provider to filter voices returned by the
+              endpoint:
+
+
+              - **`HUME_AI`**: Lists preset, shared voices from Hume's [Voice
+              Library](https://platform.hume.ai/tts/voice-library).
+
+              - **`CUSTOM_VOICE`**: Lists custom voices created and saved to
+              your account.
           page_number:
             type: optional<integer>
+            default: 0
             docs: >-
               Specifies the page number to retrieve, enabling pagination.
 
@@ -74,9 +81,13 @@ service:
       method: POST
       auth: true
       docs: >-
-        Creates a new voice from a specified TTS generation ID and saves it to
-        your **Voice Library**. This allows for consistent speech style and
-        prosody across multiple requests.
+        Saves a new custom voice to your account using the specified TTS
+        generation ID.
+
+
+        Once saved, this voice can be reused in subsequent TTS requests,
+        ensuring consistent speech style and prosody. For more details on voice
+        creation, see the [Voices Guide](/docs/text-to-speech-tts/voices).
       source:
         openapi: tts-openapi.yml
       display-name: Create voice
@@ -113,7 +124,7 @@ service:
       path: /v0/tts/voices
       method: DELETE
       auth: true
-      docs: Removes a custom voice from your **Voice Library**.
+      docs: Deletes a previously generated custom voice.
       source:
         openapi: tts-openapi.yml
       display-name: Delete voice

package/.mock/fern.config.json

@@ -1,4 +1,4 @@
 {
   "organization" : "hume",
-  "version" : "0.57.5"
+  "version" : "0.64.10"
 }

package/Client.d.ts

@@ -1,12 +1,14 @@
 /** THIS FILE IS MANUALLY MAINAINED: see .fernignore */
 import * as environments from "./environments";
 import * as core from "./core";
-import { ExpressionMeasurement } from "./api/resources/expressionMeasurement/client/Client";
-import { EmpathicVoice } from "./api/resources/empathicVoice/client/Client";
 import { Tts } from "./api/resources/tts/client/Client";
+import { EmpathicVoice } from "./api/resources/empathicVoice/client/Client";
+import { ExpressionMeasurement } from "./api/resources/expressionMeasurement/client/Client";
 export declare namespace HumeClient {
     interface Options {
         environment?: core.Supplier<environments.HumeEnvironment | string>;
+        /** Specify a custom URL to connect the client to. */
+        baseUrl?: core.Supplier<string>;
         apiKey?: core.Supplier<string | undefined>;
         accessToken?: core.Supplier<string | undefined>;
         fetcher?: core.FetchFunction;
@@ -18,15 +20,17 @@ export declare namespace HumeClient {
         maxRetries?: number;
         /** A hook to abort the request. */
         abortSignal?: AbortSignal;
+        /** Additional headers to include in the request. */
+        headers?: Record<string, string>;
     }
 }
 export declare class HumeClient {
     protected readonly _options: HumeClient.Options;
-    constructor(_options?: HumeClient.Options);
-    protected _expressionMeasurement: ExpressionMeasurement | undefined;
-    get expressionMeasurement(): ExpressionMeasurement;
-    protected _empathicVoice: EmpathicVoice | undefined;
-    get empathicVoice(): EmpathicVoice;
     protected _tts: Tts | undefined;
+    protected _empathicVoice: EmpathicVoice | undefined;
+    protected _expressionMeasurement: ExpressionMeasurement | undefined;
+    constructor(_options?: HumeClient.Options);
     get tts(): Tts;
+    get empathicVoice(): EmpathicVoice;
+    get expressionMeasurement(): ExpressionMeasurement;
 }

package/Client.js

@@ -1,25 +1,73 @@
 "use strict";
 /** THIS FILE IS MANUALLY MAINAINED: see .fernignore */
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+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.HumeClient = void 0;
-const Client_1 = require("./api/resources/expressionMeasurement/client/Client");
+const core = __importStar(require("./core"));
+const Client_1 = require("./api/resources/tts/client/Client");
 const Client_2 = require("./api/resources/empathicVoice/client/Client");
-const Client_3 = require("./api/resources/tts/client/Client");
+const Client_3 = require("./api/resources/expressionMeasurement/client/Client");
+const version_1 = require("./version");
+const fetcherThatAddsHeaders = (fetcherToWrap) => {
+    return (args) => {
+        var _a;
+        const newArgs = Object.assign({}, args);
+        newArgs.headers = (_a = newArgs.headers) !== null && _a !== void 0 ? _a : {};
+        (newArgs.headers["X-Hume-Client-Name"] = "typescript_sdk"),
+            (newArgs.headers["X-Hume-Client-Version"] = version_1.SDK_VERSION);
+        return fetcherToWrap(args);
+    };
+};
 class HumeClient {
     constructor(_options = {}) {
+        var _a;
         this._options = _options;
+        const defaultFetcher = (_a = _options.fetcher) !== null && _a !== void 0 ? _a : core.fetcher;
+        this._options.fetcher = fetcherThatAddsHeaders(defaultFetcher);
     }
-    get expressionMeasurement() {
+    get tts() {
         var _a;
-        return ((_a = this._expressionMeasurement) !== null && _a !== void 0 ? _a : (this._expressionMeasurement = new Client_1.ExpressionMeasurement(this._options)));
+        return ((_a = this._tts) !== null && _a !== void 0 ? _a : (this._tts = new Client_1.Tts(this._options)));
     }
     get empathicVoice() {
         var _a;
         return ((_a = this._empathicVoice) !== null && _a !== void 0 ? _a : (this._empathicVoice = new Client_2.EmpathicVoice(this._options)));
     }
-    get tts() {
+    get expressionMeasurement() {
         var _a;
-        return ((_a = this._tts) !== null && _a !== void 0 ? _a : (this._tts = new Client_3.Tts(this._options)));
+        return ((_a = this._expressionMeasurement) !== null && _a !== void 0 ? _a : (this._expressionMeasurement = new Client_3.ExpressionMeasurement(this._options)));
     }
 }
 exports.HumeClient = HumeClient;

package/api/resources/empathicVoice/errors/BadRequestError.d.ts

@@ -3,6 +3,7 @@
  */
 import * as errors from "../../../../errors/index";
 import * as Hume from "../../../index";
+import * as core from "../../../../core";
 export declare class BadRequestError extends errors.HumeError {
-    constructor(body: Hume.empathicVoice.ErrorResponse);
+    constructor(body: Hume.empathicVoice.ErrorResponse, rawResponse?: core.RawResponse);
 }

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

@@ -39,11 +39,12 @@ Object.defineProperty(exports, "__esModule", { value: true });
 exports.BadRequestError = void 0;
 const errors = __importStar(require("../../../../errors/index"));
 class BadRequestError extends errors.HumeError {
-    constructor(body) {
+    constructor(body, rawResponse) {
         super({
             message: "BadRequestError",
             statusCode: 400,
             body: body,
+            rawResponse: rawResponse,
         });
         Object.setPrototypeOf(this, BadRequestError.prototype);
     }

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

@@ -59,7 +59,8 @@ export declare class ChatGroups {
      *         ascendingOrder: true
      *     })
      */
-    getChatGroup(id: string, request?: Hume.empathicVoice.ChatGroupsGetChatGroupRequest, requestOptions?: ChatGroups.RequestOptions): Promise<Hume.empathicVoice.ReturnChatGroupPagedChats>;
+    getChatGroup(id: string, request?: Hume.empathicVoice.ChatGroupsGetChatGroupRequest, requestOptions?: ChatGroups.RequestOptions): core.HttpResponsePromise<Hume.empathicVoice.ReturnChatGroupPagedChats>;
+    private __getChatGroup;
     /**
      * Fetches a paginated list of **Chat** events associated with a **Chat Group**.
      *
@@ -93,7 +94,8 @@ export declare class ChatGroups {
      *         ascendingOrder: true
      *     })
      */
-    getAudio(id: string, request?: Hume.empathicVoice.ChatGroupsGetAudioRequest, requestOptions?: ChatGroups.RequestOptions): Promise<Hume.empathicVoice.ReturnChatGroupPagedAudioReconstructions>;
+    getAudio(id: string, request?: Hume.empathicVoice.ChatGroupsGetAudioRequest, requestOptions?: ChatGroups.RequestOptions): core.HttpResponsePromise<Hume.empathicVoice.ReturnChatGroupPagedAudioReconstructions>;
+    private __getAudio;
     protected _getCustomAuthorizationHeaders(): Promise<{
         "X-Hume-Api-Key": string | undefined;
     }>;