hume 0.13.1 → 0.13.3

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

@@ -142,8 +142,8 @@ types:
       openapi: evi-asyncapi.json
   ContextType:
     enum:
-      - temporary
       - persistent
+      - temporary
     source:
       openapi: evi-asyncapi.json
   Encoding:
@@ -990,6 +990,7 @@ types:
     union:
       - type: AssistantEnd
       - type: AssistantMessage
+      - type: AssistantProsody
       - type: ChatMetadata
       - type: WebSocketError
       - type: UserInterruption
@@ -997,7 +998,6 @@ types:
       - type: ToolCallMessage
       - type: ToolResponseMessage
       - type: ToolErrorMessage
-      - type: AssistantProsody
     source:
       openapi: evi-asyncapi.json
   HTTPValidationError:
@@ -1142,6 +1142,26 @@ types:
       type: string
     source:
       openapi: evi-openapi.json
+  VoiceId:
+    properties:
+      id:
+        type: string
+        docs: ID of the voice in the `Voice Library`.
+      provider:
+        type: optional<VoiceProvider>
+        docs: Model provider associated with this Voice ID.
+    source:
+      openapi: evi-openapi.json
+  VoiceName:
+    properties:
+      name:
+        type: string
+        docs: Name of the voice in the `Voice Library`.
+      provider:
+        type: optional<VoiceProvider>
+        docs: Model provider associated with this Voice Name.
+    source:
+      openapi: evi-openapi.json
   WebhookEventChatEnded:
     properties:
       event_name:
@@ -1551,7 +1571,9 @@ types:
           model that takes into account both expression measures and language.
           The eLLM generates short, empathic language responses and guides
           text-to-speech (TTS) prosody.
-      voice: optional<unknown>
+      voice:
+        type: optional<ReturnVoice>
+        docs: A voice specification associated with this Config.
       prompt: optional<ReturnPrompt>
       webhooks:
         type: optional<list<optional<ReturnWebhookSpec>>>
@@ -2928,33 +2950,6 @@ types:
           minutes).
     source:
       openapi: evi-openapi.json
-  VoiceProvider:
-    enum:
-      - HUME_AI
-      - CUSTOM_VOICE
-      - OCTAVE_COMBINED
-    source:
-      openapi: evi-openapi.json
-  VoiceId:
-    properties:
-      id:
-        type: string
-        docs: ID of the voice in the `Voice Library`.
-      provider:
-        type: optional<VoiceProvider>
-        docs: Model provider associated with this Voice ID.
-    source:
-      openapi: evi-openapi.json
-  VoiceName:
-    properties:
-      name:
-        type: string
-        docs: Name of the voice in the `Voice Library`.
-      provider:
-        type: optional<VoiceProvider>
-        docs: Model provider associated with this Voice Name.
-    source:
-      openapi: evi-openapi.json
   VoiceRef:
     discriminated: false
     union:
@@ -2962,3 +2957,17 @@ types:
       - type: VoiceName
     source:
       openapi: evi-openapi.json
+  ReturnVoice:
+    docs: An Octave voice available for text-to-speech
+    properties:
+      id: optional<string>
+      name: optional<string>
+      provider: optional<VoiceProvider>
+    source:
+      openapi: evi-openapi.json
+  VoiceProvider:
+    enum:
+      - HUME_AI
+      - CUSTOM_VOICE
+    source:
+      openapi: evi-openapi.json

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

@@ -29,7 +29,7 @@ service:
         The response includes the base64-encoded audio and metadata in JSON
         format.
       source:
-        openapi: tts-openapi.yml
+        openapi: tts-openapi.json
       display-name: Text-to-speech (Json)
       request:
         body:
@@ -43,14 +43,6 @@ service:
         - UnprocessableEntityError
       examples:
         - request:
-            utterances:
-              - text: >-
-                  Beauty is no quality in things themselves: It exists merely in
-                  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,
-                  academic quality.
             context:
               utterances:
                 - text: How can people see beauty so differently?
@@ -61,16 +53,24 @@ service:
             format:
               type: mp3
             num_generations: 1
+            utterances:
+              - text: >-
+                  Beauty is no quality in things themselves: It exists merely in
+                  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,
+                  academic quality.
           response:
             body:
               generations:
-                - generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
+                - audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
                   duration: 7.44225
-                  file_size: 120192
                   encoding:
                     format: mp3
                     sample_rate: 48000
-                  audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
+                  file_size: 120192
+                  generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
                   snippets:
                     - - audio: //PExAA0DDYRvkpNfhv3JI5JZ...etc.
                         generation_id: 795c949a-1510-4a80-9646-7d0863b023ab
@@ -93,7 +93,7 @@ service:
 
         The response contains the generated audio file in the requested format.
       source:
-        openapi: tts-openapi.yml
+        openapi: tts-openapi.json
       display-name: Text-to-speech (File)
       request:
         body:
@@ -107,6 +107,11 @@ service:
         - UnprocessableEntityError
       examples:
         - request:
+            context:
+              generation_id: 09ad914d-8e7f-40f8-a279-e34f07f7dab2
+            format:
+              type: mp3
+            num_generations: 1
             utterances:
               - text: >-
                   Beauty is no quality in things themselves: It exists merely in
@@ -115,11 +120,6 @@ service:
                   Middle-aged masculine voice with a clear, rhythmic Scots lilt,
                   rounded vowels, and a warm, steady tone with an articulate,
                   academic quality.
-            context:
-              generation_id: 09ad914d-8e7f-40f8-a279-e34f07f7dab2
-            format:
-              type: mp3
-            num_generations: 1
     synthesize-json-streaming:
       path: /v0/tts/stream/json
       method: POST
@@ -134,7 +134,7 @@ service:
         The response is a stream of JSON objects including audio encoded in
         base64.
       source:
-        openapi: tts-openapi.yml
+        openapi: tts-openapi.json
       display-name: Text-to-speech (Streamed JSON)
       request:
         body:
@@ -165,7 +165,7 @@ service:
         additional context can be included to influence the speech's style and
         prosody.
       source:
-        openapi: tts-openapi.yml
+        openapi: tts-openapi.json
       display-name: Text-to-speech (Streamed File)
       request:
         body:
@@ -187,7 +187,7 @@ service:
                   name: Male English Actor
                   provider: HUME_AI
   source:
-    openapi: tts-openapi.yml
+    openapi: tts-openapi.json
 types:
   PostedContextWithGenerationId:
     properties:
@@ -198,13 +198,13 @@ types:
           consistent speech style and prosody across multiple requests.
           Including context may increase audio generation times.
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedContextWithUtterances:
     properties:
       utterances:
         type: list<PostedUtterance>
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   AudioEncoding:
     docs: >-
       Encoding information about the generated audio, including the `format` and
@@ -219,14 +219,14 @@ types:
           The sample rate (`Hz`) of the generated audio. The default sample rate
           is `48000 Hz`.
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   AudioFormatType:
     enum:
       - mp3
       - pcm
       - wav
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   ReturnGeneration:
     properties:
       generation_id:
@@ -256,17 +256,17 @@ types:
           optimized for speech delivery.
         type: list<list<Snippet>>
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   HTTPValidationError:
     properties:
       detail:
         type: optional<list<ValidationError>>
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   FormatMp3:
     properties: {}
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedContext:
     discriminated: false
     docs: >-
@@ -277,7 +277,7 @@ types:
       - type: PostedContextWithGenerationId
       - type: PostedContextWithUtterances
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
     inline: true
   Format:
     discriminant: type
@@ -291,7 +291,7 @@ types:
       wav:
         type: FormatWav
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedTts:
     properties:
       context:
@@ -373,7 +373,7 @@ types:
           must be `1` or omitted).
         default: true
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   ReturnTts:
     properties:
       request_id:
@@ -385,7 +385,7 @@ types:
       generations:
         type: list<ReturnGeneration>
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   ReturnVoice:
     docs: An Octave voice available for text-to-speech
     properties:
@@ -404,11 +404,11 @@ types:
           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
+      openapi: tts-openapi.json
   FormatPcm:
     properties: {}
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   Snippet:
     properties:
       id:
@@ -434,11 +434,49 @@ types:
           The segmented audio output in the requested format, encoded as a
           base64 string.
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   SnippetAudioChunk:
-    properties: {}
+    properties:
+      generation_id:
+        type: string
+        docs: >-
+          The generation ID of the parent snippet that this chunk corresponds
+          to.
+      snippet_id:
+        type: string
+        docs: The ID of the parent snippet that this chunk corresponds to.
+      text:
+        type: string
+        docs: The text of the parent snippet that this chunk corresponds to.
+      transcribed_text:
+        type: optional<string>
+        docs: >-
+          The transcribed text of the generated audio of the parent snippet that
+          this chunk corresponds to. It is only present if `instant_mode` is set
+          to `false`.
+      chunk_index:
+        type: integer
+        docs: The index of the audio chunk in the snippet.
+      audio:
+        type: string
+        docs: The generated audio output chunk in the requested format.
+      audio_format:
+        type: AudioFormatType
+        docs: The generated audio output format.
+      is_last_chunk:
+        type: boolean
+        docs: >-
+          Whether or not this is the last chunk streamed back from the decoder
+          for one input snippet.
+      utterance_index:
+        type: optional<integer>
+        docs: >-
+          The index of the utterance in the request that the parent snippet of
+          this chunk corresponds to.
+      snippet:
+        type: Snippet
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedUtterance:
     properties:
       text:
@@ -492,14 +530,14 @@ types:
           min: 0
           max: 5
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   ValidationErrorLocItem:
     discriminated: false
     union:
       - string
       - integer
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
     inline: true
   ValidationError:
     properties:
@@ -508,7 +546,7 @@ types:
       msg: string
       type: string
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedUtteranceVoiceWithId:
     properties:
       id:
@@ -537,7 +575,7 @@ types:
           users. In contrast, your custom voices are private and accessible only
           via requests authenticated with your API key.
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedUtteranceVoiceWithName:
     properties:
       name:
@@ -566,31 +604,31 @@ types:
           users. In contrast, your custom voices are private and accessible only
           via requests authenticated with your API key.
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   VoiceProvider:
     enum:
       - HUME_AI
       - CUSTOM_VOICE
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   PostedUtteranceVoice:
     discriminated: false
     union:
       - type: PostedUtteranceVoiceWithId
       - type: PostedUtteranceVoiceWithName
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   FormatWav:
     properties: {}
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   ErrorResponse:
     properties:
       error: optional<string>
       message: optional<string>
       code: optional<string>
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json
   ReturnPagedVoices:
     docs: A paginated list Octave voices available for text-to-speech
     properties:
@@ -619,4 +657,4 @@ types:
           List of voices returned for the specified `page_number` and
           `page_size`.
     source:
-      openapi: tts-openapi.yml
+      openapi: tts-openapi.json

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

@@ -15,7 +15,7 @@ service:
         offset: $request.page_number
         results: $response.voices_page
       source:
-        openapi: tts-openapi.yml
+        openapi: tts-openapi.json
       display-name: List voices
       request:
         name: VoicesListRequest
@@ -70,11 +70,11 @@ service:
               page_size: 10
               total_pages: 1
               voices_page:
-                - name: David Hume
-                  id: c42352c0-4566-455d-b180-0f654b65b525
+                - id: c42352c0-4566-455d-b180-0f654b65b525
+                  name: David Hume
                   provider: CUSTOM_VOICE
-                - name: Goliath Hume
-                  id: d87352b0-26a3-4b11-081b-d157a5674d19
+                - id: d87352b0-26a3-4b11-081b-d157a5674d19
+                  name: Goliath Hume
                   provider: CUSTOM_VOICE
     create:
       path: /v0/tts/voices
@@ -89,7 +89,7 @@ service:
         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
+        openapi: tts-openapi.json
       display-name: Create voice
       request:
         name: PostedVoice
@@ -117,8 +117,8 @@ service:
             name: David Hume
           response:
             body:
-              name: David Hume
               id: c42352c0-4566-455d-b180-0f654b65b525
+              name: David Hume
               provider: CUSTOM_VOICE
     delete:
       path: /v0/tts/voices
@@ -126,7 +126,7 @@ service:
       auth: true
       docs: Deletes a previously generated custom voice.
       source:
-        openapi: tts-openapi.yml
+        openapi: tts-openapi.json
       display-name: Delete voice
       request:
         name: VoicesDeleteRequest
@@ -140,4 +140,4 @@ service:
         - query-parameters:
             name: David Hume
   source:
-    openapi: tts-openapi.yml
+    openapi: tts-openapi.json

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

@@ -82,6 +82,9 @@ class Chat {
         if (args.verboseTranscription !== null) {
             queryParams["verbose_transcription"] = args.verboseTranscription ? "true" : "false";
         }
+        if (args.voiceId !== null && args.voiceId !== undefined && args.voiceId !== "") {
+            queryParams["voice_id"] = args.voiceId;
+        }
         if (args.queryParams !== null && args.queryParams !== undefined) {
             for (const [name, value] of Object.entries(args.queryParams)) {
                 queryParams[name] = value;

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

@@ -1,8 +1,8 @@
 /**
  * This file was auto-generated by Fern from our API Definition.
  */
-export type ContextType = "temporary" | "persistent";
+export type ContextType = "persistent" | "temporary";
 export declare const ContextType: {
-    readonly Temporary: "temporary";
     readonly Persistent: "persistent";
+    readonly Temporary: "temporary";
 };

package/api/resources/empathicVoice/types/ContextType.js

@@ -5,6 +5,6 @@
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.ContextType = void 0;
 exports.ContextType = {
-    Temporary: "temporary",
     Persistent: "persistent",
+    Temporary: "temporary",
 };

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

@@ -2,4 +2,4 @@
  * This file was auto-generated by Fern from our API Definition.
  */
 import * as Hume from "../../../index";
-export type JsonMessage = Hume.empathicVoice.AssistantEnd | Hume.empathicVoice.AssistantMessage | Hume.empathicVoice.ChatMetadata | Hume.empathicVoice.WebSocketError | Hume.empathicVoice.UserInterruption | Hume.empathicVoice.UserMessage | Hume.empathicVoice.ToolCallMessage | Hume.empathicVoice.ToolResponseMessage | Hume.empathicVoice.ToolErrorMessage | Hume.empathicVoice.AssistantProsody;
+export type JsonMessage = Hume.empathicVoice.AssistantEnd | Hume.empathicVoice.AssistantMessage | Hume.empathicVoice.AssistantProsody | Hume.empathicVoice.ChatMetadata | Hume.empathicVoice.WebSocketError | Hume.empathicVoice.UserInterruption | Hume.empathicVoice.UserMessage | Hume.empathicVoice.ToolCallMessage | Hume.empathicVoice.ToolResponseMessage | Hume.empathicVoice.ToolErrorMessage;

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

@@ -45,7 +45,8 @@ export interface ReturnConfig {
      * Hume's eLLM (empathic Large Language Model) is a multimodal language model that takes into account both expression measures and language. The eLLM generates short, empathic language responses and guides text-to-speech (TTS) prosody.
      */
     ellmModel?: Hume.empathicVoice.ReturnEllmModel;
-    voice?: unknown;
+    /** A voice specification associated with this Config. */
+    voice?: Hume.empathicVoice.ReturnVoice;
     prompt?: Hume.empathicVoice.ReturnPrompt;
     /** Map of webhooks associated with this config. */
     webhooks?: (Hume.empathicVoice.ReturnWebhookSpec | undefined)[];

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

@@ -0,0 +1,12 @@
+/**
+ * This file was auto-generated by Fern from our API Definition.
+ */
+import * as Hume from "../../../index";
+/**
+ * An Octave voice available for text-to-speech
+ */
+export interface ReturnVoice {
+    id?: string;
+    name?: string;
+    provider?: Hume.empathicVoice.VoiceProvider;
+}

package/api/resources/empathicVoice/types/ReturnVoice.js

@@ -0,0 +1,5 @@
+"use strict";
+/**
+ * This file was auto-generated by Fern from our API Definition.
+ */
+Object.defineProperty(exports, "__esModule", { value: true });

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

@@ -1,9 +1,8 @@
 /**
  * This file was auto-generated by Fern from our API Definition.
  */
-export type VoiceProvider = "HUME_AI" | "CUSTOM_VOICE" | "OCTAVE_COMBINED";
+export type VoiceProvider = "HUME_AI" | "CUSTOM_VOICE";
 export declare const VoiceProvider: {
     readonly HumeAi: "HUME_AI";
     readonly CustomVoice: "CUSTOM_VOICE";
-    readonly OctaveCombined: "OCTAVE_COMBINED";
 };

package/api/resources/empathicVoice/types/VoiceProvider.js

@@ -7,5 +7,4 @@ exports.VoiceProvider = void 0;
 exports.VoiceProvider = {
     HumeAi: "HUME_AI",
     CustomVoice: "CUSTOM_VOICE",
-    OctaveCombined: "OCTAVE_COMBINED",
 };

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

@@ -38,6 +38,8 @@ export * from "./LanguageModelType";
 export * from "./ModelProviderEnum";
 export * from "./ValidationErrorLocItem";
 export * from "./ValidationError";
+export * from "./VoiceId";
+export * from "./VoiceName";
 export * from "./WebhookEventChatEnded";
 export * from "./WebhookEventChatStartType";
 export * from "./WebhookEventChatStarted";
@@ -102,7 +104,6 @@ export * from "./PostedEventMessageSpec";
 export * from "./PostedTimeoutSpec";
 export * from "./ReturnEventMessageSpec";
 export * from "./ReturnTimeoutSpec";
-export * from "./VoiceProvider";
-export * from "./VoiceId";
-export * from "./VoiceName";
 export * from "./VoiceRef";
+export * from "./ReturnVoice";
+export * from "./VoiceProvider";

package/api/resources/empathicVoice/types/index.js

@@ -54,6 +54,8 @@ __exportStar(require("./LanguageModelType"), exports);
 __exportStar(require("./ModelProviderEnum"), exports);
 __exportStar(require("./ValidationErrorLocItem"), exports);
 __exportStar(require("./ValidationError"), exports);
+__exportStar(require("./VoiceId"), exports);
+__exportStar(require("./VoiceName"), exports);
 __exportStar(require("./WebhookEventChatEnded"), exports);
 __exportStar(require("./WebhookEventChatStartType"), exports);
 __exportStar(require("./WebhookEventChatStarted"), exports);
@@ -118,7 +120,6 @@ __exportStar(require("./PostedEventMessageSpec"), exports);
 __exportStar(require("./PostedTimeoutSpec"), exports);
 __exportStar(require("./ReturnEventMessageSpec"), exports);
 __exportStar(require("./ReturnTimeoutSpec"), exports);
-__exportStar(require("./VoiceProvider"), exports);
-__exportStar(require("./VoiceId"), exports);
-__exportStar(require("./VoiceName"), exports);
 __exportStar(require("./VoiceRef"), exports);
+__exportStar(require("./ReturnVoice"), exports);
+__exportStar(require("./VoiceProvider"), exports);

package/api/resources/tts/client/Client.d.ts

@@ -44,10 +44,6 @@ export declare class Tts {
      *
      * @example
      *     await client.tts.synthesizeJson({
-     *         utterances: [{
-     *                 text: "Beauty is no quality in things themselves: It exists merely in 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, academic quality."
-     *             }],
      *         context: {
      *             utterances: [{
      *                     text: "How can people see beauty so differently?",
@@ -57,7 +53,11 @@ export declare class Tts {
      *         format: {
      *             type: "mp3"
      *         },
-     *         numGenerations: 1
+     *         numGenerations: 1,
+     *         utterances: [{
+     *                 text: "Beauty is no quality in things themselves: It exists merely in 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, academic quality."
+     *             }]
      *     })
      */
     synthesizeJson(request: Hume.tts.PostedTts, requestOptions?: Tts.RequestOptions): core.HttpResponsePromise<Hume.tts.ReturnTts>;