🌿 Fern Regeneration -- July 7, 2025

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

@@ -2571,10 +2571,12 @@ types:
     properties:
       enabled:
         type: optional<boolean>
-        docs: EVI will nudge user after inactivity
+        docs: >-
+          If true, EVI will 'nudge' the user to speak after a determined
+          interval of silence.
       interval_secs:
         type: optional<integer>
-        docs: Time interval in seconds after which the nudge will be sent.
+        docs: The interval of inactivity (in seconds) before a nudge is triggered.
     source:
       openapi: evi-openapi.json
   PostedTimeoutSpecsInactivity:

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

@@ -47,14 +47,6 @@ channel:
 
         Include this parameter to apply a specific version of an EVI
         configuration. If omitted, the latest version will be applied.
-    enable_context_injection:
-      type: optional<boolean>
-      default: true
-      docs: >-
-        A flag to enable context injection. Set this query parameter to true to
-        have EVI inject context into the conversation. This is useful for
-        scenarios where you want to provide additional information to EVI to
-        help it better understand the user's request.
     event_limit:
       type: optional<integer>
       docs: >-

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

@@ -202,7 +202,13 @@ service:
               type: optional<list<optional<root.PostedBuiltinTool>>>
               docs: List of built-in tools associated with this Config.
             event_messages: optional<root.PostedEventMessageSpecs>
-            nudges: optional<root.PostedNudgeSpec>
+            nudges:
+              type: optional<root.PostedNudgeSpec>
+              docs: >-
+                Configures nudges, brief audio prompts that can guide
+                conversations when users pause or need encouragement to continue
+                speaking. Nudges help create more natural, flowing interactions
+                by providing gentle conversational cues. 
             timeouts: optional<root.PostedTimeoutSpecs>
             webhooks:
               type: optional<list<optional<root.PostedWebhookSpec>>>

.mock/definition/tts/__package__.yml

@@ -392,22 +392,19 @@ types:
           see our documentation on [instant
           mode](/docs/text-to-speech-tts/overview#ultra-low-latency-streaming-instant-mode). 
 
-          - Dynamic voice generation is not supported with this mode; a
-          predefined
+          - A
           [voice](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.utterances.voice)
-          must be specified in your request.
+          must be specified when instant mode is enabled. Dynamic voice
+          generation is not supported with this mode.
 
-          - This mode is only supported for streaming endpoints (e.g.,
+          - Instant 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)).
 
           - Ensure only a single generation is requested
           ([num_generations](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.num_generations)
           must be `1` or omitted).
-
-          - With `instant_mode` enabled, **requests incur a 10% higher cost**
-          due to increased compute and resource requirements.
-        default: false
+        default: true
     source:
       openapi: tts-openapi.yml
   ReturnTts:
@@ -515,14 +512,20 @@ types:
         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
-          accent').
+          and accent.
 
-          - If a Voice is specified in the request, this description serves as
-          acting instructions. For tips on how to effectively guide speech
-          delivery, see our guide on [Acting
+
+          **This field behaves differently depending on whether a voice is
+          specified**:
+
+          - **Voice specified**: the description will serve as acting directions
+          for delivery. Keep directions concise—100 characters or fewer—for best
+          results. 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.
+
+          - **Voice not specified**: the description will serve as a voice
+          prompt for generating a voice. See our [prompting
+          guide](/docs/text-to-speech-tts/prompting) for design tips.
         validation:
           maxLength: 1000
       speed:

package.json

@@ -1,6 +1,6 @@
 {
     "name": "hume",
-    "version": "0.11.4",
+    "version": "0.11.5",
     "private": false,
     "repository": "https://github.com/HumeAI/hume-typescript-sdk",
     "main": "./index.js",

src/api/resources/empathicVoice/resources/configs/client/requests/PostedConfig.ts

@@ -65,6 +65,7 @@ export interface PostedConfig {
     /** List of built-in tools associated with this Config. */
     builtinTools?: (Hume.empathicVoice.PostedBuiltinTool | undefined)[];
     eventMessages?: Hume.empathicVoice.PostedEventMessageSpecs;
+    /** Configures nudges, brief audio prompts that can guide conversations when users pause or need encouragement to continue speaking. Nudges help create more natural, flowing interactions by providing gentle conversational cues. */
     nudges?: Hume.empathicVoice.PostedNudgeSpec;
     timeouts?: Hume.empathicVoice.PostedTimeoutSpecs;
     /** Webhook config specifications for each subscriber. */

src/api/resources/empathicVoice/types/PostedNudgeSpec.ts

@@ -6,8 +6,8 @@
  * A nudge specification posted to the server
  */
 export interface PostedNudgeSpec {
-    /** EVI will nudge user after inactivity */
+    /** If true, EVI will 'nudge' the user to speak after a determined interval of silence. */
     enabled?: boolean;
-    /** Time interval in seconds after which the nudge will be sent. */
+    /** The interval of inactivity (in seconds) before a nudge is triggered. */
     intervalSecs?: number;
 }

src/api/resources/tts/types/PostedTts.ts

@@ -31,10 +31,9 @@ export interface PostedTts {
     utterances: Hume.tts.PostedUtterance[];
     /**
      * Enables ultra-low latency streaming, significantly reducing the time until the first audio chunk is received. Recommended for real-time applications requiring immediate audio playback. For further details, see our documentation on [instant 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) must be specified in your request.
-     * - 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)).
+     * - A [voice](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.utterances.voice) must be specified when instant mode is enabled. Dynamic voice generation is not supported with this mode.
+     * - Instant 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)).
      * - Ensure only a single generation is requested ([num_generations](/reference/text-to-speech-tts/synthesize-json-streaming#request.body.num_generations) must be `1` or omitted).
-     * - With `instant_mode` enabled, **requests incur a 10% higher cost** due to increased compute and resource requirements.
      */
     instantMode?: boolean;
 }

src/api/resources/tts/types/PostedUtterance.ts

@@ -6,9 +6,11 @@ import * as Hume from "../../../index";
 
 export interface PostedUtterance {
     /**
-     * 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 accent').
-     * - If a Voice is specified in the request, this description serves as 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.
+     * Natural language instructions describing how the synthesized speech should sound, including but not limited to tone, intonation, pacing, and accent.
+     *
+     * **This field behaves differently depending on whether a voice is specified**:
+     * - **Voice specified**: the description will serve as acting directions for delivery. Keep directions concise—100 characters or fewer—for best results. See our guide on [acting instructions](/docs/text-to-speech-tts/acting-instructions).
+     * - **Voice not specified**: the description will serve as a voice prompt for generating a voice. See our [prompting guide](/docs/text-to-speech-tts/prompting) for design tips.
      */
     description?: string;
     /** Speed multiplier for the synthesized speech. */

src/version.ts

@@ -1 +1 @@
-export const SDK_VERSION = "0.11.4";
+export const SDK_VERSION = "0.11.5";