hume 0.11.5-beta.2 → 0.12.1

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

@@ -1004,6 +1004,7 @@ types:
       - type: ToolCallMessage
       - type: ToolResponseMessage
       - type: ToolErrorMessage
+      - type: AssistantProsody
     source:
       openapi: evi-asyncapi.json
   HTTPValidationError:
@@ -1388,7 +1389,7 @@ types:
 
 
           For help writing a system prompt, see our [Prompting
-          Guide](/docs/empathic-voice-interface-evi/guides/prompting).
+          Guide](/docs/speech-to-speech-evi/guides/prompting).
       version:
         type: integer
         docs: >-
@@ -1424,363 +1425,6 @@ types:
         docs: An optional description of the Prompt version.
     source:
       openapi: evi-openapi.json
-  ReturnPagedCustomVoices:
-    docs: A paginated list of custom voices returned from the server
-    properties:
-      page_number:
-        type: 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: 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: integer
-        docs: The total number of pages in the collection.
-      custom_voices_page:
-        docs: List of Custom Voices for the specified `page_number` and `page_size`.
-        type: list<ReturnCustomVoice>
-    source:
-      openapi: evi-openapi.json
-  PostedCustomVoiceBaseVoice:
-    enum:
-      - ITO
-      - KORA
-      - DACHER
-      - AURA
-      - FINN
-      - WHIMSY
-      - STELLA
-      - SUNNY
-    docs: Specifies the base voice used to create the Custom Voice.
-    inline: true
-    source:
-      openapi: evi-openapi.json
-  PostedCustomVoiceParameters:
-    docs: >-
-      The specified attributes of a Custom Voice. 
-
-
-      If no parameters are specified then all attributes will be set to their
-      defaults, meaning no modfications will be made to the base voice.
-    properties:
-      gender:
-        type: optional<integer>
-        docs: >-
-          The perceived tonality of the voice, reflecting characteristics
-          typically associated with masculinity and femininity.
-
-
-          The default value is `0`, with a minimum of `-100` (more masculine)
-          and a maximum of `100` (more feminine). A value of `0` leaves this
-          parameter unchanged from the base voice.
-      assertiveness:
-        type: optional<integer>
-        docs: >-
-          The perceived firmness of the voice, ranging between whiny and bold.
-
-
-          The default value is `0`, with a minimum of `-100` (whiny) and a
-          maximum of `100` (bold). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      buoyancy:
-        type: optional<integer>
-        docs: >-
-          The perceived density of the voice, ranging between deflated and
-          buoyant.
-
-
-          The default value is `0`, with a minimum of `-100` (deflated) and a
-          maximum of `100` (buoyant). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      confidence:
-        type: optional<integer>
-        docs: >-
-          The perceived assuredness of the voice, ranging between shy and
-          confident.
-
-
-          The default value is `0`, with a minimum of `-100` (shy) and a maximum
-          of `100` (confident). A value of `0` leaves this parameter unchanged
-          from the base voice.
-      enthusiasm:
-        type: optional<integer>
-        docs: >-
-          The perceived excitement within the voice, ranging between calm and
-          enthusiastic.
-
-
-          The default value is `0`, with a minimum of `-100` (calm) and a
-          maximum of `100` (enthusiastic). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      nasality:
-        type: optional<integer>
-        docs: >-
-          The perceived openness of the voice, ranging between clear and nasal.
-
-
-          The default value is `0`, with a minimum of `-100` (clear) and a
-          maximum of `100` (nasal). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      relaxedness:
-        type: optional<integer>
-        docs: >-
-          The perceived stress within the voice, ranging between tense and
-          relaxed.
-
-
-          The default value is `0`, with a minimum of `-100` (tense) and a
-          maximum of `100` (relaxed). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      smoothness:
-        type: optional<integer>
-        docs: >-
-          The perceived texture of the voice, ranging between smooth and
-          staccato.
-
-
-          The default value is `0`, with a minimum of `-100` (smooth) and a
-          maximum of `100` (staccato). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      tepidity:
-        type: optional<integer>
-        docs: >-
-          The perceived liveliness behind the voice, ranging between tepid and
-          vigorous.
-
-
-          The default value is `0`, with a minimum of `-100` (tepid) and a
-          maximum of `100` (vigorous). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      tightness:
-        type: optional<integer>
-        docs: >-
-          The perceived containment of the voice, ranging between tight and
-          breathy.
-
-
-          The default value is `0`, with a minimum of `-100` (tight) and a
-          maximum of `100` (breathy). A value of `0` leaves this parameter
-          unchanged from the base voice.
-    source:
-      openapi: evi-openapi.json
-    inline: true
-  PostedCustomVoice:
-    docs: >-
-      A Custom Voice specification to be associated with this Config.
-
-
-      If a Custom Voice specification is not provided then the
-      [name](/reference/empathic-voice-interface-evi/configs/create-config#request.body.voice.name)
-      of a base voice or previously created Custom Voice must be provided.
-
-       See our [Voices guide](/docs/empathic-voice-interface-evi/configuration/voices) for a tutorial on how to craft a Custom Voice.
-    properties:
-      name:
-        type: string
-        docs: >-
-          The name of the Custom Voice. Maximum length of 75 characters. Will be
-          converted to all-uppercase. (e.g., "sample voice" becomes "SAMPLE
-          VOICE")
-      base_voice:
-        type: PostedCustomVoiceBaseVoice
-        docs: Specifies the base voice used to create the Custom Voice.
-      parameter_model:
-        type: literal<"20241004-11parameter">
-        docs: >-
-          The name of the parameter model used to define which attributes are
-          used by the `parameters` field. Currently, only `20241004-11parameter`
-          is supported as the parameter model.
-      parameters:
-        type: optional<PostedCustomVoiceParameters>
-        docs: >-
-          The specified attributes of a Custom Voice. 
-
-
-          If no parameters are specified then all attributes will be set to
-          their defaults, meaning no modfications will be made to the base
-          voice.
-    source:
-      openapi: evi-openapi.json
-  ReturnCustomVoiceBaseVoice:
-    enum:
-      - ITO
-      - KORA
-      - DACHER
-      - AURA
-      - FINN
-      - WHIMSY
-      - STELLA
-      - SUNNY
-    docs: The base voice used to create the Custom Voice.
-    inline: true
-    source:
-      openapi: evi-openapi.json
-  ReturnCustomVoiceParameters:
-    docs: >-
-      The specified attributes of a Custom Voice. If a parameter's value is `0`
-      (default), it will not be included in the response.
-    properties:
-      gender:
-        type: optional<integer>
-        docs: >-
-          The perceived tonality of the voice, reflecting characteristics
-          typically associated with masculinity and femininity.
-
-
-          The default value is `0`, with a minimum of `-100` (more masculine)
-          and a maximum of `100` (more feminine). A value of `0` leaves this
-          parameter unchanged from the base voice.
-      assertiveness:
-        type: optional<integer>
-        docs: >-
-          The perceived firmness of the voice, ranging between whiny and bold.
-
-
-          The default value is `0`, with a minimum of `-100` (whiny) and a
-          maximum of `100` (bold). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      buoyancy:
-        type: optional<integer>
-        docs: >-
-          The perceived density of the voice, ranging between deflated and
-          buoyant.
-
-
-          The default value is `0`, with a minimum of `-100` (deflated) and a
-          maximum of `100` (buoyant). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      confidence:
-        type: optional<integer>
-        docs: >-
-          The perceived assuredness of the voice, ranging between shy and
-          confident.
-
-
-          The default value is `0`, with a minimum of `-100` (shy) and a maximum
-          of `100` (confident). A value of `0` leaves this parameter unchanged
-          from the base voice.
-      enthusiasm:
-        type: optional<integer>
-        docs: >-
-          The perceived excitement within the voice, ranging between calm and
-          enthusiastic.
-
-
-          The default value is `0`, with a minimum of `-100` (calm) and a
-          maximum of `100` (enthusiastic). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      nasality:
-        type: optional<integer>
-        docs: >-
-          The perceived openness of the voice, ranging between clear and nasal.
-
-
-          The default value is `0`, with a minimum of `-100` (clear) and a
-          maximum of `100` (nasal). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      relaxedness:
-        type: optional<integer>
-        docs: >-
-          The perceived stress within the voice, ranging between tense and
-          relaxed.
-
-
-          The default value is `0`, with a minimum of `-100` (tense) and a
-          maximum of `100` (relaxed). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      smoothness:
-        type: optional<integer>
-        docs: >-
-          The perceived texture of the voice, ranging between smooth and
-          staccato.
-
-
-          The default value is `0`, with a minimum of `-100` (smooth) and a
-          maximum of `100` (staccato). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      tepidity:
-        type: optional<integer>
-        docs: >-
-          The perceived liveliness behind the voice, ranging between tepid and
-          vigorous.
-
-
-          The default value is `0`, with a minimum of `-100` (tepid) and a
-          maximum of `100` (vigorous). A value of `0` leaves this parameter
-          unchanged from the base voice.
-      tightness:
-        type: optional<integer>
-        docs: >-
-          The perceived containment of the voice, ranging between tight and
-          breathy.
-
-
-          The default value is `0`, with a minimum of `-100` (tight) and a
-          maximum of `100` (breathy). A value of `0` leaves this parameter
-          unchanged from the base voice.
-    source:
-      openapi: evi-openapi.json
-    inline: true
-  ReturnCustomVoice:
-    docs: A Custom Voice specification associated with this Config.
-    properties:
-      id:
-        type: string
-        docs: Identifier for a Custom Voice. Formatted as a UUID.
-      version:
-        type: integer
-        docs: >-
-          Version number for a Custom Voice.
-
-
-          Custom Voices, Prompts, Configs, and Tools are versioned. This
-          versioning system supports iterative development, allowing you to
-          progressively refine configurations and revert to previous versions if
-          needed.
-
-
-          Version numbers are integer values representing different iterations
-          of the Custom Voice. Each update to the Custom Voice increments its
-          version number.
-      name:
-        type: string
-        docs: The name of the Custom Voice. Maximum length of 75 characters.
-      created_on:
-        type: long
-        docs: >-
-          Time at which the Custom Voice was created. Measured in seconds since
-          the Unix epoch.
-      modified_on:
-        type: long
-        docs: >-
-          Time at which the Custom Voice was last modified. Measured in seconds
-          since the Unix epoch.
-      base_voice:
-        type: ReturnCustomVoiceBaseVoice
-        docs: The base voice used to create the Custom Voice.
-      parameter_model:
-        type: literal<"20241004-11parameter">
-        docs: >-
-          The name of the parameter model used to define which attributes are
-          used by the `parameters` field. Currently, only `20241004-11parameter`
-          is supported as the parameter model.
-      parameters:
-        type: ReturnCustomVoiceParameters
-        docs: >-
-          The specified attributes of a Custom Voice. If a parameter's value is
-          `0` (default), it will not be included in the response.
-    source:
-      openapi: evi-openapi.json
   ReturnPagedConfigs:
     docs: A paginated list of config versions returned from the server
     properties:
@@ -1840,7 +1484,7 @@ types:
           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/empathic-voice-interface-evi/configuration/evi-version).
+          [guide](/docs/speech-to-speech-evi/configuration/evi-version).
       timeouts: optional<ReturnTimeoutSpecs>
       nudges: optional<ReturnNudgeSpec>
       ellm_model:
@@ -1853,9 +1497,7 @@ 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:
-        type: optional<ReturnVoice>
-        docs: A voice specification associated with this Config.
+      voice: optional<unknown>
       prompt: optional<ReturnPrompt>
       tools:
         type: optional<list<optional<ReturnUserDefinedTool>>>
@@ -2517,7 +2159,7 @@ types:
 
 
       For more information, see our guide on [using built-in
-      tools](/docs/empathic-voice-interface-evi/features/tool-use#using-built-in-tools).
+      tools](/docs/speech-to-speech-evi/features/tool-use#using-built-in-tools).
     inline: true
     source:
       openapi: evi-openapi.json
@@ -2539,7 +2181,7 @@ types:
 
 
           For more information, see our guide on [using built-in
-          tools](/docs/empathic-voice-interface-evi/features/tool-use#using-built-in-tools).
+          tools](/docs/speech-to-speech-evi/features/tool-use#using-built-in-tools).
       fallback_content:
         type: optional<string>
         docs: >-
@@ -2715,20 +2357,11 @@ types:
 
 
           See our [webhooks
-          guide](/docs/empathic-voice-interface-evi/configuration/build-a-configuration#supported-events)
+          guide](/docs/speech-to-speech-evi/configuration/build-a-configuration#supported-events)
           for more information on supported events.
         type: list<PostedWebhookEventType>
     source:
       openapi: evi-openapi.json
-  ReturnVoiceSpec:
-    discriminated: false
-    docs: An voice specification posted to the server
-    union:
-      - ReturnVoiceSpecEvi2
-      - ReturnVoiceSpecOctavecustom
-      - ReturnVoiceSpecOctaveshared
-    source:
-      openapi: evi-openapi.json
   ReturnLanguageModel:
     docs: A specific LanguageModel
     properties:
@@ -2898,7 +2531,7 @@ types:
 
 
           See our [webhooks
-          guide](/docs/empathic-voice-interface-evi/configuration/build-a-configuration#supported-events)
+          guide](/docs/speech-to-speech-evi/configuration/build-a-configuration#supported-events)
           for more information on supported events.
         type: list<ReturnWebhookEventType>
     source:
@@ -3210,48 +2843,6 @@ types:
         docs: Duration in seconds for the timeout.
     source:
       openapi: evi-openapi.json
-  ReturnVoiceSpecEvi2:
-    docs: A specific voice specification for use with EVI 1 or 2
-    properties:
-      provider:
-        type: string
-        docs: The provider of the voice to use. Based on the enum VoiceProvider.
-      name:
-        type: optional<string>
-        docs: >-
-          String with the name of the voice to use. Maximum length of 75
-          characters. Will be converted to all-uppercase.
-      custom_voice: ReturnCustomVoice
-    source:
-      openapi: evi-openapi.json
-  ReturnVoiceSpecOctavecustom:
-    docs: A specific voice specification for an Octave voice
-    properties:
-      provider:
-        type: string
-        docs: The provider of the voice to use. Based on the enum VoiceProvider.
-      name:
-        type: optional<string>
-        docs: >-
-          String with the name of the voice to use. Maximum length of 75
-          characters. Will be converted to all-uppercase.
-      custom_voice: optional<ReturnVoiceOctaveCustom>
-    source:
-      openapi: evi-openapi.json
-  ReturnVoiceSpecOctaveshared:
-    docs: A specific voice specification for an Octave voice
-    properties:
-      provider:
-        type: string
-        docs: The provider of the voice to use. Based on the enum VoiceProvider.
-      name:
-        type: optional<string>
-        docs: >-
-          String with the name of the voice to use. Maximum length of 75
-          characters. Will be converted to all-uppercase.
-      custom_voice: optional<ReturnVoiceOctaveShared>
-    source:
-      openapi: evi-openapi.json
   ReturnEventMessageSpec:
     docs: A specific event message configuration to be returned from the server
     properties:
@@ -3291,116 +2882,36 @@ types:
           minutes).
     source:
       openapi: evi-openapi.json
-  ReturnVoiceOctaveCustom:
-    docs: An octave custom voice specification returned from the server
-    properties:
-      id: optional<string>
-      version: optional<integer>
-      name: optional<string>
-      description: optional<string>
-      voice_type: optional<string>
-      created_on: optional<long>
-      modified_on: optional<long>
-      voice_prompt: optional<string>
-      normalization_gain_db: optional<double>
-      speaker_embedding: optional<string>
-      reference_uri: optional<string>
-      reference_audio_format: optional<string>
-      clone_reference_uri: optional<string>
-      clone_reference_audio_format: optional<string>
-      reference_tokens: optional<string>
-      reference_atoks: optional<string>
-      reference_decoder_dtoks: optional<string>
-      reference_text: optional<string>
-      signed_preview_reference_uri: optional<ReturnSignedUri>
-      signed_clone_reference_uri: optional<ReturnSignedUri>
-      image_uri: optional<string>
-      disabled: optional<boolean>
-    source:
-      openapi: evi-openapi.json
-  ReturnVoiceOctaveShared:
-    docs: An octave shared voice specification returned from the server
-    properties:
-      id: optional<string>
-      version: optional<integer>
-      name: optional<string>
-      description: optional<string>
-      reference_signed_uri: optional<ReturnSignedUri>
-      image_uri: optional<string>
-    source:
-      openapi: evi-openapi.json
-  ReturnSignedUri:
-    docs: A signed URI linking to a file in GCS
-    properties:
-      filename: optional<string>
-      method: optional<string>
-      signed_uri: optional<string>
-      expiration_timestamp_millis: optional<long>
-    source:
-      openapi: evi-openapi.json
-  PostedVoiceProvider:
+  VoiceProvider:
     enum:
       - HUME_AI
       - CUSTOM_VOICE
-    docs: >-
-      The provider of the voice to use. Supported values are `HUME_AI` and
-      `CUSTOM_VOICE`.
-    inline: true
     source:
       openapi: evi-openapi.json
-  PostedVoice:
-    docs: A Voice specification posted to the server
+  VoiceId:
     properties:
+      id:
+        type: string
+        docs: ID of the voice in the `Voice Library`.
       provider:
-        type: PostedVoiceProvider
-        docs: >-
-          The provider of the voice to use. Supported values are `HUME_AI` and
-          `CUSTOM_VOICE`.
-      name:
-        type: optional<string>
-        docs: >-
-          Specifies the name of the voice to use.
-
-
-          This can be either the name of a previously created Custom Voice or
-          one of our 8 base voices: `ITO`, `KORA`, `DACHER`, `AURA`, `FINN`,
-          `WHIMSY`, `STELLA`, or `SUNNY`.
-
-
-          The name will be automatically converted to uppercase (e.g., "Ito"
-          becomes "ITO"). If a name is not specified, then a [Custom
-          Voice](/reference/empathic-voice-interface-evi/configs/create-config#request.body.voice.custom_voice)
-          specification must be provided.
-      custom_voice: optional<PostedCustomVoice>
+        type: optional<VoiceProvider>
+        docs: Model provider associated with this Voice ID.
     source:
       openapi: evi-openapi.json
-  ReturnVoiceProvider:
-    enum:
-      - HUME_AI
-      - CUSTOM_VOICE
-    docs: >-
-      The provider of the voice to use. Supported values are `HUME_AI` and
-      `CUSTOM_VOICE`.
-    inline: true
-    source:
-      openapi: evi-openapi.json
-  ReturnVoice:
-    docs: A specific voice specification
+  VoiceName:
     properties:
-      provider:
-        type: ReturnVoiceProvider
-        docs: >-
-          The provider of the voice to use. Supported values are `HUME_AI` and
-          `CUSTOM_VOICE`.
       name:
-        type: optional<string>
-        docs: >-
-          The name of the specified voice.
-
-
-          This will either be the name of a previously created Custom Voice or
-          one of our 8 base voices: `ITO`, `KORA`, `DACHER`, `AURA`, `FINN`,
-          `WHIMSY`, `STELLA`, or `SUNNY`.
-      custom_voice: optional<ReturnCustomVoice>
+        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:
+      - type: VoiceId
+      - type: VoiceName
     source:
       openapi: evi-openapi.json

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

@@ -551,7 +551,7 @@ service:
       docs: >-
         Fetches a paginated list of audio for each **Chat** within the specified
         **Chat Group**. For more details, see our guide on audio reconstruction
-        [here](/docs/empathic-voice-interface-evi/faq#can-i-access-the-audio-of-previous-conversations-with-evi).
+        [here](/docs/speech-to-speech-evi/faq#can-i-access-the-audio-of-previous-conversations-with-evi).
       source:
         openapi: evi-openapi.json
       path-parameters:

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

@@ -475,7 +475,7 @@ service:
       docs: >-
         Fetches the audio of a previous **Chat**. For more details, see our
         guide on audio reconstruction
-        [here](/docs/empathic-voice-interface-evi/faq#can-i-access-the-audio-of-previous-conversations-with-evi).
+        [here](/docs/speech-to-speech-evi/faq#can-i-access-the-audio-of-previous-conversations-with-evi).
       source:
         openapi: evi-openapi.json
       path-parameters: