Empathic Voice Interface (EVI)Configs

Create config

Creates a Config which can be applied to EVI.

For more details on configuration options and how to configure EVI, see our configuration guide.

Headers

X-Hume-Api-KeystringRequired

Request

This endpoint expects an object.
evi_versionstringRequired

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.

namestringRequired
Name applied to all versions of a particular Config.
version_descriptionstringOptional
An optional description of the Config version.
promptobjectOptional
Identifies which prompt to use in a a config OR how to create a new prompt to use in the config
voiceobjectOptional
A voice specification associated with this Config.
language_modelobjectOptional

The supplemental language model associated with this Config.

This model is used to generate longer, more detailed responses from EVI. Choosing an appropriate supplemental language model for your use case is crucial for generating fast, high-quality responses from EVI.

ellm_modelobjectOptional

The eLLM setup associated with this Config.

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.

toolslist of objectsOptional

List of user-defined tools associated with this Config.

builtin_toolslist of objectsOptional

List of built-in tools associated with this Config.

event_messagesobjectOptional
Collection of event messages returned by the server. Event messages are sent by the server when specific events occur during a chat session. These messages are used to configure behaviors for EVI, such as controlling how EVI starts a new conversation.
nudgesobjectOptional
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.
timeoutsobjectOptional

Collection of timeout specifications returned by the server.

Timeouts are sent by the server when specific time-based events occur during a chat session. These specifications set the inactivity timeout and the maximum duration an EVI WebSocket connection can stay open before it is automatically disconnected.

webhookslist of objectsOptional
Webhook config specifications for each subscriber.

Response

Created
idstring or null
Identifier for a Config. Formatted as a UUID.
versioninteger or null
Version number for a Config. Configs, Prompts, Custom Voices, 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 Config. Each update to the Config increments its version number.
evi_versionstring or null

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.

version_descriptionstring or null
An optional description of the Config version.
namestring or null
Name applied to all versions of a particular Config.
created_onlong or null
Time at which the Config was created. Measured in seconds since the Unix epoch.
modified_onlong or null
Time at which the Config was last modified. Measured in seconds since the Unix epoch.
promptobject or null
A Prompt associated with this Config.
voiceobject or null
A voice specification associated with this Config.
language_modelobject or null

The supplemental language model associated with this Config.

This model is used to generate longer, more detailed responses from EVI. Choosing an appropriate supplemental language model for your use case is crucial for generating fast, high-quality responses from EVI.

ellm_modelobject or null

The eLLM setup associated with this Config.

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.

toolslist of objects or null

List of user-defined tools associated with this Config.

builtin_toolslist of objects or null

List of built-in tools associated with this Config.

event_messagesobject or null
Collection of event messages returned by the server. Event messages are sent by the server when specific events occur during a chat session. These messages are used to configure behaviors for EVI, such as controlling how EVI starts a new conversation.
timeoutsobject or null

Collection of timeout specifications returned by the server.

Timeouts are sent by the server when specific time-based events occur during a chat session. These specifications set the inactivity timeout and the maximum duration an EVI WebSocket connection can stay open before it is automatically disconnected.

nudgesobject or null
A specific nudge configuration returned from the server
webhookslist of objects or null
Map of webhooks associated with this config.