> This page is for Voice APIs. > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://dev.hume.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://dev.hume.ai/_mcp/server. # Create config POST https://api.hume.ai/v0/evi/configs Content-Type: application/json Creates a **Config** which can be applied to EVI. For more details on configuration options and how to configure EVI, see our [configuration guide](/docs/speech-to-speech-evi/configuration). Reference: https://dev.hume.ai/voice/reference/speech-to-speech-evi/configs/create-config ## Authentication - `X-Hume-Api-Key` header (required) — API Key authentication via header ## Request ### Body (application/json) This endpoint expects a posted_config. - `evi_version` (string, required) — EVI version to use. Only versions `3` and `4-mini` are supported. - `name` (string, required) — Name applied to all versions of a particular Config. - `builtin_tools` (list of posted_builtin_tool, optional, nullable) — Built-in tool specification for a Config. - `ellm_model` (PostedConfigEllmModel, optional) — 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. - `event_messages` (PostedConfigEventMessages, optional) — Map of event messages associated with this config. - `interruption` (posted_interruption_spec, optional) — An interruption specification posted to the server - `language_model` (PostedConfigLanguageModel, optional) — 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. - `nudges` (PostedConfigNudges, optional) — 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. - `prompt` (PostedConfigPrompt, optional) — A Prompt associated with this Config. - `timeouts` (PostedConfigTimeouts, optional) — Map of timeouts associated with this config. - `tools` (list of posted_user_defined_tool_spec, optional, nullable) — Tool specification for a Config. - `turn_detection` (posted_turn_detection_spec, optional) — A turn detection specification posted to the server - `version_description` (string, optional, nullable) — An optional description of the Config version. - `voice` (VoiceRef, optional) — A voice specification associated with this Config. - `webhooks` (list of posted_webhook_spec, optional, nullable) — Webhook config specifications for each subscriber. ## Response ### 201 Created - `builtin_tools` (list of return_builtin_tool, optional, nullable) — List of built-in tools associated with this Config. - `created_on` (long, optional) — Time at which the Config was created. Measured in seconds since the Unix epoch. - `ellm_model` (return_ellm_model, optional) — A specific eLLM Model configuration - `event_messages` (return_event_message_specs, optional) — 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. - `evi_version` (string, optional) — Specifies the EVI version to use. See our [EVI Version Guide](/docs/speech-to-speech-evi/configuration/evi-version) for differences between versions. **We're officially sunsetting EVI versions 1 and 2 on August 30, 2025**. To keep things running smoothly, be sure to [migrate to EVI 3](/docs/speech-to-speech-evi/configuration/evi-version#migrating-to-evi-3) before then. - `id` (string, optional) — Identifier for a Config. Formatted as a UUID. - `interruption` (return_interruption_spec, optional) — An interruption configuration returned from the server - `language_model` (return_language_model, optional) — A specific LanguageModel - `modified_on` (long, optional) — Time at which the Config was last modified. Measured in seconds since the Unix epoch. - `name` (string, optional) — Name applied to all versions of a particular Config. - `nudges` (return_nudge_spec, optional) — A specific nudge configuration returned from the server - `prompt` (return_prompt_public, optional) — A specific prompt version returned from the server - `timeouts` (return_timeout_specs, optional) — 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. - `tools` (list of return_user_defined_tool, optional, nullable) — List of user-defined tools associated with this Config. - `turn_detection` (return_turn_detection_spec, optional) — A turn detection configuration returned from the server - `version` (integer, optional) — 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. - `version_description` (string, optional, nullable) — An optional description of the Config version. - `voice` (ReturnVoice, optional) — An Octave voice available for text-to-speech - `webhooks` (list of returned_webhook_spec, optional, nullable) — Map of webhooks associated with this config. ## Types ### posted_builtin_tool A configuration of a built-in tool to be posted to the server - `name` (enum, required) - Allowed values: `web_search`, `hang_up` - `fallback_content` (string, optional, nullable) — Optional text passed to the supplemental LLM in place of the tool call result. The LLM then uses this text to generate a response back to the user, ensuring continuity in the conversation if the Tool errors. ### PostedConfigEllmModel 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. - `allow_short_responses` (boolean, optional, nullable) — Boolean indicating if the eLLM is allowed to generate short responses (new EVI 3 configs default to disabled; new versions inherit prior value when omitted). ### PostedConfigEventMessages Map of event messages associated with this config. - `on_inactivity_timeout` (PostedConfigEventMessagesOnInactivityTimeout, optional) — Specifies the message EVI provides when the chat is about to be disconnected due to a user inactivity timeout, such as a message mentioning a lack of user input for a period of time. Enabling an inactivity message allows developers to use this message event for "checking in" with the user if they are not responding to see if they are still active. If the user does not respond in the number of seconds specified in the `inactivity_timeout` field, then EVI will say the message and the user has 15 seconds to respond. If they respond in time, the conversation will continue; if not, the conversation will end. However, if the inactivity message is not enabled, then reaching the inactivity timeout will immediately end the connection. - `on_max_duration_timeout` (PostedConfigEventMessagesOnMaxDurationTimeout, optional) — Specifies the message EVI provides when the chat is disconnected due to reaching the maximum chat duration, such as a message mentioning the time limit for the chat has been reached. - `on_new_chat` (PostedConfigEventMessagesOnNewChat, optional) — Specifies the initial message EVI provides when a new chat is started, such as a greeting or welcome message. ### posted_interruption_spec An interruption specification posted to the server - `min_interruption_ms` (integer, optional, nullable) — How long the user must speak while the agent is outputting audio before the agent stops and yields the floor. Lower values make the agent more responsive to the user speaking up, but increase the chance of noise or backchannels stopping the agent unnecessarily. Higher values make the agent harder to interrupt, allowing it to finish more of its response before yielding. Accepts values between 50 and 2000 milliseconds. ### PostedConfigLanguageModel 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. - `model_provider` (enum, optional) - Allowed values: `GROQ`, `OPEN_AI`, `FIREWORKS`, `ANTHROPIC`, `CUSTOM_LANGUAGE_MODEL`, `GOOGLE`, `HUME_AI`, `AMAZON_BEDROCK`, `PERPLEXITY`, `SAMBANOVA`, `CEREBRAS`, `X_AI` - `model_resource` (enum, optional) - Allowed values: `claude-3-7-sonnet-latest`, `claude-opus-4-6`, `claude-3-5-sonnet-latest`, `claude-3-5-haiku-latest`, `claude-3-5-sonnet-20240620`, `claude-3-opus-20240229`, `claude-3-sonnet-20240229`, `claude-3-haiku-20240307`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5-20250929`, `claude-haiku-4-5-20251001`, `us.anthropic.claude-3-5-haiku-20241022-v1:0`, `us.anthropic.claude-3-5-sonnet-20240620-v1:0`, `us.anthropic.claude-3-haiku-20240307-v1:0`, `gpt-oss-120b`, `qwen-3-235b-a22b`, `qwen-3-235b-a22b-instruct-2507`, `qwen-3-235b-a22b-thinking-2507`, `gemini-1.5-pro`, `gemini-1.5-flash`, `gemini-1.5-pro-002`, `gemini-1.5-flash-002`, `gemini-2.0-flash`, `gemini-2.5-flash`, `gemini-2.5-flash-preview-04-17`, `gpt-4-turbo`, `gpt-4-turbo-preview`, `gpt-3.5-turbo-0125`, `gpt-3.5-turbo`, `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-4o-priority`, `gpt-4o-mini-priority`, `gpt-4.1-priority`, `gpt-5-priority`, `gpt-5-mini-priority`, `gpt-5-nano-priority`, `gpt-5.1`, `gpt-5.1-priority`, `gpt-5.2`, `gpt-5.2-priority`, `gemma-7b-it`, `llama3-8b-8192`, `llama3-70b-8192`, `llama-3.1-70b-versatile`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `moonshotai/kimi-k2-instruct`, `accounts/fireworks/models/mixtral-8x7b-instruct`, `accounts/fireworks/models/llama-v3p1-405b-instruct`, `accounts/fireworks/models/llama-v3p1-70b-instruct`, `accounts/fireworks/models/llama-v3p1-8b-instruct`, `sonar`, `sonar-pro`, `sambanova`, `DeepSeek-R1-Distill-Llama-70B`, `Llama-4-Maverick-17B-128E-Instruct`, `Qwen3-32B`, `grok-4-fast-non-reasoning-latest`, `ellm`, `custom-language-model`, `hume-evi-3-web-search` - `temperature` (float, optional, nullable) — The model temperature, with values between 0 to 1 (inclusive). Controls the randomness of the LLM's output, with values closer to 0 yielding focused, deterministic responses and values closer to 1 producing more creative, diverse responses. ### PostedConfigNudges 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. - `enabled` (boolean, optional, nullable) — If true, EVI will 'nudge' the user to speak after a determined interval of silence. - `interval_secs` (integer, optional, nullable) — The interval of inactivity (in seconds) before a nudge is triggered. ### PostedConfigPrompt A Prompt associated with this Config. - `id` (string, optional, nullable) — Identifier for a Prompt. Formatted as a UUID. - `prompt_expansion` (prompt_expansion_spec, optional) — Configuration for prompt expansion behavior. - `text` (string, optional, nullable) — Text used to create a new prompt for a particular config. - `version` (integer, optional, nullable) — Version number for a Prompt. Version numbers should be integers. The combination of configId and version number is unique. ### PostedConfigTimeouts Map of timeouts associated with this config. - `inactivity` (PostedConfigTimeoutsInactivity, optional) - `max_duration` (PostedConfigTimeoutsMaxDuration, optional) ### posted_user_defined_tool_spec A specific tool identifier to be posted to the server - `id` (string, required) — Identifier for a Tool. Formatted as a UUID. - `version` (integer, optional, nullable) — Version number for a Tool. Version numbers should be integers. The combination of configId and version number is unique. ### posted_turn_detection_spec A turn detection specification posted to the server - `end_of_turn_silence_ms` (integer, optional, nullable) — How long the user must be silent before EVI considers their turn complete and begins generating a response. Lower values make conversations feel snappier but increase the chance of the agent responding during a mid-thought pause. Higher values give users more room to pause and collect their thoughts before the agent responds. Accepts values between 500 and 3000 milliseconds. - `prefix_padding_ms` (integer, optional, nullable) — The duration of audio captured before the detected start of speech. This ensures the beginning of an utterance is not clipped. Accepts values between 0 and 1000 milliseconds. - `speech_detection_threshold` (float, optional, nullable) — How confident the system must be that audio contains speech before it begins processing. Lower values increase sensitivity, capturing softer speech at the cost of more noise-triggered processing. Higher values require clearer, louder audio to register as speech. Accepts values between 0.0 and 1.0. ### VoiceRef ### posted_webhook_spec URL and settings for a specific webhook to be posted to the server - `events` (list of enum, required) — The list of events the specified URL is subscribed to. See our [webhooks guide](/docs/speech-to-speech-evi/configuration/build-a-configuration#supported-events) for more information on supported events. - Allowed values: `chat_started`, `chat_ended`, `tool_call` - `url` (string, required) — The URL where event payloads will be sent. This must be a valid https URL to ensure secure communication. The server at this URL must accept POST requests with a JSON payload. ### return_builtin_tool A specific builtin tool version returned from the server - `name` (string, required) — Name of the built-in tool to use. Hume supports the following built-in tools: - **web_search:** enables EVI to search the web for up-to-date information when applicable. - **hang_up:** closes the WebSocket connection when appropriate (e.g., after detecting a farewell in the conversation). For more information, see our guide on [using built-in tools](/docs/speech-to-speech-evi/features/tool-use#using-built-in-tools). - `tool_type` (enum, required) - Allowed values: `BUILTIN`, `FUNCTION` - `fallback_content` (string, optional, nullable) — Optional text passed to the supplemental LLM in place of the tool call result. The LLM then uses this text to generate a response back to the user, ensuring continuity in the conversation if the Tool errors. ### return_ellm_model A specific eLLM Model configuration - `allow_short_responses` (boolean, required) — Boolean indicating if the eLLM is allowed to generate short responses (new EVI 3 configs default to disabled; new versions inherit prior value when omitted). ### return_event_message_specs 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. - `on_inactivity_timeout` (return_event_message_spec, optional) — A specific event message configuration to be returned from the server - `on_max_duration_timeout` (return_event_message_spec, optional) — A specific event message configuration to be returned from the server - `on_new_chat` (return_event_message_spec, optional) — A specific event message configuration to be returned from the server ### return_interruption_spec An interruption configuration returned from the server - `min_interruption_ms` (integer, optional, nullable) — How long the user must speak while the agent is outputting audio before the agent stops and yields the floor. Lower values make the agent more responsive to the user speaking up, but increase the chance of noise or backchannels stopping the agent unnecessarily. Higher values make the agent harder to interrupt, allowing it to finish more of its response before yielding. Accepts values between 50 and 2000 milliseconds. ### return_language_model A specific LanguageModel - `model_provider` (enum, optional) - Allowed values: `GROQ`, `OPEN_AI`, `FIREWORKS`, `ANTHROPIC`, `CUSTOM_LANGUAGE_MODEL`, `GOOGLE`, `HUME_AI`, `AMAZON_BEDROCK`, `PERPLEXITY`, `SAMBANOVA`, `CEREBRAS`, `X_AI` - `model_resource` (enum, optional) - Allowed values: `claude-3-7-sonnet-latest`, `claude-opus-4-6`, `claude-3-5-sonnet-latest`, `claude-3-5-haiku-latest`, `claude-3-5-sonnet-20240620`, `claude-3-opus-20240229`, `claude-3-sonnet-20240229`, `claude-3-haiku-20240307`, `claude-sonnet-4-20250514`, `claude-sonnet-4-5-20250929`, `claude-haiku-4-5-20251001`, `us.anthropic.claude-3-5-haiku-20241022-v1:0`, `us.anthropic.claude-3-5-sonnet-20240620-v1:0`, `us.anthropic.claude-3-haiku-20240307-v1:0`, `gpt-oss-120b`, `qwen-3-235b-a22b`, `qwen-3-235b-a22b-instruct-2507`, `qwen-3-235b-a22b-thinking-2507`, `gemini-1.5-pro`, `gemini-1.5-flash`, `gemini-1.5-pro-002`, `gemini-1.5-flash-002`, `gemini-2.0-flash`, `gemini-2.5-flash`, `gemini-2.5-flash-preview-04-17`, `gpt-4-turbo`, `gpt-4-turbo-preview`, `gpt-3.5-turbo-0125`, `gpt-3.5-turbo`, `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `gpt-5`, `gpt-5-mini`, `gpt-5-nano`, `gpt-4o-priority`, `gpt-4o-mini-priority`, `gpt-4.1-priority`, `gpt-5-priority`, `gpt-5-mini-priority`, `gpt-5-nano-priority`, `gpt-5.1`, `gpt-5.1-priority`, `gpt-5.2`, `gpt-5.2-priority`, `gemma-7b-it`, `llama3-8b-8192`, `llama3-70b-8192`, `llama-3.1-70b-versatile`, `llama-3.3-70b-versatile`, `llama-3.1-8b-instant`, `moonshotai/kimi-k2-instruct`, `accounts/fireworks/models/mixtral-8x7b-instruct`, `accounts/fireworks/models/llama-v3p1-405b-instruct`, `accounts/fireworks/models/llama-v3p1-70b-instruct`, `accounts/fireworks/models/llama-v3p1-8b-instruct`, `sonar`, `sonar-pro`, `sambanova`, `DeepSeek-R1-Distill-Llama-70B`, `Llama-4-Maverick-17B-128E-Instruct`, `Qwen3-32B`, `grok-4-fast-non-reasoning-latest`, `ellm`, `custom-language-model`, `hume-evi-3-web-search` - `temperature` (float, optional, nullable) — The model temperature, with values between 0 to 1 (inclusive). Controls the randomness of the LLM's output, with values closer to 0 yielding focused, deterministic responses and values closer to 1 producing more creative, diverse responses. ### return_nudge_spec A specific nudge configuration returned from the server - `enabled` (boolean, required) — If true, EVI will 'nudge' the user to speak after a determined interval of silence. - `interval_secs` (integer, optional, nullable) — The interval of inactivity (in seconds) before a nudge is triggered. ### return_prompt_public A specific prompt version returned from the server - `created_on` (long, required) — Time at which the Prompt was created. Measured in seconds since the Unix epoch. - `id` (string, required) — Identifier for a Prompt. Formatted as a UUID. - `modified_on` (long, required) — Time at which the Prompt was last modified. Measured in seconds since the Unix epoch. - `name` (string, required) — Name applied to all versions of a particular Prompt. - `text` (string, required) — Instructions used to shape EVI's behavior, responses, and style. You can use the Prompt to define a specific goal or role for EVI, specifying how it should act or what it should focus on during the conversation. For example, EVI can be instructed to act as a customer support representative, a fitness coach, or a travel advisor, each with its own set of behaviors and response styles. For help writing a system prompt, see our [Prompting Guide](/docs/speech-to-speech-evi/guides/prompting). - `version` (integer, required) — Version number for a Prompt. Version numbers should be integers. The combination of configId and version number is unique. - `version_type` (string, required) — Indicates whether this prompt is using a fixed version number or auto-updating to the latest version. Values from the VersionType enum. - `prompt_expansion` (prompt_expansion_spec, optional) — Configuration for prompt expansion behavior. - `version_description` (string, optional, nullable) — An optional description of the Prompt version. ### return_timeout_specs 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. - `inactivity` (return_timeout_spec, required) — A specific timeout configuration to be returned from the server - `max_duration` (return_timeout_spec, required) — A specific timeout configuration to be returned from the server ### return_user_defined_tool A specific tool version returned from the server - `created_on` (long, required) — The timestamp when the first version of this tool was created. - `id` (string, required) — Identifier for a Tool. Formatted as a UUID. - `modified_on` (long, required) — The timestamp when this version of the tool was created. - `name` (string, required) — Name of the built-in tool to use. Hume supports the following built-in tools: - **web_search:** enables EVI to search the web for up-to-date information when applicable. - **hang_up:** closes the WebSocket connection when appropriate (e.g., after detecting a farewell in the conversation). For more information, see our guide on [using built-in tools](/docs/speech-to-speech-evi/features/tool-use#using-built-in-tools). - `parameters` (string, required) — Stringified JSON defining the parameters used by this version of the Tool. These parameters define the inputs needed for the Tool's execution, including the expected data type and description for each input field. Structured as a stringified JSON schema, this format ensures the Tool receives data in the expected format. - `tool_type` (enum, required) - Allowed values: `BUILTIN`, `FUNCTION` - `version` (integer, required) — Version number for a Tool. Version numbers should be integers. The combination of configId and version number is unique. - `version_type` (enum, required) - Allowed values: `FIXED`, `LATEST` - `description` (string, optional, nullable) — An optional description of what the Tool does, used by the supplemental LLM to choose when and how to call the function. - `fallback_content` (string, optional, nullable) — Optional text passed to the supplemental LLM in place of the tool call result. The LLM then uses this text to generate a response back to the user, ensuring continuity in the conversation if the Tool errors. - `version_description` (string, optional, nullable) — An optional description of the Tool version. ### return_turn_detection_spec A turn detection configuration returned from the server - `end_of_turn_silence_ms` (integer, optional, nullable) — How long the user must be silent before EVI considers their turn complete and begins generating a response. Lower values make conversations feel snappier but increase the chance of the agent responding during a mid-thought pause. Higher values give users more room to pause and collect their thoughts before the agent responds. Accepts values between 500 and 3000 milliseconds. - `prefix_padding_ms` (integer, optional, nullable) — The duration of audio captured before the detected start of speech. This ensures the beginning of an utterance is not clipped. Accepts values between 0 and 1000 milliseconds. - `speech_detection_threshold` (float, optional, nullable) — How confident the system must be that audio contains speech before it begins processing. Lower values increase sensitivity, capturing softer speech at the cost of more noise-triggered processing. Higher values require clearer, louder audio to register as speech. Accepts values between 0.0 and 1.0. ### ReturnVoice An Octave voice available for text-to-speech - `id` (string, required) — ID of the voice in the `Voice Library`. - `name` (string, required) — Name of the voice in the `Voice Library`. - `provider` (enum, required) - Allowed values: `HUME_AI`, `CUSTOM_VOICE` - `compatible_octave_models` (list of string, optional) ### returned_webhook_spec Collection of webhook URL endpoints to be returned from the server - `events` (list of enum, required) — The list of events the specified URL is subscribed to. See our [webhooks guide](/docs/speech-to-speech-evi/configuration/build-a-configuration#supported-events) for more information on supported events. - Allowed values: `chat_started`, `chat_ended`, `tool_call` - `url` (string, required) — The URL where event payloads will be sent. This must be a valid https URL to ensure secure communication. The server at this URL must accept POST requests with a JSON payload. ### PostedConfigEventMessagesOnInactivityTimeout Specifies the message EVI provides when the chat is about to be disconnected due to a user inactivity timeout, such as a message mentioning a lack of user input for a period of time. Enabling an inactivity message allows developers to use this message event for "checking in" with the user if they are not responding to see if they are still active. If the user does not respond in the number of seconds specified in the `inactivity_timeout` field, then EVI will say the message and the user has 15 seconds to respond. If they respond in time, the conversation will continue; if not, the conversation will end. However, if the inactivity message is not enabled, then reaching the inactivity timeout will immediately end the connection. - `enabled` (boolean, required) — Boolean indicating if this event message is enabled. If set to `true`, a message will be sent when the circumstances for the specific event are met. - `text` (string, optional, nullable) — Text to use as the event message when the corresponding event occurs. If no text is specified, EVI will generate an appropriate message based on its current context and the system prompt. ### PostedConfigEventMessagesOnMaxDurationTimeout Specifies the message EVI provides when the chat is disconnected due to reaching the maximum chat duration, such as a message mentioning the time limit for the chat has been reached. - `enabled` (boolean, required) — Boolean indicating if this event message is enabled. If set to `true`, a message will be sent when the circumstances for the specific event are met. - `text` (string, optional, nullable) — Text to use as the event message when the corresponding event occurs. If no text is specified, EVI will generate an appropriate message based on its current context and the system prompt. ### PostedConfigEventMessagesOnNewChat Specifies the initial message EVI provides when a new chat is started, such as a greeting or welcome message. - `enabled` (boolean, required) — Boolean indicating if this event message is enabled. If set to `true`, a message will be sent when the circumstances for the specific event are met. - `text` (string, optional, nullable) — Text to use as the event message when the corresponding event occurs. If no text is specified, EVI will generate an appropriate message based on its current context and the system prompt. ### prompt_expansion_spec Configuration for prompt expansion behavior. - `enabled` (boolean, optional) — Boolean indicating whether prompt expansion is enabled. Defaults to `true`. When set to `false`, no additional instructions are appended to the system prompt, giving full control over the prompt content. Only applicable when using an external supplemental language model. ### PostedConfigTimeoutsInactivity - `enabled` (boolean, required) - `duration_secs` (integer, optional, nullable) ### PostedConfigTimeoutsMaxDuration - `enabled` (boolean, required) - `duration_secs` (integer, optional, nullable) ### VoiceId - `id` (string, required) — The unique ID associated with the **Voice**. - `provider` (enum, optional) — Specifies the source provider associated with the chosen voice. - **`HUME_AI`**: Select voices from Hume's [Voice Library](https://app.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. 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`. 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. - Allowed values: `HUME_AI`, `CUSTOM_VOICE` ### VoiceName - `name` (string, required) — The name of a **Voice**. - `provider` (enum, optional) — Specifies the source provider associated with the chosen voice. - **`HUME_AI`**: Select voices from Hume's [Voice Library](https://app.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. 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`. 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. - Allowed values: `HUME_AI`, `CUSTOM_VOICE` ### return_event_message_spec A specific event message configuration to be returned from the server - `enabled` (boolean, required) — Boolean indicating if this event message is enabled. If set to `true`, a message will be sent when the circumstances for the specific event are met. - `text` (string, optional, nullable) — Text to use as the event message when the corresponding event occurs. If no text is specified, EVI will generate an appropriate message based on its current context and the system prompt. ### return_timeout_spec A specific timeout configuration to be returned from the server - `enabled` (boolean, required) — Boolean indicating if this timeout is enabled. If set to false, EVI will not timeout due to a specified duration being reached. However, the conversation will eventually disconnect after 1,800 seconds (30 minutes), which is the maximum WebSocket duration limit for EVI. - `duration_secs` (integer, optional, nullable) — Duration in seconds for the timeout (e.g. 600 seconds represents 10 minutes). ## Examples **Request** ```json { "evi_version": "3", "name": "Weather Assistant Config", "event_messages": { "on_inactivity_timeout": { "enabled": false, "text": "" }, "on_max_duration_timeout": { "enabled": false, "text": "" }, "on_new_chat": { "enabled": false, "text": "" } }, "language_model": { "model_provider": "ANTHROPIC", "model_resource": "claude-3-7-sonnet-latest", "temperature": 1 }, "prompt": { "id": "", "version": 0 }, "voice": { "name": "Ava Song", "provider": "HUME_AI" } } ``` **Response** ```json { "builtin_tools": [], "created_on": 1715275452390, "ellm_model": { "allow_short_responses": false }, "event_messages": { "on_inactivity_timeout": { "enabled": false, "text": "" }, "on_max_duration_timeout": { "enabled": false, "text": "" }, "on_new_chat": { "enabled": false, "text": "" } }, "evi_version": "3", "id": "1b60e1a0-cc59-424a-8d2c-189d354db3f3", "language_model": { "model_provider": "ANTHROPIC", "model_resource": "claude-3-7-sonnet-latest", "temperature": 1 }, "modified_on": 1715275452390, "name": "Weather Assistant Config", "prompt": { "created_on": 1715267200693, "id": "af699d45-2985-42cc-91b9-af9e5da3bac5", "modified_on": 1715267200693, "name": "Weather Assistant Prompt", "text": "You are an AI weather assistant providing users with accurate and up-to-date weather information. Respond to user queries concisely and clearly. Use simple language and avoid technical jargon. Provide temperature, precipitation, wind conditions, and any weather alerts. Include helpful tips if severe weather is expected.", "version": 0, "version_type": "FIXED", "version_description": "" }, "timeouts": { "inactivity": { "enabled": true, "duration_secs": 600 }, "max_duration": { "enabled": true, "duration_secs": 1800 } }, "tools": [], "version": 0, "version_description": "", "voice": { "id": "5bb7de05-c8fe-426a-8fcc-ba4fc4ce9f9c", "name": "Ava Song", "provider": "HUME_AI" } } ```