temperature parameter to TTS endpoints. Controls sampling temperature for speech
generation. Higher values increase variation; lower values increase consistency.turn_detection.end_of_turn_silence_ms: How long EVI waits after speech ends before committing a turn (500-3000ms,
default 800ms).turn_detection.speech_detection_threshold: Sensitivity of voice activity detection (0.0-1.0, default 0.5).turn_detection.prefix_padding_ms: Audio padding before detected speech (default 300ms).interruption.min_interruption_ms: Minimum speech duration before EVI can be interrupted (50-2000ms, default
800ms).claude-opus-4-6, gpt-5.1, gpt-5.1-priority, gpt-5.2, gpt-5.2-priority.prompt_expansion to ZERO when configuring an external LLM, disabling automatic prompt expansion and giving you full control over the system prompt.SESSION_SETTINGS chat event in the EVI chat history API. When you fetch chat events via
/v0/evi/chats/:id, the response now includes entries that
indicate when system settings were updated and which settings were applied."version": "4-mini" in your EVI config
version to use it./v0/tts/stream/json now include a request_id field for easier tracking and debugging.voice_id query parameter on the /chat endpoint only
accepted Voice Library voices. It now supports custom voices as well.voice_id query parameter to EVI /chat
endpoint.
editable context type for
injected context.GPT-5, GPT-5-mini, and GPT-5-nano models as a supplemental LLM options.evi_version: "3" in your config.
assistant_prosody message, rather than
inside the assistant_message. Each assistant_prosody message can be linked to its corresponding
assistant_message via the id field.Snippet when instant_mode is not enabled.gemini-2.5-flash-preview-04-17 model as a supplemental LLM optioninstant_mode for ultra‑low‑latency streaming, which starts sending audio chunks immediately (first chunk in ~200 ms).strip_headers to remove per‑chunk headers so that streamed audio can be concatenated into a single file.24kHz to 48kHzclaude-3-7-sonnet-latest model as a supplemental LLM optioncustom_session_id is sent in the SessionSettings message, this custom session ID will be added to all returned payloadsclaude-3.5-haiku-latest model as a supplemental LLM optiongpt-4-turbo model{{now}} default dynamic variable for system prompts, which is replaced with the current UTC timestamp and does not require sending a variable value in SessionSettingsclaude-instant-1.2 (any existing integrations should migrate to current models like claude-3.5-haiku-latest)claude-3.5-sonnet-latest (currently points to claude-3-5-sonnet-20241022) and made this model the recommended supplemental LLMgemini-1.5-pro and gemini-1.5-flash)type: temporarySunny, featuring a male voice with an Indian accentarticulation, buoyancy, enthusiasm, nasality, smoothness, tightness, assertiveness, confidence, gender, relaxedness, tepidityE0718 error code instead of silently dropping the connectiongemini-1.5-pro and gemini-1.5-flash models to use the latest versions, gemini-1.5-pro-002 and gemini-1.5-flash-002GET /chat_groups/{id} endpoint would return all chats, not just the chats in the chat_groupchat_id is passed to users when using custom language models and phone calling together, enabling developers to retrieve post-call details with these featuresE0717 error type, which will occur when a developer tries resuming a chat when one of the chats in its chat_group is already active.E0718, and if a provider has unexpected internal errors EVI will return E0719. If these errors occur, developers can try again later or change their configurations to use a different LM provider.llama-3.1-70b-versatile and llama-3.1-8b-instantaccounts/fireworks/models/llama-v3p1-405b-instruct, accounts/fireworks/models/llama-v3p1-70b-instruct, and accounts/fireworks/models/llama-v3p1-8b-instructhang_up built in tool to allow EVI to end calls. To use this, developers can include the hang_up tool in the builtin_tools object when creating a config, and provide instructions on when EVI should end the call in the promptid, version, and text). Providing only text in the prompt field when creating a new config will create a new promptaccounts/fireworks/models/llama-v3-70b-instruct), as it is replaced by the new Llama 3.1 70B model (accounts/fireworks/models/llama-v3p1-70b-instruct)SessionSettings payloads now return an E0716 error. Invalid payloads include empty system prompts, duplicate tool names, removing previously enabled tools, and overlapping builtin and custom tool names. If an update is invalid, the error message will explain why, and the SessionSettings will not be appliedon_inactivity_timeout configuration option, allowing EVI to speak a message when the user is inactive for some period of time: Inactivity timeout messageon_max_duration_timeout configuration option, allowing EVI to speak a message when the maximum chat duration is reached: Max duration timeout messagegpt-4o-mini language modelSessionSettings and reference their values in the system prompt (e.g., {{variable_name}}): Dynamic variablesgemini-1.5-pro and gemini-1.5-flash language modelsinactivity) and maximum session duration (max_duration): Timeoutsmetadata.twilio.caller_number property of the evi/chats/:id endpoint: List chat events/v0/evi/language-models API endpoint to retrieve the language models supported by EVI and the built-in tools available for each modelconfig_id filter option for the GET /chat_groups endpoint, allowing developers to limit paginated results to chat groups associated with a specific config IDname filter option for the GET /configs, GET /tools, and GET /prompts endpoints. These allow developers to limit paginated results to only include objects with a specific namerequest_id field to ChatMetadata to uniquely identify sessionsevent_messages.on_new_chat.enabled to true to have EVI speak first in the conversation. To control the exact text of that first message, also set event_messages.on_new_chat.textellm_model.allow_short_responses to falseclaude-3-5-sonnet-20240620) to the EVI APIItoAssistantInput message at the beginning of an EVI chat configured with Anthropic models would result in an errortotal_pages field to all paginated EVI REST endpointsE0712:custom_language_model_timed_out error. If the connection fails, we will send an E0713:custom_language_model_connection_failed errorresumed_chat_group_id query parameter: Chat resumabilityapi.hume.ai/v0/evi/chat_groups endpoint to support listing chat groups or listing events from a specific chat group: Chat groups endpointChatMetadata output message, which includes a chat_id to identify each individual chat with EVI and a chat_group_id to support resumability and group resumed chats together: ChatMetadataE0706: custom_language_model_unreachable error to the developerE0710: resuming_chat_group_with_new_config when a developer attempts to resume a chat group with a new config, E0708: chat_group_not_found when a chat group does not exist, and E0709: config_not_found when a config does not existE0711: language_model_unavailable errorAdded support for streaming custom language model responses in parts. Developers can send text chunks to start generating audio responses much faster The Custom Language Model endpoint now expects text to be formatted in the following payload:
Added support for pausing and resuming EVI responses with with pause_assistant_message and resume_assistant_message. Sending a pause message stops EVI from generating and speaking Assistant messages. Sending a resume message allows EVI to continue responding to the User messages
tool_name to 64 charsDACHER voice to the voice configuration optionsgpt-4o language modelgemma-7b-it), Llama 3 8B (llama3-8b-8192), and Llama 3 70B (llama3-70b-8192)accounts/fireworks/models/llama-v3-70b-instruct)custom_session_id field in the SessionSettings message, and documentation for using it: Custom Session IDE0300 error code if they are out of credits or E0301 if they are blocked via subscription. The WebSocket connection will also be closed with code 1008from_text field in UserMessage. It is now set to True if any part of the UserMessage is from a developer-provided UserInput messageTools through our tool use featureToolErrorMessage as a supported input type400 if a Config, Tool, or Prompt is created with a name or versionDescription that’s too long or non-ASCII. Names must be under 75 chars, versionDescription must be under 256 chars, description for Tools must be under 100 chars, fallback_content for Tools must be under 2048 chars, and model_resource for LanguageModels must be under 1024 charstemperature from EVI configsSessionSettings message to allow dynamic prompt updatingTextInput message to UserInput to indicate this is text to be added to the chat history as a User message and used as context by the LLMTtsInput message to AssistantInput to make it clear that this is input text to be spoken by EVI and added to the chat history as an Assistant messageSessionSettings messagecustom_model and prompt, because custom language models do not use prompts