Feature Requests

I paid for creator subscription and it still says my current subscription is the free one. Please fix I have projects to be completed.

When I try to access my configurations on the portal, I just get the message "An unexpected error occured. We were unable to load your voice configurations. Please try again later." When I try using the get configs api ( https://api.hume.ai/v0/evi/configs ), I get this response with status 500: { "timestamp": "2025-06-23T08:25:26.217+00:00", "status": 500, "error": "Internal Server Error", "message": "No enum constant ai.hume.stenographer.dao.types.EventMessageType.on_disconnect_resume_chat", "path": "/configs" } This has been happening for past 3-4 days now and it's still not resolved.

Hi, the expression measurement functionality is generally great, but one big hang I have right now is that the transcriptions are pretty rough. Is there any way for me to be able to supply a different transcript as grounding information. (something from whisper_timestamped for example). Thanks!

I need to add trace_id's to LLM responses for feedback annotation purposes in my web application. It is not currently possible to add any information to Custom LLM responses. See https://dev.hume.ai/docs/empathic-voice-interface-evi/guides/custom-language-model#clm-outgoing-message-data-format I propose adding metadata to the assistant_message responses that would be passed through to the client. type OutgoingCLMMessage = AssistantInputMessage | AssistantEndMessage; interface AssistantInputMessage { type: "assistant_input"; text: string; metadata?: { [key: string]: any }; // 👈🏼 Add } interface AssistantEndMessage { type: "assistant_end"; metadata?: { [key: string]: any }; // 👈🏼 Add }

On Discord, user here_for_the_life_lessons reports that when using the built-in EVI hang-up tool, sometimes EVI hangs up and the player on the client stops playing back in the middle of audio and EVI doesn't get a chance to finish what it is saying.

Help with integratiing EVI in Unity, from a plug in to at least some kind of documentation

UI and an API for seeing past generations that you have done via the API or in the TTS playground

Vapi AI has a web snippet that makes it easy to use, all i need to to is to copy and paste a code, inset api public key and assistant ID and i'm able to use it. Hume ai could have it too