AsyncAPI channel · Hume AI · Hume AI WebSocket APIs

/chat/{chat_id}/connect

Secondary connection to an in-progress EVI chat. The original chat must have been opened with `allow_connection=true`. The secondary connection can send the same control-plane messages as `/chat` except `audio_input`, and receives the same subscribe events. Connection URL: `wss://api.hume.ai/v0/evi/chat/{chat_id}/connect`.

Open source AsyncAPI → All Hume AI channels Hume AI provider profile
Provider: Hume AI AsyncAPI: v2.6.0 Spec: Hume AI WebSocket APIs Operations: 2 Messages: 16

Channel address

/chat/{chat_id}/connect

Parameters

Operations

publish
eviChatConnectSend
Control-plane messages the secondary client sends to EVI.
eviChatConnectReceive
Events streamed to the secondary client.

Messages

session_settings
Configure session-level parameters such as audio encoding, context, language model, tools and variables.
Content-Type:
user_input
Plain text inserted into the conversation as the user.
Content-Type:
assistant_input
Plain text the assistant should synthesize and speak.
Content-Type:
tool_response
Successful response to a tool call.
Content-Type:
tool_error
Error response to a tool call.
Content-Type:
pause_assistant_message
Pause assistant responses while still recording user audio.
Content-Type:
resume_assistant_message
Resume assistant responses after a pause.
Content-Type:
chat_metadata
Sent once at the start of a connection with chat and chat-group identifiers.
Content-Type:
user_message
Transcript and prosody scores for a user utterance.
Content-Type:
assistant_message
A piece of generated assistant text returned by the language model.
Content-Type:
assistant_prosody
Predicted expression scores for an assistant utterance.
Content-Type:
audio_output
Base64-encoded chunk of synthesized assistant audio.
Content-Type:
assistant_end
Marks the end of an assistant turn.
Content-Type:
user_interruption
Signals that the user started speaking and EVI interrupted itself.
Content-Type:
tool_call
Request from EVI to invoke a registered tool.
Content-Type:
error
WebSocket-level error emitted by the EVI server.
Content-Type:

About AsyncAPI

The AsyncAPI specification describes event-driven APIs the way OpenAPI describes request/response APIs. A channel is the named pipe — a webhook URL, a Kafka topic, a WebSocket route, an MQTT subject — that producers and consumers publish or subscribe to. Each channel carries one or more messages with structured payloads, and an operation declares whether a given party sends or receives on that channel.

Browse every event-driven channel on the APIs.io network or compare with the broader Agent Skill and MCP server surfaces of the same providers.

Work with this as data

Every channel here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for event channels

4 MCP tools reach this
  • find_channelsBrowse and filter every channel in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This channel 
curl "https://apis.io/api/v1/channels/chat-chat-id-connect"
All event channels 
curl "https://apis.io/api/v1/channels?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.