AsyncAPI channel · Hume AI
· Hume AI WebSocket APIs
/models
Streaming multimodal expression measurement inference.
Connection URL: `wss://api.hume.ai/v0/stream/models`.
Each client message includes a `models` configuration and the
`data` payload (Base64-encoded media or raw text). Hume returns
a per-model predictions envelope, an error envelope, or a warning.
Provider:Hume AIAsyncAPI: v2.6.0Spec: Hume AI WebSocket APIsOperations: 2Messages: 4
Channel address
/models
Operations
publish
streamModelsSend
Streaming inference request from the client.
subscribe
streamModelsReceive
Streaming inference response from the server.
Messages
models_input
Streaming inference request - models config + media payload.
Content-Type:
models_success
Per-model predictions for a streamed input.
Content-Type:
models_error
Error returned by the streaming inference server.
Content-Type:
models_warning
Non-fatal warning returned by the streaming inference 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.
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
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.