AsyncAPI channel · inworld-ai · Inworld AI Runtime WebSocket APIs

/stt/v1/transcribe:streamBidirectional

Bidirectional WebSocket endpoint for streaming speech-to-text transcription. The first client message must be a TranscribeConfig followed by AudioChunk messages and (optionally) EndTurn / CloseStream control messages.

Open source AsyncAPI → All inworld-ai channels inworld-ai provider profile
Provider: inworld-ai AsyncAPI: v2.6.0 Spec: Inworld AI Runtime WebSocket APIs Operations: 2 Messages: 8

Channel address

/stt/v1/transcribe:streamBidirectional

Operations

publish
sttClientMessage
Messages sent from client to Inworld STT.
sttServerMessage
Messages streamed from Inworld STT to the client.

Messages

stt.transcribeConfig
Transcribe config (client, first message)
Content-Type:
stt.audioChunk
Audio chunk (client)
Content-Type:
stt.endTurn
End turn (client)
Content-Type:
stt.closeStream
Close stream (client)
Content-Type:
stt.transcription
Transcription (server)
Content-Type:
stt.speechStarted
Speech started (server)
Content-Type:
stt.speechStopped
Speech stopped (server)
Content-Type:
stt.usage
Usage (server, coming soon)
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 Naftiko capability, Agent Skill, and MCP server surfaces of the same providers.