AsyncAPI channel · Azure OpenAI Service · Azure OpenAI Service - Streaming and Realtime APIs

/openai/realtime#server

Aggregate stream of server events emitted by the Azure OpenAI Realtime service to the connected client.

Open source AsyncAPI → All Azure OpenAI Service channels Azure OpenAI Service provider profile
Provider: Azure OpenAI Service AsyncAPI: v2.6.0 Spec: Azure OpenAI Service - Streaming and Realtime APIs Operations: 1 Messages: 47

Channel address

/openai/realtime#server

Operations

receiveRealtimeServerEvent
Subscribe to any Realtime server event from the service.

Messages

error
An error occurred on the server.
Content-Type: application/json
session.created
A new realtime session was created.
Content-Type: application/json
session.updated
A session was updated.
Content-Type: application/json
transcription_session.updated
A transcription session was updated.
Content-Type: application/json
conversation.created
A conversation was created.
Content-Type: application/json
conversation.item.added
An item was added to the conversation.
Content-Type: application/json
conversation.item.created
A conversation item was created (in response to `conversation.item.create`).
Content-Type: application/json
conversation.item.done
A conversation item finished streaming.
Content-Type: application/json
conversation.item.retrieved
A conversation item was retrieved.
Content-Type: application/json
conversation.item.truncated
A previous assistant audio item was truncated.
Content-Type: application/json
conversation.item.deleted
A conversation item was deleted.
Content-Type: application/json
conversation.item.input_audio_transcription.delta
Partial user input audio transcription.
Content-Type: application/json
conversation.item.input_audio_transcription.segment
A timestamped segment of the user input audio transcription.
Content-Type: application/json
conversation.item.input_audio_transcription.completed
Transcription of the user's input audio is complete.
Content-Type: application/json
conversation.item.input_audio_transcription.failed
Transcription of the user's input audio failed.
Content-Type: application/json
input_audio_buffer.committed
The user input audio buffer was committed.
Content-Type: application/json
input_audio_buffer.cleared
The user input audio buffer was cleared.
Content-Type: application/json
input_audio_buffer.speech_started
Server VAD detected the user started speaking.
Content-Type: application/json
input_audio_buffer.speech_stopped
Server VAD detected the user stopped speaking.
Content-Type: application/json
input_audio_buffer.timeout_triggered
A buffer-timeout was triggered without speech being detected.
Content-Type: application/json
input_audio_buffer.dtmf_event_received
A DTMF tone was received on the input audio buffer.
Content-Type: application/json
output_audio_buffer.started
The server began streaming output audio.
Content-Type: application/json
output_audio_buffer.stopped
The server stopped streaming output audio.
Content-Type: application/json
output_audio_buffer.cleared
The server cleared its output audio buffer.
Content-Type: application/json
response.created
A new response was created.
Content-Type: application/json
response.done
A response finished streaming (completed, cancelled, failed, or incomplete).
Content-Type: application/json
response.output_item.added
A new output item was added to the response.
Content-Type: application/json
response.output_item.done
An output item finished streaming.
Content-Type: application/json
response.content_part.added
A new content part was added to an output item.
Content-Type: application/json
response.content_part.done
A content part finished streaming.
Content-Type: application/json
response.output_text.delta
Incremental text output from the model.
Content-Type: application/json
response.output_text.done
Text output is complete.
Content-Type: application/json
response.output_audio.delta
Incremental base64 audio output from the model.
Content-Type: application/json
response.output_audio.done
Audio output is complete.
Content-Type: application/json
response.output_audio_transcript.delta
Incremental transcript text for the model's audio output.
Content-Type: application/json
response.output_audio_transcript.done
Audio output transcript is complete.
Content-Type: application/json
response.function_call_arguments.delta
Incremental JSON argument text for a function call.
Content-Type: application/json
response.function_call_arguments.done
Function call arguments streaming complete.
Content-Type: application/json
response.mcp_call_arguments.delta
Incremental MCP tool-call arguments.
Content-Type: application/json
response.mcp_call_arguments.done
MCP tool-call arguments streaming complete.
Content-Type: application/json
response.mcp_call.in_progress
An MCP tool call is in progress.
Content-Type: application/json
response.mcp_call.completed
An MCP tool call completed successfully.
Content-Type: application/json
response.mcp_call.failed
An MCP tool call failed.
Content-Type: application/json
mcp_list_tools.in_progress
MCP server tool-listing is in progress.
Content-Type: application/json
mcp_list_tools.completed
MCP server tool-listing completed.
Content-Type: application/json
mcp_list_tools.failed
MCP server tool-listing failed.
Content-Type: application/json
rate_limits.updated
Updated rate-limit information emitted after each `response.created` event.
Content-Type: application/json

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.