AsyncAPI channel · StepFun
· StepFun Realtime Voice & Streaming TTS WebSocket API
/v1/realtime
Bidirectional realtime voice conversation channel.
Channel address
/v1/realtime
Operations
send
realtimeConversation
Bidirectional realtime voice conversation.
Messages
session.update
Client updates session configuration (model, voice, modalities).
Content-Type:
session.created
Server confirms session creation (object realtime.session).
Content-Type:
session.updated
Server confirms session update.
Content-Type:
input_audio_buffer.append
Client appends audio to the input buffer.
Content-Type:
input_audio_buffer.commit
Client commits the input audio buffer.
Content-Type:
input_audio_buffer.clear
Client clears the input audio buffer.
Content-Type:
input_audio_buffer.committed
Server acknowledges the committed buffer.
Content-Type:
input_audio_buffer.cleared
Server acknowledges the cleared buffer.
Content-Type:
input_audio_buffer.speech_started
Server VAD detected start of speech.
Content-Type:
input_audio_buffer.speech_stopped
Server VAD detected end of speech.
Content-Type:
conversation.item.create
Client adds an item to the conversation.
Content-Type:
conversation.item.created
Server confirms the conversation item.
Content-Type:
conversation.item.delete
Client deletes a conversation item.
Content-Type:
conversation.item.deleted
Server confirms the deletion.
Content-Type:
conversation.item.input_audio_transcription.completed
Server delivers the transcription of user input audio.
Content-Type:
response.create
Client requests a model response.
Content-Type:
response.cancel
Client cancels an in-flight response.
Content-Type:
response.created
Server starts a response.
Content-Type:
response.output_item.added
Server adds an output item to the response.
Content-Type:
response.content_part.added
Server adds a content part.
Content-Type:
response.text.delta
Incremental text output.
Content-Type:
response.text.done
Text output complete.
Content-Type:
response.thinking.delta
Incremental reasoning output (reasoning models).
Content-Type:
response.thinking.done
Reasoning output complete.
Content-Type:
response.audio_transcript.delta
Incremental transcript of generated audio.
Content-Type:
response.audio_transcript.done
Audio transcript complete.
Content-Type:
response.audio.delta
Incremental generated audio.
Content-Type:
response.audio.done
Audio generation complete.
Content-Type:
response.content_part.done
Content part complete.
Content-Type:
response.output_item.done
Output item complete.
Content-Type:
response.done
Response complete.
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.