AsyncAPI channel · StepFun
· StepFun Realtime Voice & Streaming TTS WebSocket API
/v1/realtime/audio
Streaming text-to-speech channel (model selected via ?model=, e.g. step-tts-mini).
Channel address
/v1/realtime/audio
Operations
send
streamingTts
Streaming text-to-speech synthesis.
Messages
tts.create
Client creates a TTS synthesis session.
Content-Type:
tts.connection.done
Server confirms the TTS connection.
Content-Type:
tts.text.delta
Client streams text to synthesize.
Content-Type:
tts.text.done
Client signals end of text input.
Content-Type:
tts.text.flush
Client forces synthesis of buffered text.
Content-Type:
tts.text.flushed
Server acknowledges the flush.
Content-Type:
tts.response.created
Server starts a synthesis response.
Content-Type:
tts.response.audio.delta
Incremental synthesized audio.
Content-Type:
tts.response.audio.done
Synthesized audio complete.
Content-Type:
tts.response.sentence.start
Sentence boundary start marker.
Content-Type:
tts.response.sentence.end
Sentence boundary end marker.
Content-Type:
tts.response.subtitle
Subtitle/timestamp payload for synthesized audio.
Content-Type:
tts.response.error
Synthesis error event.
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.