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

/tts/v1/voice:streamBidirectional

Bidirectional WebSocket endpoint for streaming text-to-speech synthesis. A single connection may host up to five contexts; the account is limited to 20 concurrent connections. The connection auto-closes after 10 minutes of inactivity across all contexts.

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

/tts/v1/voice:streamBidirectional

Operations

publish
ttsClientMessage
Messages sent from client to Inworld TTS.
ttsServerMessage
Messages streamed from Inworld TTS to the client.

Messages

tts.create
Establishes an independent synthesis stream within the connection (max 5 per connection).
Content-Type:
tts.send_text
Sends up to 1000 characters of text to a context.
Content-Type:
tts.flush_context
Manually triggers synthesis of buffered text.
Content-Type:
tts.close_context
Terminates a context and releases resources, flushing pending text.
Content-Type:
tts.contextCreated
Context created (server)
Content-Type:
tts.audioChunk
Audio chunk (server)
Content-Type:
tts.flushCompleted
Flush completed (server)
Content-Type:
tts.contextClosed
Context closed (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.

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.