AsyncAPI channel · Together AI · Together AI Streaming Inference API

/audio/speech

Text-to-speech (TTS). When `"stream": true` the server responds with `text/event-stream` emitting `audio.tts.chunk` events containing base64-encoded raw PCM audio. When streaming, the only supported `response_format` is `raw`. The stream terminates with `[DONE]`.

Open source AsyncAPI → All Together AI channels Together AI provider profile
Provider: Together AI AsyncAPI: v2.6.0 Spec: Together AI Streaming Inference API Operations: 2 Messages: 3

Channel address

/audio/speech

Operations

publish
createStreamingAudioSpeech
Open a streaming text-to-speech request.
streamAudioSpeech
Receive streaming text-to-speech audio chunks.

Messages

AudioSpeechRequest
JSON body posted by the client to open a streaming TTS session.
Content-Type: application/json
AudioSpeechChunk
A single `data:` event carrying a base64-encoded audio segment.
Content-Type: application/json
StreamDone
Final SSE event signalling the end of the stream. The literal payload is `[DONE]` (not JSON).
Content-Type: text/plain

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.