Multi-context TTS WebSocket

GET 
wss://api.knoxstudio.ai/v1/text-to-speech/:voice_id/multi-stream-input

Same transport as TTS WebSocket, but each context_id keeps its own generation state. Useful for interleaved voice-agent replies. GET and POST accept the upgrade. Stream formats only. Billed per character.

Request

Path, query, and auth match Text-to-speech WebSocket: voice_id, model_id, stream output_format, enable_logging, apply_text_normalization. Plain HTTP returns 400.

Client messages

{
  "text": "First context ",
  "context_id": "agent-a",
  "try_trigger_generation": true
}

Flush or close a single context independently:

{ "context_id": "agent-a", "text": "", "flush": true }

{ "context_id": "agent-a", "close_context": true }

Terminate the whole socket with close_socket: true.

Server messages

Audio frames include contextId so you can demux concurrent generations. isFinal applies to that context.

Use this API when you need concurrent or interleaved streams. For a single sequential stream, prefer /stream-input.

Error Responses

Validation uses HTTP 422:

{
  "detail": [
    {
      "loc": ["body", "field"],
      "msg": "…",
      "type": "value_error"
    }
  ]
}

Other errors use { "detail": "message" }.

Status	When
400	WebSocket path called without Upgrade: websocket.
401	Missing or invalid API key.
402	Insufficient credits.
403	Token is not allowed to use this model.
404	Resource not found.
422	Validation error.
429	Rate limit exceeded.
500	Internal server error.