{
  "opencollection": "1.0.0",
  "info": {
    "name": "Inworld Models Text To Speech API",
    "version": "v1"
  },
  "request": {
    "auth": {
      "type": "basic",
      "username": "{{username}}",
      "password": "{{password}}"
    }
  },
  "items": [
    {
      "info": {
        "name": "Text To Speech",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Synthesize Speech",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.inworld.ai/tts/v1/voice",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Synthesize a single audio response from text. Returns base64-encoded audio plus optional word/character/phoneme alignment metadata. Maximum 2,000 input characters per request and 16 MB output audio.\n"
        },
        {
          "info": {
            "name": "Stream Synthesize Speech",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.inworld.ai/tts/v1/voice:stream",
            "body": {
              "type": "json",
              "data": "{}"
            }
          },
          "docs": "Stream synthesis. The response is a chunked sequence of JSON envelopes, each containing a base64 audio fragment. Use for low-latency playback of long-form text.\n"
        },
        {
          "info": {
            "name": "WebSocket Synthesize Speech",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://api.inworld.ai/tts/v1/voice:websocket"
          },
          "docs": "Upgrade to a WebSocket connection for bidirectional streaming synthesis. Clients send `SynthesizeRequest` frames and receive chunked audio frames with timestamp metadata. Auth via `Authorization: Basic` header on the upgrade request.\n"
        },
        {
          "info": {
            "name": "List TTS Voices",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://api.inworld.ai/tts/v1/voices",
            "params": [
              {
                "name": "filter",
                "value": "",
                "type": "query",
                "description": "Optional filter expression (e.g. by tag, language, gender)."
              }
            ]
          },
          "docs": "List voices available for synthesis. Includes Inworld-shipped voices and any custom-cloned or designed voices in the caller's workspace.\n"
        }
      ]
    }
  ],
  "bundled": true
}