{
  "opencollection": "1.0.0",
  "info": {
    "name": "Telnyx Access Tokens Speech To Text over WebSockets API",
    "version": "2.0.0"
  },
  "request": {
    "auth": {
      "type": "bearer",
      "token": "{{bearerToken}}"
    }
  },
  "items": [
    {
      "info": {
        "name": "Speech To Text over WebSockets",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Speech to text over WebSocket",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "https://api.telnyx.com/v2/speech-to-text/transcription",
            "params": [
              {
                "name": "transcription_engine",
                "value": "Telnyx",
                "type": "query",
                "description": "The transcription engine to use for processing the audio stream."
              },
              {
                "name": "input_format",
                "value": "mp3",
                "type": "query",
                "description": "The format of input audio stream."
              },
              {
                "name": "language",
                "value": "en-US",
                "type": "query",
                "description": "The language spoken in the audio stream."
              },
              {
                "name": "interim_results",
                "value": "true",
                "type": "query",
                "description": "Whether to receive interim transcription results."
              },
              {
                "name": "model",
                "value": "",
                "type": "query",
                "description": "The specific model to use within the selected transcription engine."
              },
              {
                "name": "endpointing",
                "value": "500",
                "type": "query",
                "description": "Silence duration (in milliseconds) that triggers end-of-speech detection. When set, the engine uses this value to determine when a speaker has stopped talking. Supported by `xAI`, `Deepgram`, `Google`, and `Speechmatics`. Other engines may not support this parameter."
              },
              {
                "name": "redact",
                "value": "pci",
                "type": "query",
                "description": "Enable redaction of sensitive information (e.g., PCI data, SSN) from transcription results. Supported values depend on the transcription engine."
              },
              {
                "name": "keyterm",
                "value": "Telnyx",
                "type": "query",
                "description": "A key term to boost in the transcription. The engine will be more likely to recognize this term. Can be specified multiple times for multiple terms."
              },
              {
                "name": "keywords",
                "value": "Telnyx,SIP,WebRTC",
                "type": "query",
                "description": "Comma-separated list of keywords to boost in the transcription. The engine will prioritize recognition of these words."
              }
            ]
          },
          "docs": "Open a WebSocket connection to stream audio and receive transcriptions in real-time. Authentication is provided via the standard `Authorization: Bearer <API_KEY>` header.\n\nSupported engines: `Azure`, `Deepgram`, `Google`, `Telnyx`, `xAI`, `Speechmatics`.\n\n**Connection flow:**\n1. Open WebSocket with query parameters specifying engine, input format, and language.\n2. Send binary audio frames (mp3/wav format).\n3. Receive JSON transcript frames with `transcript`, `is_final`, and `confidence` fields.\n"
        }
      ]
    }
  ],
  "bundled": true
}