{
  "opencollection": "1.0.0",
  "info": {
    "name": "Cartesia Agents Speech-to-Text API",
    "version": "2026-03-01"
  },
  "request": {
    "auth": {
      "type": "bearer",
      "token": "{{bearerToken}}"
    }
  },
  "items": [
    {
      "info": {
        "name": "Speech-to-Text",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Batch Speech-to-Text",
            "type": "http"
          },
          "http": {
            "method": "POST",
            "url": "https://api.cartesia.ai/stt",
            "headers": [
              {
                "name": "Cartesia-Version",
                "value": ""
              }
            ],
            "params": [
              {
                "name": "encoding",
                "value": "",
                "type": "query",
                "description": "PCM encoding, required only when uploading raw headerless PCM."
              },
              {
                "name": "sample_rate",
                "value": "",
                "type": "query",
                "description": "Sample rate in Hz, required only when uploading raw headerless PCM."
              }
            ],
            "body": {
              "type": "multipart-form",
              "data": [
                {
                  "name": "file",
                  "type": "text",
                  "value": ""
                },
                {
                  "name": "model",
                  "type": "text",
                  "value": ""
                },
                {
                  "name": "language",
                  "type": "text",
                  "value": ""
                },
                {
                  "name": "timestamp_granularities[]",
                  "type": "text",
                  "value": ""
                }
              ]
            }
          },
          "docs": "Transcribes an audio file of any length using the ink-whisper model."
        }
      ]
    }
  ],
  "bundled": true
}