Transcribe - Live audio

Deepgram provides its customers with real-time, streaming transcription via its streaming endpoints. These endpoints are high-performance, full-duplex services running over the WebSocket protocol.

To learn more about working with real-time streaming data and results, see Get Started with Streaming Audio.

Endpoint

Production WebSocket server for Deepgram's real-time transcription with streaming audio. TLS encryption will protect your connection and data. We support a minimum of TLS 1.2.

Accepts

Headers

Body Params

Sending Audio Data

All audio data is transmitted to the streaming endpoint as binary WebSocket messages, with payloads containing the raw audio data. The full-duplex protocol allows for real-time streaming, enabling you to receive transcription responses simultaneously as you upload data. For optimal performance, each streaming buffer should represent between 20 and 250 milliseconds of audio.

Messages

Keep Alive

Optional

Periodically send KeepAlive messages while streaming can ensure uninterrupted communication and minimizing costs. Learn More .

{ 
  "type": "KeepAlive"
}

Finalize

Optional

Finalize message can be used to handle specific scenarios where you need to force the server to process all unprocessed audio data and immediately return the final results. Learn More.

{ 
  "type": "Finalize" 
}

Close Stream

Optional

The CloseStream message can be sent to the Deepgram server, instructing it close the connection. Learn More.

{ 
  "type": "CloseStream"
}

Responses

Refer to API Errors for more information.

Response Schema

{
  "metadata": {
    "transaction_key": "string",
    "request_id": "uuid",
    "sha256": "string",
    "created": "string",
    "duration": 0,
    "channels": 0,
    "models": [
      "string"
    ],
  },
  "type": "Results",
  "channel_index": [
    0,
    0
  ],
  "duration": 0.0,
  "start": 0.0,
  "is_final": boolean,
  "speech_final": boolean,
  "channel": {
    "alternatives": [
      {
        "transcript": "string",
        "confidence": 0,
        "words": [
          {
            "word": "string",
            "start": 0,
            "end": 0,
            "confidence": 0
          }
        ]
      }
    ],
    "search": [
      {
        "query": "string",
        "hits": [
          {
            "confidence": 0,
            "start": 0,
            "end": 0,
            "snippet": "string"
          }
        ]
      }
    ]
  }
}

Errors & Warnings

If Deepgram encounters an error during real-time streaming, we will return a WebSocket Close frame. The body of the Close frame will indicate the reason for closing using one of the specification’s pre-defined status codes followed by a UTF-8-encoded payload that represents the reason for the error.

Current codes and payloads in use include: