WebSocket API

const ws = new WebSocket("wss://platform-api.wisprflow.ai/api/v1/dash/ws?api_key=Bearer%20<YOUR_API_KEY>");

ws.onopen = () => {
  console.log("WebSocket connected");
};

ws.onerror = (error) => {
  console.error("WebSocket error:", error);
};

ws.onclose = () => {
  console.log("WebSocket closed");
};

ws.send(JSON.stringify({
  type: "auth",
  access_token: "...",
  language: ["en"], // If known beforehand, set to list of languages the user speaks
  context: { // Optional contextual information used to improve dictation quality when applicable
    app: {
      name: "Weather Forecast Chatbot",
      type: "ai" // one of {email, ai, other}
    },
    dictionary_context: [], // list of uncommon names or words relevant to the context
    user_identifier: "john_doe_1",
    user_first_name: "John",
    user_last_name: "Doe",
    textbox_contents: {
      before_text: "", // text immediately before cursor position
      selected_text: "", // text highlighted by cursor for replacement
      after_text: "" // text immediately after cursor position
    },
    screenshot: null, // screenshor for when speaking about something on the screen
    content_text: null, // plaintext content of the app user is dictating in
    content_html: null, // HTML content of the app user is dictating in
    conversation: { // chatbot style history of conversation (messaging or AI app)
      id: "ai_chat_126", // conversation identifier
      participants: ["John Doe", "AI Assistant"], // list of people the user might be addresing
      messages: [ // list of messages in conversation, in chronological order
        {
          role: "user" // One of {user, human, assistant}
          content: "How is the weather in SF today?"
        },
        {
          role: "assistant"
          content: "It's partly cloudy. Do you want to know the temperature?"
        }
      ]
    }
  }
}));

ws.send(JSON.stringify({
  type: "append",
  position: 0,
  audio_packets: {
    packets: [base64Audio1, base64Audio2, base64Audio3, ...], // you can send any number of packets
    volumes: [volume1, volume2, volume3, ...], // The number of volumes must match the number of packets
    packet_duration: BUFFER_SIZE / audioContext.sampleRate, // in seconds
    audio_encoding: "wav", // pcm wav data 
    byte_encoding: "base64" // set to "binary" for reduced message size (see "Network Optimization" below)
  }
}));

ws.send(JSON.stringify({
  type: "commit",
  total_packets: n
}));

ws.onmessage = (event) => {
  const response = JSON.parse(event.data);
  if (response.status == "text") {
    if (response.final) { // final transcription result (websocket will close)
      console.log("Final server response");
    } else { // intermediate transcription result (roughly every 30 seconds)
      console.log("Interim server response");
    }
  } else if (response.status == "error") { // unrecoverable (websocket will close)
    console.log("Server returned error response");
  } else { // other information
    console.log("Server returned other response");
  }
};

{
  "status": "auth"
}

{
  "status": "info",
  "message": {
    "event": "commit_received"
  }
}

{
  "status": "text",
  "position": 180,
  "final": false,
  "body": {
    "text": "This is a partial transcription...",
    "detected_language": "en"
  }
}

{
  "status": "text",
  "position": 205,
  "final": false,
  "body": {
    "text": "This is a partial transcription... and this is the full text.",
    "detected_language": "en"
  }
}

Encoding: 'msgpack'