IVR JS Example (OpenAI)

This example demonstrates an IVR script that harnesses the power of OpenAI by integrating it with Vodia's Javascript IVR capabilities.

Scenario:

• Play a welcome message using Vodia's TTS.
• Send a predefined set of instructions to OpenAI, in this case a map of words to numbers.
• Parse OpenAI's response to determine the appropriate call routing.

//
// OpenAI integration
//
// (C) Vodia Networks 2024
//
// This file is property of Vodia Networks Inc. All rights reserved. 
// For more information mail Vodia Networks Inc., info@vodia.com.
//

'use strict';
var secret = "sk-proj-KEY"
var codec = "g711_ulaw" // or pcm16
var texts = {
  initial: {
    en: "Hi, I am your Vodia AI assistant. How may I help you today?",
    de: "Sagen Sie etwas."
  }
}
function text(name) {
  var prompt = texts[name]
  if (call.lang in prompt) return prompt[call.lang];
  return prompt["en"]
}
call.say({text: text("initial")});

var timer = setTimeout(function() {call.transfer('700')}, 30000);

var ws = new Websocket("wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview-2024-10-01")
ws.header([{ name: "Authorization", value: "Bearer " + secret, secret: true },
           { name: "Cache-Control", value: "no-cache" },
           { name: "Pragma", value: "no-cache" },
           { name: "Sec-Fetch-Dest", value: "websocket" },
           { name: "Sec-Fetch-Mode", value: "websocket" },
           { name: "Sec-Fetch-Site", value: "same-site" },
           { name: "Sec-WebSocket-Protocol", value: "realtime" },
           { name: "OpenAI-Beta", value: "realtime=v1" },
           { name: "User-Agent", value: "Vodia-PBX/69.5.3" }
          ])
ws.on('open', function() {
  console.log("Websocket opened")
})
ws.on('close', function() {
  console.log("Websocket closed")
  call.stream()
})
ws.on('message', function(message) {
  if (message.type != "response.audio.delta") console.log(message);
  var msg = JSON.parse(message)
  if (msg.type == "session.created") {
    var update = {
      type: "session.update",
      session: {
        instructions: "Here is a map of words to numbers: { sales: 785, marketing: 785, support: 739, Bob: 451, technical support: 739 }. Whenever someone tells you to call, or transfer to, would like to talk to, get someone online, return the exact text transfer, followed by a colon, followed by the number from that map based on the destination. If the destination is directly a number then don't use the map, just directly use that number. If there is no number mapped, then return transfer:700",
        turn_detection: {
          type: "server_vad",
          threshold: 0.5,
          prefix_padding_ms: 300,
          silence_duration_ms: 500
        },
        voice: "alloy",
        temperature: 0.8,
        max_response_output_tokens: 4096,
        tools: [],
        modalities: ["text","audio"],
        input_audio_format: codec,
        output_audio_format: codec,
        input_audio_transcription:{ model: "whisper-1" },
        tool_choice: "auto"
      }
    }
    ws.send(JSON.stringify(update))
  }
  else if (msg.type == "session.updated") {
    call.stream({
      codec: codec,
      interval: 0.5,
      callback: stream
    })
  }
  else if (msg.type == "response.audio.delta") {
    var audio = fromBase64String(msg.delta)
    call.play({
      direction: "out",
      codec: codec,
      audio: audio
    })
  }
  else if (msg.type == "response.audio_transcript.done") {
    if (msg.transcript) {
      call.log("Message transcript: " + msg.transcript);
      var t = msg.transcript.split(':');
      if (t.length > 1) {
        call.mute();
        if (timer) clearTimeout(timer);
        var cmd = t[0];
        var value = t[1];
        if (cmd == "transfer" && value) {
          call.transfer(value);
        }
        else {
          call.transfer('700');
        }
      }
    }
  }
})
function stream(audio) {
  var frame = JSON.stringify({
    "type": "input_audio_buffer.append",
    "audio": toBase64String(audio)
  })
  ws.send(frame)
}
ws.connect()

For more information on Vodia's JavaScript capabilities, refer to: Vodia Backend JavaScript Documentation