Use a SIP connection to get conversation intelligence

Connect to a call

The following code sample shows how you can connect the Telephony API to your cell phone (or any other type of phone number). Making a phone call is also the quickest way to test Symbl’s Telephony API. It can make an outbound call to a phone number using SIP endpoints that can be accessed over the internet using a SIP URI.

📘

Note

The Symbl SDK (Node.js) snippet must be run using Node.js, while the Native Javascript snippet can be run in your web browser.

Authentication

Before continuing, you must generate an authentication token (AUTH_TOKEN) as described in Authentication.

curl Code Example

curl -k -X POST "https://api.symbl.ai/v1/endpoint:connect" \
     -H "accept: application/json" \
     -H "Content-Type: application/json" \
     -H "X-API-KEY: $AUTH_TOKEN" \
     -d {
      "operation": "start",
      "endpoint": {
        "providerName": "Symbl",
        "type": "sip",
        "uri": "sip:[email protected]",
        "audioConfig": {
          "sampleRate": 48000,
          "encoding": "OPUS",
          "sampleSize": 16
        }
      },
      "actions": [
        {
          "invokeOn": "stop",
          "name": "sendSummaryEmail",
          "parameters": {
            "emails": [
              "[email protected]",
            ]
          }
        }
      ],
      "data": {
        "session": {
          "name": "My Meeting"
        }
      }
    }

Testing

Open up your shell terminal and copy and paste the command. Replace the placeholder values with the proper values and hit enter.

Node.js Code Example

const {sdk, SpeakerEvent} = require("symbl-node");
const appId = appId;
const appSecret = appSecret;

sdk.init({
  appId: appId,
  appSecret: appSecret,
  basePath: "https://api.symbl.ai",
}).then(async() => {
  console.log('SDK initialized.');
  try {
    sdk.startEndpoint({
      endpoint: {
        type: "sip",
        uri: "sip:555@your_sip_domain", // SIP URI to dial in
        audioConfig: { // Optionally any audio configuration
          sampleRate: 48000,
          encoding: "OPUS",
          sampleSize: "16"
        }
      },
      actions: [
        {
          invokeOn: "stop",
          name: "sendSummaryEmail",
          parameters: {
            emails: [
              "[email protected]"
            ],
          },
        },
      ],
      data: {
        session: {
          name: "Meeting name",
        },
      },
    }).then((connection) => {
      const connectionId = connection.connectionId;
      console.log("Successfully connected.", connectionId);
      console.log('Conversation ID', connection.conversationId);
      console.log('Full Conection Object', JSON.stringify(connection, null, 2));
    })
    .catch((err) => {
       console.error("Error while starting the connection", err);
    });
  } catch (e) {
    console.error(e);
  }
}).catch(err => console.error('Error in SDK initialization.', err));

Testing

Create a JavaScript file named app.js and copy the preceding code block into the file. Fill in the placeholder values with the proper values. Use npm to install the required libraries: npm install symbl-node.

From a terminal window, run

$ node app.js

If successful, you receive a response in the console.

Native JavaScript Code Example

const phoneNumber = PHONE_NUMBER;
const emailAddress = EMAIL_ADDRESS;
const authToken = AUTH_TOKEN;

const payload = {
  "operation": "start",
  "endpoint": {
    "type": "sip",
    "uri": "sip:555@your_sip_domain", // SIP URI to dial in
    "audioConfig": { // Optionally any audio configuration
      "sampleRate": 48000,
      "encoding": "OPUS",
      "sampleSize": "16"
    }
  },
  "actions": [{
    "invokeOn": "stop",
    "name": "sendSummaryEmail",
    "parameters": {
      "emails": [
        emailAddress
      ]
    }
  }],
  "data" : {
    "session": {
      "name" : "My Meeting"
    }
  }
}

const endpoint = 'https://api.symbl.ai/v1/endpoint:connect';
const fetchData = {
  method: "POST",
  headers: {
    'X-API-KEY': `${authToken}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify(payload),
}

fetch(endpoint, fetchData).then(response => {
  if (response.ok) {
    return response.json();
  } else {
    throw new Error('Something went wrong on api server!');
  }
}).then(response => {
  console.log('response', response);
  console.log('conversation ID', response.conversationId);
  console.log('connection ID', response.connectionId);
}).catch(error => {
  console.error(error);
});

Testing

Open your browser development tools and copy this code into the console. Replace the placeholder values with the proper values.

If successful you should receive a response in the console.

Python Code Example

import json
import requests

url = "https://api.symbl.ai/v1/endpoint:connect"

# set your access token here. See https://docs.symbl.ai/docs/developer-tools/authentication
access_token = 'your_access_token'

payload = {
    "operation": "start",  # enum([start, stop]) - Start or Stop connection
    "endpoint": {
      "type": "sip",
      "uri": "sip:555@your_sip_domain", // SIP URI to dial in
      "audioConfig": { // Optionally any audio configuration
        "sampleRate": 48000,
        "encoding": "OPUS",
        "sampleSize": "16"
      }
    },
    "actions": [{
        # actions that should be performed while this connection is active. Currently only one action is supported - sendSummaryEmail
        "invokeOn": "stop",
        "name": "sendSummaryEmail",
        "parameters": {
            "emails": [
                emailAddress
            ]
        }
    }],
    "languages": ['en-US'],  # The first language code in the array is used to specify the session’s language.
    "data": {  # Object containing a session object which has a field name corresponding to the name of the meeting
        "session": {
            "name": "My Meeting"
        }
    }
}

headers = {
    'X-API-KEY': access_token,
    'Content-Type': 'application/json'
}

responses = {
    400: 'Bad Request! Please refer docs for correct input fields.',
    401: 'Unauthorized. Please generate a new access token.',
    404: 'The conversation and/or it\'s metadata you asked could not be found, please check the input provided',
    429: 'Maximum number of concurrent jobs reached. Please wait for some requests to complete.',
    500: 'Something went wrong! Please contact [email protected]'
}

response = requests.request("POST", url, headers=headers, data=json.dumps(payload))

if response.status_code == 201:
    # Successful API execution
    print("conversationId => " + response.json()['conversationId'])  # ID to be used with Conversation API.
    print("connectionId => " + response.json()['connectionId'])
    # Ephemeral connection identifier of the request, to uniquely identify the telephony connection. Once the connection is stopped using “stop” operation, or is closed due to some other reason, the connectionId is no longer valid
    print("resultWebSocketUrl => " + response.json()['resultWebSocketUrl'])
    # objSame as eventUrl but over WebSocket. The latency of events is lower with a dedicated WebSocket connection.ct
    print("eventUrl => " + response.json()['eventUrl'])
    # REST API to push speaker events as the conversation is in progress, to add additional speaker context in the conversation. Example - In an on-going meeting, you can push speaker events
elif response.status_code in responses.keys():
    print(responses[response.status_code] + ", Debug Message => " + str(response.text))  # Expected error occurred
else:
    print("Unexpected error occurred. Please contact [email protected]" + ", Debug Message => " + str(response.text))

exit()

Testing

Create a python file named app.py and copy this code into the file. Fill in the placeholder values with the proper values. Use Python pip (learn how to install here) to install Python Requests (pip install requests). In your termninal, now run:

$ python app.py

If successful you should receive a response in the console.

Running this code should connect our API to your phone call. Once the call is completed you will receive an email that details the conversation and provides you with a transcription and Insights about the call.

Response

If successful, you will receive a response in the console as shown below:

{
    "eventUrl": "https://api.symbl.ai/v1/event/f31ad3b9-341a-4950-a1c2-152f08da8aaa",
    "resultWebSocketUrl": "wss://api.symbl.ai/events/f31ad3b9-341a-4950-a1c2-152f08da8aaa",
    "conversationId": "5687907911204864",
    "connectionId": "f31ad3b9-341a-4950-a1c2-152f08da8aaa"
}

Response Parameters

FieldDescription
eventUrlREST API to push speaker events as the conversation is in progress, to add additional speaker context in the conversation. Example - In an on-going meeting, you can push speaker events.
resultWebSocketUrlSame as eventUrl but over WebSocket. The latency of events is lower with a dedicated WebSocket connection.ct.
connectionIdEphemeral connection identifier of the request, to uniquely identify the telephony connection. Once the connection is stopped using “stop” operation, or is closed due to some other reason, the connectionId is no longer valid.
conversationIdRepresents the conversation - this is the ID that needs to be used in conversation API to access the conversation.

📘

If you have any questions or concerns about our API, you can join our Support Slack or send us an email at [email protected]