Make a Phone Call with Twilio API on New Batch Completed from OpenAI (ChatGPT) API

Pipedream makes it easy to connect APIs for Twilio, OpenAI (ChatGPT) and 2,400+ other apps remarkably fast.

Trigger workflow on

New Batch Completed from the OpenAI (ChatGPT) API

Next, do this

Make a Phone Call with the Twilio API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a OpenAI (ChatGPT) trigger and Twilio action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Batch Completed trigger
1. Connect your OpenAI (ChatGPT) account
2. Configure timer
Configure the Make a Phone Call action
1. Connect your Twilio account
2. Select a From
3. Configure To
4. Select a Call Type
5. Configure Text
6. Configure URL
7. Select a Application SID
8. Optional- Configure Timeout
9. Optional- Configure Record
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New Batch Completed on OpenAI (ChatGPT)

Description:Emit new event when a new batch is completed in OpenAI. [See the documentation](https://platform.openai.com/docs/api-reference/batch/list)

Version:0.0.5

Key:openai-new-batch-completed

View on GitHub

OpenAI (ChatGPT) Overview#

OpenAI provides a suite of powerful AI models through its API, enabling developers to integrate advanced natural language processing and generative capabilities into their applications. Here’s an overview of the services offered by OpenAI's API:

Use Python or Node.js code to make fully authenticated API requests with your OpenAI account:

Trigger Code#

import common from "../common/common.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  ...common,
  key: "openai-new-batch-completed",
  name: "New Batch Completed",
  description: "Emit new event when a new batch is completed in OpenAI. [See the documentation](https://platform.openai.com/docs/api-reference/batch/list)",
  version: "0.0.5",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    _getLastCompleted() {
      return this.db.get("lastCompleted") || 0;
    },
    _setLastCompleted(lastCompleted) {
      this.db.set("lastCompleted", lastCompleted);
    },
    getMeta(batch) {
      return {
        id: batch.id,
        summary: `Batch Completed with ID ${batch.id}`,
        ts: batch.completed_at * 1000,
      };
    },
    async getAndProcessItems(max) {
      const lastCompleted = this._getLastCompleted();
      let maxCompleted = lastCompleted;
      const results = this.openai.paginate({
        resourceFn: this.openai.listBatches,
        max,
      });
      const batches = [];
      for await (const batch of results) {
        if (batch.completed_at && batch.completed_at > lastCompleted) {
          batches.push(batch);
          maxCompleted = Math.max(batch.completed_at, maxCompleted);
        }
      }
      this._setLastCompleted(maxCompleted);
      batches.reverse().forEach((item) => this.$emit(item, this.getMeta(item)));
    },
  },
  sampleEmit,
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
OpenAI (ChatGPT)	`openai`	`app`	This component uses the OpenAI (ChatGPT) app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

OpenAI (ChatGPT) uses API keys for authentication. When you connect your OpenAI (ChatGPT) account, Pipedream securely stores the keys so you can easily authenticate to OpenAI (ChatGPT) APIs in both code and no-code steps.

About OpenAI (ChatGPT)#

OpenAI is an AI research and deployment company with the mission to ensure that artificial general intelligence benefits all of humanity. They are the makers of popular models like ChatGPT, DALL-E, and Whisper.

Action#

Make a Phone Call on Twilio

Description:Make a phone call passing text, a URL, or an application that Twilio will use to handle the call. [See the documentation](https://www.twilio.com/docs/voice/api/call-resource#create-a-call-resource)

Version:0.1.5

Key:twilio-make-phone-call

View on GitHub

Twilio Overview#

Twilio's API on Pipedream opens up a multitude of communication capabilities, allowing you to build robust, scalable, and automated workflows. With Twilio, you can send and receive SMS and MMS messages, make voice calls, and perform other communication functions programmatically. Leveraging Pipedream's seamless integration, you can connect these communications features with hundreds of other services to automate notifications, streamline customer interactions, and enhance operational efficiency.

Action Code#

import { phone } from "phone";
import twilio from "../../twilio.app.mjs";
import { callToString } from "../../common/utils.mjs";

export default {
  key: "twilio-make-phone-call",
  name: "Make a Phone Call",
  description: "Make a phone call passing text, a URL, or an application that Twilio will use to handle the call. [See the documentation](https://www.twilio.com/docs/voice/api/call-resource#create-a-call-resource)",
  version: "0.1.5",
  type: "action",
  props: {
    twilio,
    from: {
      propDefinition: [
        twilio,
        "from",
      ],
    },
    to: {
      propDefinition: [
        twilio,
        "to",
      ],
    },
    callType: {
      type: "string",
      label: "Call Type",
      description: "Whether to use `text`, a `URL`, or an `application` to handle the call",
      options: [
        {
          label: "Enter text for Twilio to speak when the user picks up the phone",
          value: "text",
        },
        {
          label: "Enter a URL that returns the TwiML instructions for the call",
          value: "url",
        },
        {
          label: "Enter the SID of an Application resource that will handle the call",
          value: "application",
        },
      ],
      reloadProps: true,
    },
    text: {
      label: "Text",
      type: "string",
      description: "The text you'd like Twilio to speak to the user when they pick up the phone.",
      hidden: true,
    },
    url: {
      type: "string",
      label: "URL",
      description: "The absolute URL that returns the TwiML instructions for the call",
      hidden: true,
    },
    applicationSid: {
      propDefinition: [
        twilio,
        "applicationSid",
      ],
      hidden: true,
    },
    timeout: {
      type: "integer",
      label: "Timeout",
      description: "The integer number of seconds that we should allow the phone to ring before assuming there is no answer. The default is `60` seconds and the maximum is `600` seconds.",
      optional: true,
    },
    record: {
      type: "boolean",
      label: "Record",
      description: "Whether to record the call",
      optional: true,
      reloadProps: true,
    },
  },
  async additionalProps(existingProps) {
    const props = {};
    existingProps.text.hidden = !(this.callType === "text");
    existingProps.url.hidden = !(this.callType === "url");
    existingProps.applicationSid.hidden = !(this.callType === "application");
    if (this.record) {
      props.trim = {
        type: "string",
        label: "Trim",
        description: "Whether to trim any leading and trailing silence from the recording",
        options: [
          "trim-silence",
          "do-not-trim",
        ],
        optional: true,
      };
      props.recordingTrack = {
        type: "string",
        label: "Recording Track",
        description: "The audio track to record for the call. Default is `both`.",
        options: [
          "inbound",
          "outbound",
          "both",
        ],
        optional: true,
      };
      props.recordingCallbackUrl = {
        type: "string",
        label: "Recording Callback URL",
        description: "The URL that we call when the recording is available to be accessed",
        optional: true,
      };
    }
    return props;
  },
  async run({ $ }) {
    // Parse the given number into its E.164 equivalent
    // The E.164 phone number will be included in the first element
    // of the array, but the array will be empty if parsing fails.
    // See https://www.npmjs.com/package/phone
    const toParsed = phone(this.to);
    console.log(toParsed);
    if (!toParsed || !toParsed.phoneNumber) {
      throw new Error(`Phone number ${this.to} could not be parsed as a valid number.`);
    }

    const fromParsed = phone(this.from);
    if (!fromParsed || !fromParsed.phoneNumber) {
      throw new Error(`Phone number ${this.from} could not be parsed as a valid number.`);
    }

    const data = {
      to: toParsed.phoneNumber,
      from: fromParsed.phoneNumber,
      twiml: this.text && `<Response><Say>${this.text}</Say></Response>`,
      url: this.url,
      applicationSid: this.applicationSid,
      timeout: this.timeout,
      record: this.record,
      trim: this.trim,
      recordingTrack: this.recordingTrack,
      recordingStatusCallback: this.recordingCallbackUrl,
    };

    const resp = await this.twilio.getClient().calls.create(data);
    $.export("$summary", `Successfully made a new phone call, "${callToString(resp)}"`);
    return resp;
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Twilio	`twilio`	`app`	This component uses the Twilio app.
From	`from`	`string`	Select a value from the drop down menu.
To	`to`	`string`	The destination phone number in E.164 format. Format with a `+` and country code (e.g., `+16175551212`).
Call Type	`callType`	`string`	Select a value from the drop down menu:`{ "label": "Enter text for Twilio to speak when the user picks up the phone", "value": "text" }{ "label": "Enter a URL that returns the TwiML instructions for the call", "value": "url" }{ "label": "Enter the SID of an Application resource that will handle the call", "value": "application" }`
Timeout	`timeout`	`integer`	The integer number of seconds that we should allow the phone to ring before assuming there is no answer. The default is `60` seconds and the maximum is `600` seconds.
Record	`record`	`boolean`	Whether to record the call

Action Authentication#

Twilio uses API keys for authentication. When you connect your Twilio account, Pipedream securely stores the keys so you can easily authenticate to Twilio APIs in both code and no-code steps.

To connect your Twilio account to Pipedream,

API Key and API Key SID

First, create an API key in Twilio.

There are three types of keys: Main, Standard, and Restricted. You'll need a Main key to interact with certain API endpoints, like /Accounts.
If you don't need to interact with those endpoints, you can use a Standard or Restricted key.

After creating your key, you'll see fields for Sid and Secret. Enter those in the fields below.

Account SID and Auth Token

Visit your Twilio Dashboard. You'll see your Account SID and Auth Token under Account info.