← LiveKit + Bland AI integrations

Analyze Call with Bland AI API on New Room Event (Instant) from LiveKit API

Pipedream makes it easy to connect APIs for Bland AI, LiveKit and 2,700+ other apps remarkably fast.

Trigger workflow on
New Room Event (Instant) from the LiveKit API
Next, do this
Analyze Call with the Bland AI API
No credit card required
Intro to Pipedream
Watch us build a workflow
Watch us build a workflow
8 min
Watch now ➜

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

Adyen logo
Appcues logo
Bandwidth logo
Checkr logo
ChartMogul logo
Dataminr logo
Gopuff logo
Gorgias logo
LinkedIn logo
Logitech logo
Replicated logo
Rudderstack logo
SAS logo
Scale AI logo
Webflow logo
Warner Bros. logo
Adyen logo
Appcues logo
Bandwidth logo
Checkr logo
ChartMogul logo
Dataminr logo
Gopuff logo
Gorgias logo
LinkedIn logo
Logitech logo
Replicated logo
Rudderstack logo
SAS logo
Scale AI logo
Webflow logo
Warner Bros. logo

Developers Pipedream

Getting Started

This integration creates a workflow with a LiveKit trigger and Bland AI action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

  1. Select this integration
  2. Configure the New Room Event (Instant) trigger
    1. Connect your LiveKit account
    2. Select one or more Event Types
    3. Optional- Configure Room Name Filter
  3. Configure the Analyze Call action
    1. Connect your Bland AI account
    2. Select a Call ID
    3. Configure Goal
    4. Configure Questions
  4. Deploy the workflow
  5. Send a test event to validate your setup
  6. 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

Description:Emit new event for LiveKit room activities via webhook. [See the documentation](https://docs.livekit.io/home/server/webhooks/).
Version:0.0.1
Key:livekit-new-room-event-instant

Trigger Code

import app from "../../livekit.app.mjs";

export default {
  key: "livekit-new-room-event-instant",
  name: "New Room Event (Instant)",
  description: "Emit new event for LiveKit room activities via webhook. [See the documentation](https://docs.livekit.io/home/server/webhooks/).",
  version: "0.0.1",
  type: "source",
  dedupe: "unique",
  props: {
    app,
    http: "$.interface.http",
    eventTypes: {
      type: "string[]",
      label: "Event Types",
      description: "Select which types of events to monitor",
      options: [
        {
          label: "Room Started (e.g., call initiated)",
          value: "room_started",
        },
        {
          label: "Room Finished (e.g., call ended)",
          value: "room_finished",
        },
        {
          label: "Participant Joined (e.g., call answered)",
          value: "participant_joined",
        },
        {
          label: "Participant Left (e.g., call ended)",
          value: "participant_left",
        },
        {
          label: "Track Published (e.g., video track published)",
          value: "track_published",
        },
        {
          label: "Track Unpublished (e.g., video track unpublished)",
          value: "track_unpublished",
        },
        {
          label: "Egress Started (e.g., egress started for recording or streaming)",
          value: "egress_started",
        },
        {
          label: "Egress Updated (e.g., egress updated for recording or streaming)",
          value: "egress_updated",
        },
        {
          label: "Egress Ended (e.g., egress ended for recording or streaming)",
          value: "egress_ended",
        },
        {
          label: "Ingress Started (e.g., ingress started for recording or streaming)",
          value: "ingress_started",
        },
        {
          label: "Ingress Ended (e.g., ingress ended for recording or streaming)",
          value: "ingress_ended",
        },
      ],
    },
    roomNameFilter: {
      type: "string",
      label: "Room Name Filter",
      description: "Only emit events for this specific room. Leave empty to monitor all rooms.",
      optional: true,
    },
  },
  methods: {
    shouldEmitEvent({
      event, room,
    }) {
      // Check if event type is in our filter
      if (!this.eventTypes.includes(event)) {
        return false;
      }

      // Filter by room if specified, with case-insensitive comparison
      if (this.roomNameFilter
        && room?.name?.toLowerCase() !== this.roomNameFilter.toLowerCase()) {
        return false;
      }

      return true;
    },
    generateSummary(event) {
      const room = event.room?.name || "Unknown room";

      switch (event.event) {
      case "room_started":
        return `Room started: ${room}`;
      case "room_finished":
        return `Room finished: ${room}`;
      case "participant_joined": {
        const joinedParticipant = event.participant?.identity || "Unknown";
        return `${joinedParticipant} joined room: ${room}`;
      }
      case "participant_left": {
        const leftParticipant = event.participant?.identity || "Unknown";
        return `${leftParticipant} left room: ${room}`;
      }
      case "track_published": {
        const publishedBy = event.participant?.identity || "Unknown";
        const trackType = event.track?.type || "track";
        return `${publishedBy} published ${trackType} in room: ${room}`;
      }
      case "track_unpublished": {
        const unpublishedBy = event.participant?.identity || "Unknown";
        const unpublishedTrackType = event.track?.type || "track";
        return `${unpublishedBy} unpublished ${unpublishedTrackType} in room: ${room}`;
      }
      case "egress_started": {
        const egressId = event.egressInfo?.egressId || "Unknown";
        return `Egress started (${egressId}) in room: ${room}`;
      }
      case "egress_updated": {
        const egressId = event.egressInfo?.egressId || "Unknown";
        return `Egress updated (${egressId}) in room: ${room}`;
      }
      case "egress_ended": {
        const egressId = event.egressInfo?.egressId || "Unknown";
        return `Egress ended (${egressId}) in room: ${room}`;
      }
      case "ingress_started": {
        const ingressId = event.ingressInfo?.ingressId || "Unknown";
        return `Ingress started (${ingressId}) in room: ${room}`;
      }
      case "ingress_ended": {
        const ingressId = event.ingressInfo?.ingressId || "Unknown";
        return `Ingress ended (${ingressId}) in room: ${room}`;
      }
      default:
        return `${event.event} in room: ${room}`;
      }
    },
  },
  async run({
    headers, bodyRaw,
  }) {
    if (!headers.authorization) {
      throw new Error("Missing Authorization header");
    }

    const webhookEvent = await this.app.verifyWebhook(bodyRaw, headers.authorization);

    if (this.shouldEmitEvent(webhookEvent)) {
      this.$emit(webhookEvent, {
        id: webhookEvent.id,
        summary: this.generateSummary(webhookEvent),
        ts: parseInt(webhookEvent.createdAt) * 1000,
      });
    }
  },
};

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.
LabelPropTypeDescription
LiveKitappappThis component uses the LiveKit app.
N/Ahttp$.interface.httpThis component uses $.interface.http to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the run() method of the component.
Event TypeseventTypesstring[]Select a value from the drop down menu:{ "label": "Room Started (e.g., call initiated)", "value": "room_started" }{ "label": "Room Finished (e.g., call ended)", "value": "room_finished" }{ "label": "Participant Joined (e.g., call answered)", "value": "participant_joined" }{ "label": "Participant Left (e.g., call ended)", "value": "participant_left" }{ "label": "Track Published (e.g., video track published)", "value": "track_published" }{ "label": "Track Unpublished (e.g., video track unpublished)", "value": "track_unpublished" }{ "label": "Egress Started (e.g., egress started for recording or streaming)", "value": "egress_started" }{ "label": "Egress Updated (e.g., egress updated for recording or streaming)", "value": "egress_updated" }{ "label": "Egress Ended (e.g., egress ended for recording or streaming)", "value": "egress_ended" }{ "label": "Ingress Started (e.g., ingress started for recording or streaming)", "value": "ingress_started" }{ "label": "Ingress Ended (e.g., ingress ended for recording or streaming)", "value": "ingress_ended" }
Room Name FilterroomNameFilterstring

Only emit events for this specific room. Leave empty to monitor all rooms.

Trigger Authentication

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

To retrieve your API Key, Secret Key and Project URL,

  • Navigate to your LiveKit account and sign in
  • Go to “Settings” > "Project" for Project URL
  • Go to “Settings” > "Keys" for API Key and Secret Key

About LiveKit

Build realtime AI. Instantly transport audio + video between LLMs and your users.

Action

Description:Analyzes an input call, extracting structured data and providing insights. [See the documentation](https://docs.bland.ai/api-v1/post/calls-id-analyze)
Version:0.0.1
Key:bland_ai-analyze-call

Bland AI Overview

The Bland AI API offers a suite of artificial intelligence services, which, when integrated with Pipedream, can automate tasks, analyze data, and enhance applications with machine learning capabilities. Through Pipedream's serverless platform, you can connect Bland AI with various apps to create custom workflows, process data, and respond to events in real time without managing infrastructure.

Action Code

import blandAi from "../../bland_ai.app.mjs";

export default {
  key: "bland_ai-analyze-call",
  name: "Analyze Call",
  description: "Analyzes an input call, extracting structured data and providing insights. [See the documentation](https://docs.bland.ai/api-v1/post/calls-id-analyze)",
  version: "0.0.1",
  type: "action",
  props: {
    blandAi,
    callId: {
      propDefinition: [
        blandAi,
        "callId",
      ],
    },
    goal: {
      propDefinition: [
        blandAi,
        "goal",
      ],
    },
    questions: {
      propDefinition: [
        blandAi,
        "questions",
      ],
    },
  },
  async run({ $ }) {
    const response = await this.blandAi.analyzeCall({
      $,
      callId: this.callId,
      data: {
        goal: this.goal,
        questions: this.questions?.map?.((str) => typeof str === "string"
          ? JSON.parse(str)
          : str),
      },
    });
    $.export("$summary", "Call analyzed successfully");
    return response;
  },
};

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.

LabelPropTypeDescription
Bland AIblandAiappThis component uses the Bland AI app.
Call IDcallIdstringSelect a value from the drop down menu.
Goalgoalstring

This is the overall purpose of the call. Provides context for the analysis to guide how the questions/transcripts are interpreted.

Questionsquestionsstring[]

An array of questions to be analyzed for the call. Each question should be an array with two elements: the question text and the expected answer type. Examples: ["Who answered the call?", "human or voicemail"], ["Positive feedback about the product: ", "string"]

Action Authentication

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

About Bland AI

Send or receive millions of phone calls per day, using programmable voice agents that sound and feel human.

More Ways to Connect Bland AI + LiveKit

End Call with Bland AI API on New Room Event (Instant) from LiveKit API
LiveKit + Bland AI
 
Try it
Get Transcript with Bland AI API on New Room Event (Instant) from LiveKit API
LiveKit + Bland AI
 
Try it
New Room Event (Instant) from the LiveKit API

Emit new event for LiveKit room activities via webhook. See the documentation

 
Try it
Create Ingress From URL with the LiveKit API

Create a new ingress from url in LiveKit. See the documentation

 
Try it
Create Room with the LiveKit API

Create a new room in LiveKit. See the documentation

 
Try it
Delete Room with the LiveKit API

Delete a room in LiveKit. See the documentation

 
Try it
Generate Access Token with the LiveKit API

Generate an access token for a participant to join a LiveKit room. See the documentation

 
Try it
List Rooms with the LiveKit API

List all rooms with LiveKit. See the documentation

 
Try it

Explore Other Apps

1
-
24
of
2,700+
apps by most popular

HTTP / Webhook
HTTP / Webhook
Get a unique URL where you can send HTTP or webhook requests
Node
Node
Anything you can do with Node.js, you can do in a Pipedream workflow. This includes using most of npm's 400,000+ packages.
Python
Python
Anything you can do in Python can be done in a Pipedream Workflow. This includes using any of the 350,000+ PyPi packages available in your Python powered workflows.
Pipedream Utils
Pipedream Utils
Utility functions to use within your Pipedream workflows
Notion
Notion
Notion is a new tool that blends your everyday work apps into one. It's the all-in-one workspace for you and your team.
OpenAI (ChatGPT)
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.
Anthropic (Claude)
Anthropic (Claude)
AI research and products that put safety at the frontier. Introducing Claude, a next-generation AI assistant for your tasks, no matter the scale.
Google Sheets
Google Sheets
Use Google Sheets to create and edit online spreadsheets. Get insights together with secure sharing in real-time and from any device.
Telegram
Telegram
Telegram, is a cloud-based, cross-platform, encrypted instant messaging (IM) service.
Google Drive
Google Drive
Google Drive is a file storage and synchronization service which allows you to create and share your work online, and access your documents from anywhere.
Pinterest
Pinterest
Pinterest is a visual discovery engine for finding ideas like recipes, home and style inspiration, and more.
Google Calendar
Google Calendar
With Google Calendar, you can quickly schedule meetings and events and get reminders about upcoming activities, so you always know what’s next.
Shopify
Shopify
Shopify is a complete commerce platform that lets anyone start, manage, and grow a business. You can use Shopify to build an online store, manage sales, market to customers, and accept payments in digital and physical locations.
Supabase
Supabase
Supabase is an open source Firebase alternative.
MySQL
MySQL
MySQL is an open-source relational database management system.
PostgreSQL
PostgreSQL
PostgreSQL is a free and open-source relational database management system emphasizing extensibility and SQL compliance.
Premium
AWS
AWS
Amazon Web Services (AWS) offers reliable, scalable, and inexpensive cloud computing services.
Premium
Twilio SendGrid
Twilio SendGrid
Send marketing and transactional email through the Twilio SendGrid platform with the Email API, proprietary mail transfer agent, and infrastructure for scalable delivery.
Amazon SES
Amazon SES
Amazon SES is a cloud-based email service provider that can integrate into any application for high volume email automation
Premium
Klaviyo
Klaviyo
Email Marketing and SMS Marketing Platform
Premium
Zendesk
Zendesk
Zendesk is award-winning customer service software trusted by 200K+ customers. Make customers happy via text, mobile, phone, email, live chat, social media.
Premium
ServiceNow
ServiceNow
The smarter way to workflow
Slack
Slack
Slack is a channel-based messaging platform. With Slack, people can work together more effectively, connect all their software tools and services, and find the information they need to do their best work — all within a secure, enterprise-grade environment.
Microsoft Teams
Microsoft Teams
Microsoft Teams has communities, events, chats, channels, meetings, storage, tasks, and calendars in one place.