Create Agent with ElevenLabs API on New Message Sent from WhatsApp Business API

Pipedream makes it easy to connect APIs for ElevenLabs, WhatsApp Business and 2,900+ other apps remarkably fast.

Trigger workflow on

New Message Sent from the WhatsApp Business API

Next, do this

Create Agent with the ElevenLabs 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 WhatsApp Business trigger and ElevenLabs action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Message Sent trigger
1. Connect your WhatsApp Business account
Configure the Create Agent action
1. Connect your ElevenLabs account
2. Configure Prompt
3. Optional- Configure Name
4. Optional- Select a LLM
5. Optional- Configure Temperature
6. Optional- Configure Max Tokens
7. Optional- Configure First Message
8. Optional- Configure Language
9. Optional- Configure Max Duration in Seconds
10. Optional- Configure Turn Timeout
11. Optional- Select a Voice ID
12. Optional- Select a TTS Model ID
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 Message Sent on WhatsApp Business

Description:Emit new event when a new message is sent or received. A Webhook subscribed to field "messages" must be set up from the App Dashboard of your [Facebook Developer Account](https://developers.facebook.com/). See [documentation](https://developers.facebook.com/docs/graph-api/webhooks/getting-started#configure-webhooks-product) for more information about Webhook setup.

Version:0.0.4

Key:whatsapp_business-new-message-sent

View on GitHub

WhatsApp Business Overview#

The WhatsApp Business API on Pipedream is a powerful avenue for automating interactions with customers on WhatsApp. You can send messages, set up automated responses, and manage conversations on a large scale. With Pipedream's serverless platform, you can create workflows that trigger from various events and connect WhatsApp Business with numerous other apps to automate tasks, notify teams, sync data, and more, all without managing infrastructure.

Trigger Code#

import whatsapp from "../../whatsapp_business.app.mjs";
import sampleEmit from "./test-event.mjs";

export default {
  key: "whatsapp_business-new-message-sent",
  name: "New Message Sent",
  description: "Emit new event when a new message is sent or received. A Webhook subscribed to field \"messages\" must be set up from the App Dashboard of your [Facebook Developer Account](https://developers.facebook.com/). See [documentation](https://developers.facebook.com/docs/graph-api/webhooks/getting-started#configure-webhooks-product) for more information about Webhook setup.",
  version: "0.0.4",
  type: "source",
  dedupe: "unique",
  props: {
    whatsapp,
    db: "$.service.db",
    httpInterface: {
      type: "$.interface.http",
      customResponse: true,
    },
  },
  methods: {
    _getChallengeToken() {
      return this.db.get("challengeToken");
    },
    _setChallengeToken(challengeToken) {
      this.db.set("challengeToken", challengeToken);
    },
  },
  async run(event) {
    const {
      body, query,
    } = event;
    if (query["hub.challenge"]) {
      this._setChallengeToken(query["hub.challenge"]);
    }
    const challengeToken = this._getChallengeToken();

    this.httpInterface.respond({
      status: "200",
      body: challengeToken,
      headers: {
        "content-type": "application/json",
      },
    });

    if (!body) {
      return;
    }

    const entries = body?.entry || [];
    for (const entry of entries) {
      if (entry.changes && entry.changes?.length > 0) {
        const status = entry?.changes[0]?.value?.statuses
          ? entry?.changes[0]?.value?.statuses[0]?.status
          : null;
        if (status && status !== "sent") {
          continue;
        }
      }
      this.$emit(entry, {
        id: Date.now(),
        summary: "New Message Sent",
        ts: Date.now(),
      });
    }
  },
  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
WhatsApp Business	`whatsapp`	`app`	This component uses the WhatsApp Business app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
N/A	`httpInterface`	`$.interface.http`	This component uses `$.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.

Trigger Authentication#

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

To connect your WhatsApp Business Cloud account to Pipedream, follow the steps below to find your Business Account ID and your Permanent Access Token.

For additional info on setting up a WhatsApp Business account, refer to their getting started docs

About WhatsApp Business#

WhatsApp Business products support businesses from large to small. Engage audiences, accelerate sales and drive better customer support outcomes on the platform with more than 2 billion users around the world.

Action#

Create Agent on ElevenLabs

Description:Create an agent in Eleventlabs. [See the documentation](https://elevenlabs.io/docs/api-reference/agents/create-agent)

Version:0.0.3

Key:elevenlabs-create-agent

View on GitHub

ElevenLabs Overview#

The ElevenLabs API offers text-to-speech capabilities with realistic voice synthesis. Integrating this API on Pipedream allows you to build automated workflows that convert text content into spoken audio files. You can trigger these conversions from various events, process the text data, send it to the ElevenLabs API, and handle the audio output—all within a serverless environment.

Action Code#

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

export default {
  key: "elevenlabs-create-agent",
  name: "Create Agent",
  description: "Create an agent in Eleventlabs. [See the documentation](https://elevenlabs.io/docs/api-reference/agents/create-agent)",
  version: "0.0.3",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: false,
  },
  type: "action",
  props: {
    elevenlabs,
    prompt: {
      type: "string",
      label: "Prompt",
      description: "The prompt for the agent",
    },
    name: {
      type: "string",
      label: "Name",
      description: "A name to make the agent easier to find",
      optional: true,
    },
    llm: {
      type: "string",
      label: "LLM",
      description: "The LLM to query with the prompt and the chat history",
      options: [
        "gpt-4o-mini",
        "gpt-4o",
        "gpt-4",
        "gpt-4-turbo",
        "gpt-3.5-turbo",
        "gemini-1.5-pro",
        "gemini-1.5-flash",
        "gemini-2.0-flash-001",
        "gemini-2.0-flash-lite",
        "gemini-1.0-pro",
        "claude-3-7-sonnet",
        "claude-3-5-sonnet",
      ],
      optional: true,
    },
    temperature: {
      type: "string",
      label: "Temperature",
      description: "The temperature for the LLM. Defaults to `0`",
      optional: true,
    },
    maxTokens: {
      type: "integer",
      label: "Max Tokens",
      description: "If greater than 0, maximum number of tokens the LLM can predict",
      optional: true,
    },
    firstMessage: {
      type: "string",
      label: "First Message",
      description: "If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion.",
      optional: true,
    },
    language: {
      type: "string",
      label: "Language",
      description: "Language of the agent - used for ASR and TTS. Defaults to `en`",
      optional: true,
    },
    maxDurationSeconds: {
      type: "integer",
      label: "Max Duration in Seconds",
      description: "The maximum duration of a conversation in seconds. Defaults to `600`",
      optional: true,
    },
    turnTimeout: {
      type: "string",
      label: "Turn Timeout",
      description: "Maximum wait time for the user’s reply before re-engaging the user. Defaults to `7`",
      optional: true,
    },
    voiceId: {
      propDefinition: [
        elevenlabs,
        "voiceId",
      ],
      description: "The voice ID to use for TTS",
      optional: true,
    },
    ttsModelId: {
      type: "string",
      label: "TTS Model ID",
      description: "The model to use for TTS",
      options: [
        "eleven_turbo_v2",
        "eleven_turbo_v2_5",
        "eleven_flash_v2",
        "eleven_flash_v2_5",
      ],
      optional: true,
    },
  },
  async run({ $ }) {
    const response = await this.elevenlabs.createAgent({
      $,
      data: {
        conversation_config: {
          conversation: {
            max_duration_seconds: this.maxDurationSeconds,
          },
          turn: {
            turn_timeout: this.turnTimeout && +this.turnTimeout,
          },
          agent: {
            first_message: this.firstMessage,
            language: this.language,
            prompt: {
              prompt: this.prompt,
              llm: this.llm,
              temperature: this.temperature && +this.temperature,
              max_tokens: this.maxTokens,
            },
          },
          tts: {
            voice_id: this.voiceId,
            model_id: this.ttsModelId,
          },
        },
        name: this.name,
      },
    });
    if (response?.agent_id) {
      $.export("$summary", `Successfully created agent with ID: ${response.agent_id}`);
    }
    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.

Label	Prop	Type	Description
ElevenLabs	`elevenlabs`	`app`	This component uses the ElevenLabs app.
Prompt	`prompt`	`string`	The prompt for the agent
Name	`name`	`string`	A name to make the agent easier to find
LLM	`llm`	`string`	Select a value from the drop down menu:`gpt-4o-minigpt-4ogpt-4gpt-4-turbogpt-3.5-turbogemini-1.5-progemini-1.5-flashgemini-2.0-flash-001gemini-2.0-flash-litegemini-1.0-proclaude-3-7-sonnetclaude-3-5-sonnet`
Temperature	`temperature`	`string`	The temperature for the LLM. Defaults to `0`
Max Tokens	`maxTokens`	`integer`	If greater than 0, maximum number of tokens the LLM can predict
First Message	`firstMessage`	`string`	If non-empty, the first message the agent will say. If empty, the agent waits for the user to start the discussion.
Language	`language`	`string`	Language of the agent - used for ASR and TTS. Defaults to `en`
Max Duration in Seconds	`maxDurationSeconds`	`integer`	The maximum duration of a conversation in seconds. Defaults to `600`
Turn Timeout	`turnTimeout`	`string`	Maximum wait time for the user’s reply before re-engaging the user. Defaults to `7`
Voice ID	`voiceId`	`string`	Select a value from the drop down menu.
TTS Model ID	`ttsModelId`	`string`	Select a value from the drop down menu:`eleven_turbo_v2eleven_turbo_v2_5eleven_flash_v2eleven_flash_v2_5`

Action Authentication#

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

To retrieve your API Key,

Navigate to your ElevenLabs account and sign in
Click the dropdown on the top right
Go to “Profile” > “API Key”

About ElevenLabs#

Research lab exploring new frontiers of Voice AI. Deploying tools for prime long-form synthetic speech, voice cloning and automatic dubbing.