How to Connect WhatsApp to Google Gemini

Combine whatsmeow-node with the Google GenAI SDK to build a WhatsApp chatbot powered by Gemini. Messages come in via WhatsApp, get sent to Gemini for a response, and the reply goes back to the user — with typing indicators while the model thinks.

Prerequisites

A paired whatsmeow-node session (How to Pair)
A Google AI API key (set as GEMINI_API_KEY environment variable) — get one at ai.google.dev
The Google GenAI SDK: npm install @google/genai

Step 1: Set Up Both Clients

import { createClient } from "@whatsmeow-node/whatsmeow-node";
import { GoogleGenAI } from "@google/genai";

const client = createClient({ store: "session.db" });
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });

const SYSTEM_PROMPT = "You are a helpful WhatsApp assistant. Keep responses concise — under 500 characters when possible, since this is a chat interface.";

Step 2: Handle Incoming Messages

client.on("message", async ({ info, message }) => {
  if (info.isFromMe) return;

  const text =
    (message.conversation as string) ??
    (message.extendedTextMessage as { text?: string } | undefined)?.text;
  if (!text) return;

  await client.sendChatPresence(info.chat, "composing");

  const reply = await askGemini(info.sender, text);
  await client.sendMessage(info.chat, { conversation: reply });
});

Step 3: Send to Gemini

async function askGemini(userJid: string, userMessage: string): Promise<string> {
  const response = await ai.models.generateContent({
    model: "gemini-2.5-flash",
    contents: userMessage,
    config: {
      systemInstruction: SYSTEM_PROMPT,
    },
  });

  return response.text ?? "I couldn't generate a response.";
}

Step 4: Add Conversation History

Gemini supports multi-turn chat via the chats.create() API. Store a chat session per user:

import type { Chat } from "@google/genai";

const chats = new Map<string, Chat>();

function getChat(userJid: string): Chat {
  let chat = chats.get(userJid);
  if (!chat) {
    chat = ai.chats.create({
      model: "gemini-2.5-flash",
      config: {
        systemInstruction: SYSTEM_PROMPT,
      },
    });
    chats.set(userJid, chat);
  }
  return chat;
}

async function askGemini(userJid: string, userMessage: string): Promise<string> {
  const chat = getChat(userJid);
  const response = await chat.sendMessage({ message: userMessage });
  return response.text ?? "I couldn't generate a response.";
}

Complete Example

import { createClient } from "@whatsmeow-node/whatsmeow-node";
import { GoogleGenAI } from "@google/genai";
import type { Chat } from "@google/genai";

const client = createClient({ store: "session.db" });
const ai = new GoogleGenAI({ apiKey: process.env.GEMINI_API_KEY });

const SYSTEM_PROMPT =
  "You are a helpful WhatsApp assistant. Keep responses concise — under 500 characters when possible, since this is a chat interface.";

const chats = new Map<string, Chat>();

function getChat(userJid: string): Chat {
  let chat = chats.get(userJid);
  if (!chat) {
    chat = ai.chats.create({
      model: "gemini-2.5-flash",
      config: {
        systemInstruction: SYSTEM_PROMPT,
      },
    });
    chats.set(userJid, chat);
  }
  return chat;
}

async function askGemini(userJid: string, userMessage: string): Promise<string> {
  const chat = getChat(userJid);
  const response = await chat.sendMessage({ message: userMessage });
  return response.text ?? "I couldn't generate a response.";
}

client.on("message", async ({ info, message }) => {
  if (info.isFromMe) return;

  const text =
    (message.conversation as string) ??
    (message.extendedTextMessage as { text?: string } | undefined)?.text;
  if (!text) return;

  console.log(`${info.pushName}: ${text}`);
  await client.sendChatPresence(info.chat, "composing");

  try {
    const reply = await askGemini(info.sender, text);
    await client.sendMessage(info.chat, { conversation: reply });
    console.log(`→ ${reply.slice(0, 80)}...`);
  } catch (err) {
    console.error("Gemini API error:", err);
    await client.sendMessage(info.chat, {
      conversation: "Sorry, I'm having trouble right now. Try again in a moment.",
    });
  }
});

client.on("logged_out", ({ reason }) => {
  console.error(`Logged out: ${reason}`);
  client.close();
  process.exit(1);
});

async function main() {
  const { jid } = await client.init();
  if (!jid) {
    console.error("Not paired! See: How to Pair WhatsApp");
    process.exit(1);
  }
  await client.connect();
  await client.sendPresence("available");
  console.log("Gemini bot is online!");

  process.on("SIGINT", async () => {
    await client.sendPresence("unavailable");
    await client.disconnect();
    client.close();
    process.exit(0);
  });
}

main().catch(console.error);

Common Pitfalls

Echo loops

Always check info.isFromMe first. Without this, the bot sends a message, sees its own message, sends it to Gemini, and replies again — forever.

API key exposure

Never hardcode your API key in the source. Use environment variables (GEMINI_API_KEY) or a .env file (added to .gitignore).

Chat history is in-memory

The Chat objects are stored in a Map and lost on restart. For persistence, store conversation history in a database and recreate chats with the history option.

Prerequisites​

Step 1: Set Up Both Clients​

Step 2: Handle Incoming Messages​

Step 3: Send to Gemini​

Step 4: Add Conversation History​

Complete Example​

Common Pitfalls​

Related Guides

Connect to Claude AI

Connect to ChatGPT

Connect to Ollama

Connect to DeepSeek